{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/sota/action-classification-on-kinetics-400","task":{"name":"Action Classification","url":"/task/action-classification","note":null},"dataset":{"name":"Kinetics-400","url":"/dataset/kinetics"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"Image source: [The Kinetics Human Action Video Dataset](https://arxiv.org/pdf/1705.06950.pdf)","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Acc@1","Acc@5","FLOPs (G) x views","Clip acc@1","Parameters (M)","Clip acc@5"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction; the tokens 'score' and 'time' are not used on this page); null = not inferred, chart draws points only","by_metric":{"Acc@1":"higher","Acc@5":"higher","FLOPs (G) x views":"lower","Clip acc@1":"higher","Parameters (M)":null,"Clip acc@5":"higher"}},"counts":{"rows":207,"rows_with_code":179,"rows_with_paper_page":207,"rows_dated":207,"rows_using_additional_data":10},"rows":[{"rank_in_archive_order":1,"model":"OmniVec2","metrics":{"Acc@1":"93.6"},"uses_additional_data":false,"paper_date":"2024-01-01","paper":"/paper/omnivec2-a-novel-transformer-based-network","paper_url":"http://openaccess.thecvf.com//content/CVPR2024/html/Srivastava_OmniVec2_-_A_Novel_Transformer_based_Network_for_Large_Scale_CVPR_2024_paper.html","paper_title":"OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":2,"model":"FTP-UniFormerV2-L/14","metrics":{"Acc@1":"93.4"},"uses_additional_data":false,"paper_date":"2024-03-24","paper":"/paper/enhancing-video-transformers-for-action","paper_url":"https://arxiv.org/abs/2403.16128v1","paper_title":"Enhancing Video Transformers for Action Understanding with VLM-aided Training","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":3,"model":"InternVideo2-6B","metrics":{"Acc@1":"92.1"},"uses_additional_data":true,"paper_date":"2024-03-22","paper":"/paper/internvideo2-scaling-video-foundation-models","paper_url":"https://arxiv.org/abs/2403.15377v4","paper_title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","code":"https://github.com/opengvlab/internvideo","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":4,"model":"InternVideo2-1B","metrics":{"Acc@1":"91.6"},"uses_additional_data":true,"paper_date":"2024-03-22","paper":"/paper/internvideo2-scaling-video-foundation-models","paper_url":"https://arxiv.org/abs/2403.15377v4","paper_title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","code":"https://github.com/opengvlab/internvideo","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":5,"model":"InternVideo","metrics":{"Acc@1":"91.1"},"uses_additional_data":false,"paper_date":"2022-12-06","paper":"/paper/internvideo-general-video-foundation-models","paper_url":"https://arxiv.org/abs/2212.03191v2","paper_title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","code":"https://github.com/opengvlab/internvideo","n_code_links":2,"official":{"repos":["opengvlab/internvideo"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0,"sample_list":"/paper/internvideo-general-video-foundation-models#ran","syntology_url":"https://syntology.ai/paper/2212.03191","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.03191"}}}},{"rank_in_archive_order":6,"model":"OmniVec","metrics":{"Acc@1":"91.1"},"uses_additional_data":false,"paper_date":"2023-11-07","paper":"/paper/omnivec-learning-robust-representations-with","paper_url":"https://arxiv.org/abs/2311.05709v1","paper_title":"OmniVec: Learning robust representations with cross modal sharing","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":7,"model":"TubeViT-H (ImageNet-1k)","metrics":{"Acc@1":"90.9","Acc@5":"98.9","FLOPs (G) x views":"176400x4x3","Parameters (M)":"632"},"uses_additional_data":false,"paper_date":"2022-12-06","paper":"/paper/rethinking-video-vits-sparse-video-tubes-for","paper_url":"https://arxiv.org/abs/2212.03229v1","paper_title":"Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning","code":"https://github.com/daniel-code/TubeViT","n_code_links":1,"official":null,"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":1,"sample_list":"/paper/rethinking-video-vits-sparse-video-tubes-for#ran","syntology_url":"https://syntology.ai/paper/2212.03229","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.03229"}}}},{"rank_in_archive_order":8,"model":"Unmasked Teacher (ViT-L)","metrics":{"Acc@1":"90.6","Acc@5":"98.7","FLOPs (G) x views":"1434×3×4","Parameters (M)":"304"},"uses_additional_data":false,"paper_date":"2023-03-28","paper":"/paper/unmasked-teacher-towards-training-efficient","paper_url":"https://arxiv.org/abs/2303.16058v2","paper_title":"Unmasked Teacher: Towards Training-Efficient Video Foundation Models","code":"https://github.com/opengvlab/unmasked_teacher","n_code_links":1,"official":{"repos":["opengvlab/unmasked_teacher"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":0,"n_samples":8,"n_pointer_only_licence":3,"sample_list":"/paper/unmasked-teacher-towards-training-efficient#ran","syntology_url":"https://syntology.ai/paper/2303.16058","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.16058"}}}},{"rank_in_archive_order":9,"model":"UMT-L (ViT-L/16)","metrics":{"Acc@1":"90.6","Acc@5":"98.7"},"uses_additional_data":false,"paper_date":"2023-03-28","paper":"/paper/unmasked-teacher-towards-training-efficient","paper_url":"https://arxiv.org/abs/2303.16058v2","paper_title":"Unmasked Teacher: Towards Training-Efficient Video Foundation Models","code":"https://github.com/opengvlab/unmasked_teacher","n_code_links":1,"official":{"repos":["opengvlab/unmasked_teacher"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":0,"n_samples":8,"n_pointer_only_licence":3,"sample_list":"/paper/unmasked-teacher-towards-training-efficient#ran","syntology_url":"https://syntology.ai/paper/2303.16058","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.16058"}}}},{"rank_in_archive_order":10,"model":"TubeVit-L (ImageNet-1k)","metrics":{"Acc@1":"90.2","Acc@5":"98.6","FLOPs (G) x views":"95300x4x3","Parameters (M)":"307"},"uses_additional_data":false,"paper_date":"2022-12-06","paper":"/paper/rethinking-video-vits-sparse-video-tubes-for","paper_url":"https://arxiv.org/abs/2212.03229v1","paper_title":"Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning","code":"https://github.com/daniel-code/TubeViT","n_code_links":1,"official":null,"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":1,"sample_list":"/paper/rethinking-video-vits-sparse-video-tubes-for#ran","syntology_url":"https://syntology.ai/paper/2212.03229","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.03229"}}}},{"rank_in_archive_order":11,"model":"UniFormerV2-L (ViT-L, 336)","metrics":{"Acc@1":"90.0","Acc@5":"98.4","FLOPs (G) x views":"75300x3x2","Parameters (M)":"354"},"uses_additional_data":true,"paper_date":"2022-09-22","paper":"/paper/uniformerv2-spatiotemporal-learning-by-arming","paper_url":"https://openreview.net/forum?id=d77RVuVg-Mf","paper_title":"UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer","code":"https://github.com/OpenGVLab/UniFormerV2","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":12,"model":"VideoMAE V2-g (64x266x266)","metrics":{"Acc@1":"90.0","Acc@5":"98.4"},"uses_additional_data":false,"paper_date":"2023-03-29","paper":"/paper/videomae-v2-scaling-video-masked-autoencoders","paper_url":"https://arxiv.org/abs/2303.16727v2","paper_title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking","code":"https://github.com/OpenGVLab/VideoMAEv2","n_code_links":1,"official":{"repos":["OpenGVLab/VideoMAEv2"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"n_samples":6,"n_pointer_only_licence":0,"sample_list":"/paper/videomae-v2-scaling-video-masked-autoencoders#ran","syntology_url":"https://syntology.ai/paper/2303.16727","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.16727"}}}},{"rank_in_archive_order":13,"model":"FluxViT-B","metrics":{"Acc@1":"90.0","FLOPs (G) x views":"440x3x4","Parameters (M)":"97"},"uses_additional_data":true,"paper_date":"2025-03-18","paper":"/paper/make-your-training-flexible-towards","paper_url":"https://arxiv.org/abs/2503.14237v1","paper_title":"Make Your Training Flexible: Towards Deployment-Efficient Video Models","code":"https://github.com/opengvlab/fluxvit","n_code_links":1,"official":{"repos":["opengvlab/fluxvit"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":17,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":17,"n_constructed":0,"n_ran_checked":17,"n_instrument":0,"n_unverified":0,"n_samples":17,"n_pointer_only_licence":6,"sample_list":"/paper/make-your-training-flexible-towards#ran","syntology_url":"https://syntology.ai/paper/2503.14237","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.14237"}}}},{"rank_in_archive_order":14,"model":"MTV-H (WTS 60M)","metrics":{"Acc@1":"89.9","Acc@5":"98.3","FLOPs (G) x views":"735700x4x3"},"uses_additional_data":false,"paper_date":"2022-01-12","paper":"/paper/multiview-transformers-for-video-recognition","paper_url":"https://arxiv.org/abs/2201.04288v4","paper_title":"Multiview Transformers for Video Recognition","code":"https://github.com/google-research/scenic","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":15,"model":"TAdaFormer-L/14","metrics":{"Acc@1":"89.9"},"uses_additional_data":false,"paper_date":"2023-08-10","paper":"/paper/temporally-adaptive-models-for-efficient","paper_url":"https://arxiv.org/abs/2308.05787v1","paper_title":"Temporally-Adaptive Models for Efficient Video Understanding","code":"https://github.com/alibaba-mmai-research/TAdaConv","n_code_links":1,"official":{"repos":["alibaba-mmai-research/TAdaConv"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0,"sample_list":"/paper/temporally-adaptive-models-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2308.05787","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.05787"}}}},{"rank_in_archive_order":16,"model":"EVA","metrics":{"Acc@1":"89.7"},"uses_additional_data":false,"paper_date":"2022-11-14","paper":"/paper/eva-exploring-the-limits-of-masked-visual","paper_url":"https://arxiv.org/abs/2211.07636v2","paper_title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":6,"official":{"repos":["baaivision/eva","rwightman/pytorch-image-models"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":0,"sample_list":"/paper/eva-exploring-the-limits-of-masked-visual#ran","syntology_url":"https://syntology.ai/paper/2211.07636","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.07636"}}}},{"rank_in_archive_order":17,"model":"AM/12 ViT-B Dinov2","metrics":{"Acc@1":"89.6"},"uses_additional_data":false,"paper_date":"2024-11-04","paper":"/paper/am-flow-adapters-for-temporal-processing-in","paper_url":"https://arxiv.org/abs/2411.02065v1","paper_title":"AM Flow: Adapters for Temporal Processing in Action Recognition","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":18,"model":"ATM","metrics":{"Acc@1":"89.4","Acc@5":"98.3"},"uses_additional_data":false,"paper_date":"2023-07-18","paper":"/paper/what-can-simple-arithmetic-operations-do-for","paper_url":"https://arxiv.org/abs/2307.08908v2","paper_title":"What Can Simple Arithmetic Operations Do for Temporal Modeling?","code":"https://github.com/whwu95/ATM","n_code_links":2,"official":{"repos":["whwu95/ATM"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_samples":6,"n_pointer_only_licence":0,"sample_list":"/paper/what-can-simple-arithmetic-operations-do-for#ran","syntology_url":"https://syntology.ai/paper/2307.08908","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.08908"}}}},{"rank_in_archive_order":19,"model":"DejaVid","metrics":{"Acc@1":"89.1","Acc@5":"98.2"},"uses_additional_data":true,"paper_date":"2025-01-01","paper":"/paper/dejavid-encoder-agnostic-learned-temporal","paper_url":"http://openaccess.thecvf.com//content/CVPR2025/html/Ho_DejaVid_Encoder-Agnostic_Learned_Temporal_Matching_for_Video_Classification_CVPR_2025_paper.html","paper_title":"DejaVid: Encoder-Agnostic Learned Temporal Matching for Video Classification","code":"https://github.com/darrylho/dejavid","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":20,"model":"CoCa (finetuned)","metrics":{"Acc@1":"88.9"},"uses_additional_data":false,"paper_date":"2022-05-04","paper":"/paper/coca-contrastive-captioners-are-image-text","paper_url":"https://arxiv.org/abs/2205.01917v2","paper_title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","code":"https://github.com/mlfoundations/open_clip","n_code_links":6,"official":null,"syntology":{"n_ran":10,"n_constructed":5,"n_ran_checked":9,"n_instrument":1,"n_unverified":7,"n_samples":17,"n_pointer_only_licence":2,"sample_list":"/paper/coca-contrastive-captioners-are-image-text#ran","syntology_url":"https://syntology.ai/paper/2205.01917","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.01917"}}}},{"rank_in_archive_order":21,"model":"BIKE (CLIP ViT-L/14)","metrics":{"Acc@1":"88.7","Acc@5":"98.4"},"uses_additional_data":false,"paper_date":"2022-12-31","paper":"/paper/bidirectional-cross-modal-knowledge","paper_url":"https://arxiv.org/abs/2301.00182v2","paper_title":"Bidirectional Cross-Modal Knowledge Exploration for Video Recognition with Pre-trained Vision-Language Models","code":"https://github.com/whwu95/Cap4Video","n_code_links":5,"official":null,"syntology":null},{"rank_in_archive_order":22,"model":"ILA (ViT-L/14)","metrics":{"Acc@1":"88.7","Acc@5":"97.8"},"uses_additional_data":false,"paper_date":"2023-04-20","paper":"/paper/implicit-temporal-modeling-with-learnable","paper_url":"https://arxiv.org/abs/2304.10465v2","paper_title":"Implicit Temporal Modeling with Learnable Alignment for Video Recognition","code":"https://github.com/francis-rings/ila","n_code_links":1,"official":{"repos":["francis-rings/ila"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":4,"sample_list":"/paper/implicit-temporal-modeling-with-learnable#ran","syntology_url":"https://syntology.ai/paper/2304.10465","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.10465"}}}},{"rank_in_archive_order":23,"model":"Side4Video (EVA, ViT-E/14)","metrics":{"Acc@1":"88.6","Acc@5":"98.2"},"uses_additional_data":false,"paper_date":"2023-11-27","paper":"/paper/side4video-spatial-temporal-side-network-for","paper_url":"https://arxiv.org/abs/2311.15769v1","paper_title":"Side4Video: Spatial-Temporal Side Network for Memory-Efficient Image-to-Video Transfer Learning","code":"https://github.com/whwu95/ATM","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":24,"model":"TubeVit-B (ImageNet-1k)","metrics":{"Acc@1":"88.6","Acc@5":"97.6","FLOPs (G) x views":"8700x3x4","Parameters (M)":"86"},"uses_additional_data":false,"paper_date":"2022-12-06","paper":"/paper/rethinking-video-vits-sparse-video-tubes-for","paper_url":"https://arxiv.org/abs/2212.03229v1","paper_title":"Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning","code":"https://github.com/daniel-code/TubeViT","n_code_links":1,"official":null,"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":1,"sample_list":"/paper/rethinking-video-vits-sparse-video-tubes-for#ran","syntology_url":"https://syntology.ai/paper/2212.03229","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.03229"}}}},{"rank_in_archive_order":25,"model":"VideoMAE V2-g","metrics":{"Acc@1":"88.5","Acc@5":"98.1"},"uses_additional_data":true,"paper_date":"2023-03-29","paper":"/paper/videomae-v2-scaling-video-masked-autoencoders","paper_url":"https://arxiv.org/abs/2303.16727v2","paper_title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking","code":"https://github.com/OpenGVLab/VideoMAEv2","n_code_links":1,"official":{"repos":["OpenGVLab/VideoMAEv2"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"n_samples":6,"n_pointer_only_licence":0,"sample_list":"/paper/videomae-v2-scaling-video-masked-autoencoders#ran","syntology_url":"https://syntology.ai/paper/2303.16727","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.16727"}}}},{"rank_in_archive_order":26,"model":"ONE-PEACE","metrics":{"Acc@1":"88.1","Acc@5":"97.8"},"uses_additional_data":false,"paper_date":"2023-05-18","paper":"/paper/one-peace-exploring-one-general","paper_url":"https://arxiv.org/abs/2305.11172v1","paper_title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","code":"https://github.com/modelscope/modelscope","n_code_links":2,"official":{"repos":["OFA-Sys/ONE-PEACE"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":5,"n_constructed":2,"n_ran_checked":4,"n_instrument":1,"n_unverified":2,"n_samples":7,"n_pointer_only_licence":1,"sample_list":"/paper/one-peace-exploring-one-general#ran","syntology_url":"https://syntology.ai/paper/2305.11172","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11172"}}}},{"rank_in_archive_order":27,"model":"FluxViT-S","metrics":{"Acc@1":"88.0","FLOPs (G) x views":"154x3x4","Parameters (M)":"24"},"uses_additional_data":true,"paper_date":"2025-03-18","paper":"/paper/make-your-training-flexible-towards","paper_url":"https://arxiv.org/abs/2503.14237v1","paper_title":"Make Your Training Flexible: Towards Deployment-Efficient Video Models","code":"https://github.com/opengvlab/fluxvit","n_code_links":1,"official":{"repos":["opengvlab/fluxvit"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":17,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":17,"n_constructed":0,"n_ran_checked":17,"n_instrument":0,"n_unverified":0,"n_samples":17,"n_pointer_only_licence":6,"sample_list":"/paper/make-your-training-flexible-towards#ran","syntology_url":"https://syntology.ai/paper/2503.14237","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.14237"}}}},{"rank_in_archive_order":28,"model":"CoCa (frozen)","metrics":{"Acc@1":"88.0"},"uses_additional_data":false,"paper_date":"2022-05-04","paper":"/paper/coca-contrastive-captioners-are-image-text","paper_url":"https://arxiv.org/abs/2205.01917v2","paper_title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","code":"https://github.com/mlfoundations/open_clip","n_code_links":6,"official":null,"syntology":{"n_ran":10,"n_constructed":5,"n_ran_checked":9,"n_instrument":1,"n_unverified":7,"n_samples":17,"n_pointer_only_licence":2,"sample_list":"/paper/coca-contrastive-captioners-are-image-text#ran","syntology_url":"https://syntology.ai/paper/2205.01917","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.01917"}}}},{"rank_in_archive_order":29,"model":"ViT-22B","metrics":{"Acc@1":"88.0"},"uses_additional_data":false,"paper_date":"2023-02-10","paper":"/paper/scaling-vision-transformers-to-22-billion","paper_url":"https://arxiv.org/abs/2302.05442v1","paper_title":"Scaling Vision Transformers to 22 Billion Parameters","code":"https://github.com/lucidrains/flash-cosine-sim-attention","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":30,"model":"Text4Vis (CLIP ViT-L/14)","metrics":{"Acc@1":"87.8","Acc@5":"97.6"},"uses_additional_data":false,"paper_date":"2022-07-04","paper":"/paper/transferring-textual-knowledge-for-visual","paper_url":"https://arxiv.org/abs/2207.01297v4","paper_title":"Revisiting Classifier: Transferring Vision-Language Models for Video Recognition","code":"https://github.com/whwu95/Cap4Video","n_code_links":5,"official":null,"syntology":null},{"rank_in_archive_order":31,"model":"Hiera-H (no extra data)","metrics":{"Acc@1":"87.8"},"uses_additional_data":false,"paper_date":"2023-06-01","paper":"/paper/hiera-a-hierarchical-vision-transformer","paper_url":"https://arxiv.org/abs/2306.00989v1","paper_title":"Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles","code":"https://github.com/huggingface/pytorch-image-models","n_code_links":4,"official":{"repos":["facebookresearch/hiera"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_samples":6,"n_pointer_only_licence":0,"sample_list":"/paper/hiera-a-hierarchical-vision-transformer#ran","syntology_url":"https://syntology.ai/paper/2306.00989","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.00989"}}}},{"rank_in_archive_order":32,"model":"EVL (CLIP ViT-L/14@336px, frozen, 32 frames)","metrics":{"Acc@1":"87.7","Acc@5":"97.8"},"uses_additional_data":false,"paper_date":"2022-08-06","paper":"/paper/frozen-clip-models-are-efficient-video","paper_url":"https://arxiv.org/abs/2208.03550v1","paper_title":"Frozen CLIP Models are Efficient Video Learners","code":"https://github.com/opengvlab/efficient-video-recognition","n_code_links":2,"official":{"repos":["opengvlab/efficient-video-recognition"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":3,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]},"syntology":{"n_ran":5,"n_constructed":3,"n_ran_checked":5,"n_instrument":0,"n_unverified":5,"n_samples":10,"n_pointer_only_licence":10,"sample_list":"/paper/frozen-clip-models-are-efficient-video#ran","syntology_url":"https://syntology.ai/paper/2208.03550","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.03550"}}}},{"rank_in_archive_order":33,"model":"DualPath w/ ViT-L/14","metrics":{"Acc@1":"87.7","Acc@5":"97.8"},"uses_additional_data":false,"paper_date":"2023-03-17","paper":"/paper/dual-path-adaptation-from-image-to-video","paper_url":"https://arxiv.org/abs/2303.09857v1","paper_title":"Dual-path Adaptation from Image to Video Transformers","code":"https://github.com/park-jungin/dualpath","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":34,"model":"X-CLIP(ViT-L/14, CLIP)","metrics":{"Acc@1":"87.7","Acc@5":"97.4"},"uses_additional_data":false,"paper_date":"2022-08-04","paper":"/paper/expanding-language-image-pretrained-models","paper_url":"https://arxiv.org/abs/2208.02816v1","paper_title":"Expanding Language-Image Pretrained Models for General Video Recognition","code":"https://github.com/microsoft/videox","n_code_links":2,"official":{"repos":["microsoft/videox"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3,"sample_list":"/paper/expanding-language-image-pretrained-models#ran","syntology_url":"https://syntology.ai/paper/2208.02816","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.02816"}}}},{"rank_in_archive_order":35,"model":"AIM (CLIP ViT-L/14, 32x224)","metrics":{"Acc@1":"87.5","Acc@5":"97.7"},"uses_additional_data":true,"paper_date":"2023-02-06","paper":"/paper/aim-adapting-image-models-for-efficient-video","paper_url":"https://arxiv.org/abs/2302.03024v1","paper_title":"AIM: Adapting Image Models for Efficient Video Action Recognition","code":"https://github.com/taoyang1122/adapt-image-models","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":36,"model":"VideoMAE (no extra data, ViT-H, 32x320x320)","metrics":{"Acc@1":"87.4","Acc@5":"97.6"},"uses_additional_data":false,"paper_date":"2022-03-23","paper":"/paper/videomae-masked-autoencoders-are-data-1","paper_url":"https://arxiv.org/abs/2203.12602v3","paper_title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","code":"https://github.com/huggingface/transformers","n_code_links":9,"official":{"repos":["MCG-NJU/VideoMAE","MCG-NJU/VideoMAE-Action-Detection"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":6,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":10,"n_constructed":6,"n_ran_checked":8,"n_instrument":2,"n_unverified":3,"n_samples":13,"n_pointer_only_licence":12,"sample_list":"/paper/videomae-masked-autoencoders-are-data-1#ran","syntology_url":"https://syntology.ai/paper/2203.12602","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.12602"}}}},{"rank_in_archive_order":37,"model":"ST-Adapter (ViT-L, CLIP)","metrics":{"Acc@1":"87.2","Acc@5":"97.6"},"uses_additional_data":false,"paper_date":"2022-06-27","paper":"/paper/parameter-efficient-image-to-video-transfer","paper_url":"https://arxiv.org/abs/2206.13559v3","paper_title":"ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning","code":"https://github.com/linziyi96/st-adapter","n_code_links":1,"official":{"repos":["linziyi96/st-adapter"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":0,"n_samples":10,"n_pointer_only_licence":3,"sample_list":"/paper/parameter-efficient-image-to-video-transfer#ran","syntology_url":"https://syntology.ai/paper/2206.13559","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.13559"}}}},{"rank_in_archive_order":38,"model":"ZeroI2V ViT-L/14","metrics":{"Acc@1":"87.2","Acc@5":"97.6"},"uses_additional_data":false,"paper_date":"2023-10-02","paper":"/paper/zeroi2v-zero-cost-adaptation-of-pre-trained","paper_url":"https://arxiv.org/abs/2310.01324v2","paper_title":"ZeroI2V: Zero-Cost Adaptation of Pre-trained Transformers from Image to Video","code":"https://github.com/mcg-nju/zeroi2v","n_code_links":2,"official":{"repos":["mcg-nju/zeroi2v","leexinhao/ZeroI2V"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":0,"sample_list":"/paper/zeroi2v-zero-cost-adaptation-of-pre-trained#ran","syntology_url":"https://syntology.ai/paper/2310.01324","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.01324"}}}},{"rank_in_archive_order":39,"model":"CoVeR (JFT-3B)","metrics":{"Acc@1":"87.2","Acc@5":"97.5"},"uses_additional_data":false,"paper_date":"2021-12-14","paper":"/paper/co-training-transformer-with-videos-and","paper_url":"https://arxiv.org/abs/2112.07175v1","paper_title":"Co-training Transformer with Videos and Images Improves Action Recognition","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":40,"model":"MVD (K400 pretrain, ViT-H, 16x224x224)","metrics":{"Acc@1":"87.2","Acc@5":"97.4"},"uses_additional_data":false,"paper_date":"2022-12-08","paper":"/paper/masked-video-distillation-rethinking-masked","paper_url":"https://arxiv.org/abs/2212.04500v2","paper_title":"Masked Video Distillation: Rethinking Masked Feature Modeling for Self-supervised Video Representation Learning","code":"https://github.com/ruiwang2021/mvd","n_code_links":4,"official":null,"syntology":null},{"rank_in_archive_order":41,"model":"mPLUG-2","metrics":{"Acc@1":"87.1","Acc@5":"97.7"},"uses_additional_data":false,"paper_date":"2023-02-01","paper":"/paper/mplug-2-a-modularized-multi-modal-foundation","paper_url":"https://arxiv.org/abs/2302.00402v1","paper_title":"mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video","code":"https://github.com/modelscope/modelscope","n_code_links":4,"official":{"repos":["alibaba/AliceMind"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":17,"n_constructed":0,"n_ran_checked":8,"n_instrument":9,"n_unverified":2,"n_samples":19,"n_pointer_only_licence":2,"sample_list":"/paper/mplug-2-a-modularized-multi-modal-foundation#ran","syntology_url":"https://syntology.ai/paper/2302.00402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.00402"}}}},{"rank_in_archive_order":42,"model":"MaskFeat (K600, MViT-L)","metrics":{"Acc@1":"87.0","Acc@5":"97.4"},"uses_additional_data":false,"paper_date":"2021-12-16","paper":"/paper/masked-feature-prediction-for-self-supervised","paper_url":"https://arxiv.org/abs/2112.09133v2","paper_title":"Masked Feature Prediction for Self-Supervised Visual Pre-Training","code":"https://github.com/facebookresearch/SlowFast","n_code_links":6,"official":null,"syntology":null},{"rank_in_archive_order":43,"model":"VicTR (ViT-L/14)","metrics":{"Acc@1":"87.0"},"uses_additional_data":false,"paper_date":"2023-04-05","paper":"/paper/victr-video-conditioned-text-representations","paper_url":"https://arxiv.org/abs/2304.02560v2","paper_title":"VicTR: Video-conditioned Text Representations for Activity Recognition","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":44,"model":"Video-SwinV2-G (ImageNet-22k and external 70M pretrain)","metrics":{"Acc@1":"86.8"},"uses_additional_data":false,"paper_date":"2021-11-18","paper":"/paper/swin-transformer-v2-scaling-up-capacity-and","paper_url":"https://arxiv.org/abs/2111.09883v2","paper_title":"Swin Transformer V2: Scaling Up Capacity and Resolution","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":23,"official":{"repos":["microsoft/Swin-Transformer"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":17,"n_constructed":0,"n_ran_checked":14,"n_instrument":3,"n_unverified":13,"n_samples":30,"n_pointer_only_licence":4,"sample_list":"/paper/swin-transformer-v2-scaling-up-capacity-and#ran","syntology_url":"https://syntology.ai/paper/2111.09883","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.09883"}}}},{"rank_in_archive_order":45,"model":"MaskFeat (no extra data, MViT-L)","metrics":{"Acc@1":"86.7","Acc@5":"97.3"},"uses_additional_data":false,"paper_date":"2021-12-16","paper":"/paper/masked-feature-prediction-for-self-supervised","paper_url":"https://arxiv.org/abs/2112.09133v2","paper_title":"Masked Feature Prediction for Self-Supervised Visual Pre-Training","code":"https://github.com/facebookresearch/SlowFast","n_code_links":6,"official":null,"syntology":null},{"rank_in_archive_order":46,"model":"VideoMAE (no extra data, ViT-H)","metrics":{"Acc@1":"86.6","Acc@5":"97.1"},"uses_additional_data":false,"paper_date":"2022-03-23","paper":"/paper/videomae-masked-autoencoders-are-data-1","paper_url":"https://arxiv.org/abs/2203.12602v3","paper_title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","code":"https://github.com/huggingface/transformers","n_code_links":9,"official":{"repos":["MCG-NJU/VideoMAE","MCG-NJU/VideoMAE-Action-Detection"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":6,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":10,"n_constructed":6,"n_ran_checked":8,"n_instrument":2,"n_unverified":3,"n_samples":13,"n_pointer_only_licence":12,"sample_list":"/paper/videomae-masked-autoencoders-are-data-1#ran","syntology_url":"https://syntology.ai/paper/2203.12602","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.12602"}}}},{"rank_in_archive_order":47,"model":"MVD (K400 pretrain, ViT-L, 16x224x224)","metrics":{"Acc@1":"86.4","Acc@5":"97.0"},"uses_additional_data":false,"paper_date":"2022-12-08","paper":"/paper/masked-video-distillation-rethinking-masked","paper_url":"https://arxiv.org/abs/2212.04500v2","paper_title":"Masked Video Distillation: Rethinking Masked Feature Modeling for Self-supervised Video Representation Learning","code":"https://github.com/ruiwang2021/mvd","n_code_links":4,"official":null,"syntology":null},{"rank_in_archive_order":48,"model":"TAdaConvNeXtV2-B","metrics":{"Acc@1":"86.4"},"uses_additional_data":false,"paper_date":"2023-08-10","paper":"/paper/temporally-adaptive-models-for-efficient","paper_url":"https://arxiv.org/abs/2308.05787v1","paper_title":"Temporally-Adaptive Models for Efficient Video Understanding","code":"https://github.com/alibaba-mmai-research/TAdaConv","n_code_links":1,"official":{"repos":["alibaba-mmai-research/TAdaConv"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0,"sample_list":"/paper/temporally-adaptive-models-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2308.05787","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.05787"}}}},{"rank_in_archive_order":49,"model":"CoVeR (JFT-300M)","metrics":{"Acc@1":"86.3","Acc@5":"97.2"},"uses_additional_data":false,"paper_date":"2021-12-14","paper":"/paper/co-training-transformer-with-videos-and","paper_url":"https://arxiv.org/abs/2112.07175v1","paper_title":"Co-training Transformer with Videos and Images Improves Action Recognition","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":50,"model":"VideoMAE (no extra data, ViT-L, 32x320x320)","metrics":{"Acc@1":"86.1","Acc@5":"97.3"},"uses_additional_data":false,"paper_date":"2022-03-23","paper":"/paper/videomae-masked-autoencoders-are-data-1","paper_url":"https://arxiv.org/abs/2203.12602v3","paper_title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","code":"https://github.com/huggingface/transformers","n_code_links":9,"official":{"repos":["MCG-NJU/VideoMAE","MCG-NJU/VideoMAE-Action-Detection"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":6,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":10,"n_constructed":6,"n_ran_checked":8,"n_instrument":2,"n_unverified":3,"n_samples":13,"n_pointer_only_licence":12,"sample_list":"/paper/videomae-masked-autoencoders-are-data-1#ran","syntology_url":"https://syntology.ai/paper/2203.12602","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.12602"}}}},{"rank_in_archive_order":51,"model":"MViTv2-L (ImageNet-21k pretrain)","metrics":{"Acc@1":"86.1","Acc@5":"97.0"},"uses_additional_data":true,"paper_date":"2021-12-02","paper":"/paper/improved-multiscale-vision-transformers-for","paper_url":"https://arxiv.org/abs/2112.01526v2","paper_title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":9,"official":null,"syntology":null},{"rank_in_archive_order":52,"model":"ILA (ViT-B/16)","metrics":{"Acc@1":"85.7","Acc@5":"97.2"},"uses_additional_data":false,"paper_date":"2023-04-20","paper":"/paper/implicit-temporal-modeling-with-learnable","paper_url":"https://arxiv.org/abs/2304.10465v2","paper_title":"Implicit Temporal Modeling with Learnable Alignment for Video Recognition","code":"https://github.com/francis-rings/ila","n_code_links":1,"official":{"repos":["francis-rings/ila"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":4,"sample_list":"/paper/implicit-temporal-modeling-with-learnable#ran","syntology_url":"https://syntology.ai/paper/2304.10465","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.10465"}}}},{"rank_in_archive_order":53,"model":"DualPath w/ ViT-B/16","metrics":{"Acc@1":"85.4","Acc@5":"97.1"},"uses_additional_data":false,"paper_date":"2023-03-17","paper":"/paper/dual-path-adaptation-from-image-to-video","paper_url":"https://arxiv.org/abs/2303.09857v1","paper_title":"Dual-path Adaptation from Image to Video Transformers","code":"https://github.com/park-jungin/dualpath","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":54,"model":"TokenLearner 16at18 (L/10)","metrics":{"Acc@1":"85.4"},"uses_additional_data":false,"paper_date":"2021-06-21","paper":"/paper/tokenlearner-what-can-8-learned-tokens-do-for","paper_url":"https://arxiv.org/abs/2106.11297v4","paper_title":"TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?","code":"https://github.com/google-research/scenic","n_code_links":11,"official":{"repos":["google-research/scenic"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":3,"n_constructed":1,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0,"sample_list":"/paper/tokenlearner-what-can-8-learned-tokens-do-for#ran","syntology_url":"https://syntology.ai/paper/2106.11297","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.11297"}}}},{"rank_in_archive_order":55,"model":"MAR (50% mask, ViT-L, 16x4)","metrics":{"Acc@1":"85.3","Acc@5":"96.3"},"uses_additional_data":false,"paper_date":"2022-07-24","paper":"/paper/mar-masked-autoencoders-for-efficient-action","paper_url":"https://arxiv.org/abs/2207.11660v1","paper_title":"MAR: Masked Autoencoders for Efficient Action Recognition","code":"https://github.com/alibaba-mmai-research/masked-action-recognition","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":56,"model":"CAST(ViT-B/16)","metrics":{"Acc@1":"85.3"},"uses_additional_data":false,"paper_date":"2023-11-30","paper":"/paper/cast-cross-attention-in-space-and-time-for-1","paper_url":"https://arxiv.org/abs/2311.18825v2","paper_title":"CAST: Cross-Attention in Space and Time for Video Action Recognition","code":"https://github.com/khu-vll/cast","n_code_links":1,"official":null,"syntology":{"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":6,"n_samples":17,"n_pointer_only_licence":17,"sample_list":"/paper/cast-cross-attention-in-space-and-time-for-1#ran","syntology_url":"https://syntology.ai/paper/2311.18825","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.18825"}}}},{"rank_in_archive_order":57,"model":"VideoMAE (no extra data, ViT-L, 16x4)","metrics":{"Acc@1":"85.2","Acc@5":"96.8"},"uses_additional_data":false,"paper_date":"2022-03-23","paper":"/paper/videomae-masked-autoencoders-are-data-1","paper_url":"https://arxiv.org/abs/2203.12602v3","paper_title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","code":"https://github.com/huggingface/transformers","n_code_links":9,"official":{"repos":["MCG-NJU/VideoMAE","MCG-NJU/VideoMAE-Action-Detection"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":6,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":10,"n_constructed":6,"n_ran_checked":8,"n_instrument":2,"n_unverified":3,"n_samples":13,"n_pointer_only_licence":12,"sample_list":"/paper/videomae-masked-autoencoders-are-data-1#ran","syntology_url":"https://syntology.ai/paper/2203.12602","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.12602"}}}},{"rank_in_archive_order":58,"model":"ViC-MAE (ViT-L)","metrics":{"Acc@1":"85.1"},"uses_additional_data":false,"paper_date":"2023-03-21","paper":"/paper/visual-representation-learning-from-unlabeled","paper_url":"https://arxiv.org/abs/2303.12001v3","paper_title":"ViC-MAE: Self-Supervised Representation Learning from Images and Video with Contrastive Masked Autoencoders","code":"https://github.com/jeffhernandez1995/vic-mae","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":59,"model":"VideoMamba-M800","metrics":{"Acc@1":"85.0"},"uses_additional_data":false,"paper_date":"2024-03-11","paper":"/paper/videomamba-state-space-model-for-efficient","paper_url":"https://arxiv.org/abs/2403.06977v2","paper_title":"VideoMamba: State Space Model for Efficient Video Understanding","code":"https://github.com/opengvlab/videomamba","n_code_links":2,"official":{"repos":["opengvlab/videomamba"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":9,"n_constructed":5,"n_ran_checked":6,"n_instrument":3,"n_unverified":6,"n_samples":15,"n_pointer_only_licence":0,"sample_list":"/paper/videomamba-state-space-model-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2403.06977","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.06977"}}}},{"rank_in_archive_order":60,"model":"Swin-L (384x384, ImageNet-21k pretrain)","metrics":{"Acc@1":"84.9","Acc@5":"96.7"},"uses_additional_data":false,"paper_date":"2021-06-24","paper":"/paper/video-swin-transformer","paper_url":"https://arxiv.org/abs/2106.13230v1","paper_title":"Video Swin Transformer","code":"https://github.com/open-mmlab/mmaction2","n_code_links":15,"official":{"repos":["SwinTransformer/Video-Swin-Transformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":19,"n_constructed":0,"n_ran_checked":14,"n_instrument":5,"n_unverified":13,"n_samples":32,"n_pointer_only_licence":7,"sample_list":"/paper/video-swin-transformer#ran","syntology_url":"https://syntology.ai/paper/2106.13230","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.13230"}}}},{"rank_in_archive_order":61,"model":"ViViT-H/16x2 (JFT)","metrics":{"Acc@1":"84.9","Acc@5":"95.8"},"uses_additional_data":false,"paper_date":"2021-03-29","paper":"/paper/2103-15691","paper_url":"https://arxiv.org/abs/2103.15691v2","paper_title":"ViViT: A Video Vision Transformer","code":"https://github.com/google-research/scenic","n_code_links":10,"official":{"repos":["google-research/scenic"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"syntology":{"n_ran":14,"n_constructed":10,"n_ran_checked":13,"n_instrument":1,"n_unverified":7,"n_samples":21,"n_pointer_only_licence":1,"sample_list":"/paper/2103-15691#ran","syntology_url":"https://syntology.ai/paper/2103.15691","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.15691"}}}},{"rank_in_archive_order":62,"model":"OMNIVORE (Swin-L)","metrics":{"Acc@1":"84.1","Acc@5":"96.1"},"uses_additional_data":false,"paper_date":"2022-01-20","paper":"/paper/omnivore-a-single-model-for-many-visual","paper_url":"https://arxiv.org/abs/2201.08377v2","paper_title":"Omnivore: A Single Model for Many Visual Modalities","code":"https://github.com/towhee-io/towhee","n_code_links":2,"official":{"repos":["facebookresearch/omnivore"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":1,"sample_list":"/paper/omnivore-a-single-model-for-many-visual#ran","syntology_url":"https://syntology.ai/paper/2201.08377","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.08377"}}}},{"rank_in_archive_order":63,"model":"OMNIVORE (Swin-B)","metrics":{"Acc@1":"84.0","Acc@5":"96.2"},"uses_additional_data":false,"paper_date":"2022-01-20","paper":"/paper/omnivore-a-single-model-for-many-visual","paper_url":"https://arxiv.org/abs/2201.08377v2","paper_title":"Omnivore: A Single Model for Many Visual Modalities","code":"https://github.com/towhee-io/towhee","n_code_links":2,"official":{"repos":["facebookresearch/omnivore"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":1,"sample_list":"/paper/omnivore-a-single-model-for-many-visual#ran","syntology_url":"https://syntology.ai/paper/2201.08377","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.08377"}}}},{"rank_in_archive_order":64,"model":"MAR (75% mask, ViT-L, 16x4)","metrics":{"Acc@1":"83.9","Acc@5":"96.0"},"uses_additional_data":false,"paper_date":"2022-07-24","paper":"/paper/mar-masked-autoencoders-for-efficient-action","paper_url":"https://arxiv.org/abs/2207.11660v1","paper_title":"MAR: Masked Autoencoders for Efficient Action Recognition","code":"https://github.com/alibaba-mmai-research/masked-action-recognition","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":65,"model":"ActionCLIP (CLIP-pretrained)","metrics":{"Acc@1":"83.8","Acc@5":"97.1"},"uses_additional_data":false,"paper_date":"2021-09-17","paper":"/paper/actionclip-a-new-paradigm-for-video-action","paper_url":"https://arxiv.org/abs/2109.08472v1","paper_title":"ActionCLIP: A New Paradigm for Video Action Recognition","code":"https://github.com/towhee-io/towhee","n_code_links":2,"official":{"repos":["sallymmx/actionclip"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]},"syntology":{"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":3,"n_samples":9,"n_pointer_only_licence":4,"sample_list":"/paper/actionclip-a-new-paradigm-for-video-action#ran","syntology_url":"https://syntology.ai/paper/2109.08472","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.08472"}}}},{"rank_in_archive_order":66,"model":"OmniSource irCSN-152 (IG-Kinetics-65M pretrain)","metrics":{"Acc@1":"83.6"},"uses_additional_data":false,"paper_date":"2020-03-29","paper":"/paper/omni-sourced-webly-supervised-learning-for","paper_url":"https://arxiv.org/abs/2003.13042v2","paper_title":"Omni-sourced Webly-supervised Learning for Video Recognition","code":"https://github.com/open-mmlab/mmaction2","n_code_links":3,"official":{"repos":["open-mmlab/mmaction"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]},"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":3,"n_samples":13,"n_pointer_only_licence":0,"sample_list":"/paper/omni-sourced-webly-supervised-learning-for#ran","syntology_url":"https://syntology.ai/paper/2003.13042","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.13042"}}}},{"rank_in_archive_order":67,"model":"MVD (K400 pretrain, ViT-B, 16x224x224)","metrics":{"Acc@1":"83.4","Acc@5":"95.8"},"uses_additional_data":false,"paper_date":"2022-12-08","paper":"/paper/masked-video-distillation-rethinking-masked","paper_url":"https://arxiv.org/abs/2212.04500v2","paper_title":"Masked Video Distillation: Rethinking Masked Feature Modeling for Self-supervised Video Representation Learning","code":"https://github.com/ruiwang2021/mvd","n_code_links":4,"official":null,"syntology":null},{"rank_in_archive_order":68,"model":"StructViT-B-4-1","metrics":{"Acc@1":"83.4"},"uses_additional_data":false,"paper_date":"2024-04-05","paper":"/paper/learning-correlation-structures-for-vision","paper_url":"https://arxiv.org/abs/2404.03924v1","paper_title":"Learning Correlation Structures for Vision Transformers","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":69,"model":"Swin-L (ImageNet-21k pretrain)","metrics":{"Acc@1":"83.1","Acc@5":"95.9"},"uses_additional_data":false,"paper_date":"2021-06-24","paper":"/paper/video-swin-transformer","paper_url":"https://arxiv.org/abs/2106.13230v1","paper_title":"Video Swin Transformer","code":"https://github.com/open-mmlab/mmaction2","n_code_links":15,"official":{"repos":["SwinTransformer/Video-Swin-Transformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":19,"n_constructed":0,"n_ran_checked":14,"n_instrument":5,"n_unverified":13,"n_samples":32,"n_pointer_only_licence":7,"sample_list":"/paper/video-swin-transformer#ran","syntology_url":"https://syntology.ai/paper/2106.13230","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.13230"}}}},{"rank_in_archive_order":70,"model":"SIFA","metrics":{"Acc@1":"83.1"},"uses_additional_data":false,"paper_date":"2022-06-14","paper":"/paper/stand-alone-inter-frame-attention-in-video-1","paper_url":"https://arxiv.org/abs/2206.06931v1","paper_title":"Stand-Alone Inter-Frame Attention in Video Models","code":"https://github.com/fuchenustc/sifa","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":71,"model":"UniFormer-B (ImageNet-1K)","metrics":{"Acc@1":"82.9","Acc@5":"94.5","FLOPs (G) x views":"259x4"},"uses_additional_data":false,"paper_date":"2021-09-29","paper":"/paper/uniformer-unified-transformer-for-efficient","paper_url":"https://openreview.net/forum?id=nBU_u6DLvoK","paper_title":"UniFormer: Unified Transformer for Efficient Spatial-Temporal Representation Learning","code":"https://github.com/towhee-io/towhee","n_code_links":3,"official":null,"syntology":null},{"rank_in_archive_order":72,"model":"irCSN-152 (IG-Kinetics-65M pretrain)","metrics":{"Acc@1":"82.8"},"uses_additional_data":false,"paper_date":"2019-05-02","paper":"/paper/large-scale-weakly-supervised-pre-training","paper_url":"http://arxiv.org/abs/1905.00561v1","paper_title":"Large-scale weakly-supervised pre-training for video action recognition","code":"https://github.com/microsoft/computervision-recipes","n_code_links":3,"official":null,"syntology":{"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":9,"n_samples":21,"n_pointer_only_licence":0,"sample_list":"/paper/large-scale-weakly-supervised-pre-training#ran","syntology_url":"https://syntology.ai/paper/1905.00561","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.00561"}}}},{"rank_in_archive_order":73,"model":"DirecFormer","metrics":{"Acc@1":"82.75","Acc@5":"94.86"},"uses_additional_data":false,"paper_date":"2022-03-19","paper":"/paper/direcformer-a-directed-attention-in","paper_url":"https://arxiv.org/abs/2203.10233v1","paper_title":"DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition","code":"https://github.com/uark-cviu/direcformer","n_code_links":1,"official":{"repos":["uark-cviu/direcformer"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]},"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":3,"n_samples":8,"n_pointer_only_licence":8,"sample_list":"/paper/direcformer-a-directed-attention-in#ran","syntology_url":"https://syntology.ai/paper/2203.10233","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.10233"}}}},{"rank_in_archive_order":74,"model":"Swin-B (ImageNet-21k pretrain)","metrics":{"Acc@1":"82.7","Acc@5":"95.5"},"uses_additional_data":false,"paper_date":"2021-06-24","paper":"/paper/video-swin-transformer","paper_url":"https://arxiv.org/abs/2106.13230v1","paper_title":"Video Swin Transformer","code":"https://github.com/open-mmlab/mmaction2","n_code_links":15,"official":{"repos":["SwinTransformer/Video-Swin-Transformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":19,"n_constructed":0,"n_ran_checked":14,"n_instrument":5,"n_unverified":13,"n_samples":32,"n_pointer_only_licence":7,"sample_list":"/paper/video-swin-transformer#ran","syntology_url":"https://syntology.ai/paper/2106.13230","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.13230"}}}},{"rank_in_archive_order":75,"model":"ir-CSN-152 (IG-65M pretraining)","metrics":{"Acc@1":"82.6"},"uses_additional_data":false,"paper_date":"2019-04-04","paper":"/paper/video-classification-with-channel-separated","paper_url":"https://arxiv.org/abs/1904.02811v4","paper_title":"Video Classification with Channel-Separated Convolutional Networks","code":"https://github.com/open-mmlab/mmaction2","n_code_links":7,"official":{"repos":["facebookresearch/VMZ"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":0,"sample_list":"/paper/video-classification-with-channel-separated#ran","syntology_url":"https://syntology.ai/paper/1904.02811","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.02811"}}}},{"rank_in_archive_order":76,"model":"ip-CSN-152 (IG-65M pretraining)","metrics":{"Acc@1":"82.5","Acc@5":"95.3"},"uses_additional_data":false,"paper_date":"2019-04-04","paper":"/paper/video-classification-with-channel-separated","paper_url":"https://arxiv.org/abs/1904.02811v4","paper_title":"Video Classification with Channel-Separated Convolutional Networks","code":"https://github.com/open-mmlab/mmaction2","n_code_links":7,"official":{"repos":["facebookresearch/VMZ"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":0,"sample_list":"/paper/video-classification-with-channel-separated#ran","syntology_url":"https://syntology.ai/paper/1904.02811","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.02811"}}}},{"rank_in_archive_order":77,"model":"TPS","metrics":{"Acc@1":"82.5"},"uses_additional_data":false,"paper_date":"2022-07-27","paper":"/paper/spatiotemporal-self-attention-modeling-with","paper_url":"https://arxiv.org/abs/2207.13259v1","paper_title":"Spatiotemporal Self-attention Modeling with Temporal Patch Shift for Action Recognition","code":"https://github.com/martinxm/tps","n_code_links":1,"official":{"repos":["martinxm/tps"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0,"sample_list":"/paper/spatiotemporal-self-attention-modeling-with#ran","syntology_url":"https://syntology.ai/paper/2207.13259","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.13259"}}}},{"rank_in_archive_order":78,"model":"ILA (ViT-B/32)","metrics":{"Acc@1":"82.4","Acc@5":"95.8"},"uses_additional_data":false,"paper_date":"2023-04-20","paper":"/paper/implicit-temporal-modeling-with-learnable","paper_url":"https://arxiv.org/abs/2304.10465v2","paper_title":"Implicit Temporal Modeling with Learnable Alignment for Video Recognition","code":"https://github.com/francis-rings/ila","n_code_links":1,"official":{"repos":["francis-rings/ila"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":4,"sample_list":"/paper/implicit-temporal-modeling-with-learnable#ran","syntology_url":"https://syntology.ai/paper/2304.10465","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.10465"}}}},{"rank_in_archive_order":79,"model":"AMD(ViT-B/16)","metrics":{"Acc@1":"82.2","Acc@5":"95.3","FLOPs (G) x views":"180x15","Parameters (M)":"87"},"uses_additional_data":false,"paper_date":"2023-11-06","paper":"/paper/asymmetric-masked-distillation-for-pre","paper_url":"https://arxiv.org/abs/2311.03149v2","paper_title":"Asymmetric Masked Distillation for Pre-Training Small Foundation Models","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":80,"model":"VATT-Large","metrics":{"Acc@1":"82.1","Acc@5":"95.5"},"uses_additional_data":false,"paper_date":"2021-04-22","paper":"/paper/vatt-transformers-for-multimodal-self","paper_url":"https://arxiv.org/abs/2104.11178v3","paper_title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","code":"https://github.com/google-research/google-research/tree/master/vatt","n_code_links":5,"official":{"repos":["google-research/google-research"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":5,"n_constructed":4,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_samples":8,"n_pointer_only_licence":8,"sample_list":"/paper/vatt-transformers-for-multimodal-self#ran","syntology_url":"https://syntology.ai/paper/2104.11178","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.11178"}}}},{"rank_in_archive_order":81,"model":"AdaMAE","metrics":{"Acc@1":"81.7","Acc@5":"95.2"},"uses_additional_data":false,"paper_date":"2022-11-16","paper":"/paper/adamae-adaptive-masking-for-efficient","paper_url":"https://arxiv.org/abs/2211.09120v1","paper_title":"AdaMAE: Adaptive Masking for Efficient Spatiotemporal Learning with Masked Autoencoders","code":"https://github.com/wgcban/adamae","n_code_links":2,"official":{"repos":["wgcban/adamae"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":18,"n_constructed":0,"n_ran_checked":13,"n_instrument":5,"n_unverified":7,"n_samples":25,"n_pointer_only_licence":6,"sample_list":"/paper/adamae-adaptive-masking-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2211.09120","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.09120"}}}},{"rank_in_archive_order":82,"model":"VideoMAE (no extra data, ViT-B, 16x4)","metrics":{"Acc@1":"81.5","Acc@5":"95.1"},"uses_additional_data":false,"paper_date":"2022-03-23","paper":"/paper/videomae-masked-autoencoders-are-data-1","paper_url":"https://arxiv.org/abs/2203.12602v3","paper_title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","code":"https://github.com/huggingface/transformers","n_code_links":9,"official":{"repos":["MCG-NJU/VideoMAE","MCG-NJU/VideoMAE-Action-Detection"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":6,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":10,"n_constructed":6,"n_ran_checked":8,"n_instrument":2,"n_unverified":3,"n_samples":13,"n_pointer_only_licence":12,"sample_list":"/paper/videomae-masked-autoencoders-are-data-1#ran","syntology_url":"https://syntology.ai/paper/2203.12602","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.12602"}}}},{"rank_in_archive_order":83,"model":"MoViNet-A6","metrics":{"Acc@1":"81.5","FLOPs (G) x views":"386x1"},"uses_additional_data":false,"paper_date":"2021-03-21","paper":"/paper/movinets-mobile-video-networks-for-efficient","paper_url":"https://arxiv.org/abs/2103.11511v2","paper_title":"MoViNets: Mobile Video Networks for Efficient Video Recognition","code":"https://github.com/tensorflow/models","n_code_links":3,"official":{"repos":["tensorflow/models"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":9,"n_constructed":6,"n_ran_checked":8,"n_instrument":1,"n_unverified":4,"n_samples":13,"n_pointer_only_licence":0,"sample_list":"/paper/movinets-mobile-video-networks-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2103.11511","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.11511"}}}},{"rank_in_archive_order":84,"model":"MLP-3D","metrics":{"Acc@1":"81.4"},"uses_additional_data":false,"paper_date":"2022-06-13","paper":"/paper/mlp-3d-a-mlp-like-3d-architecture-with-1","paper_url":"https://arxiv.org/abs/2206.06292v1","paper_title":"MLP-3D: A MLP-like 3D Architecture with Grouped Time Mixing","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":85,"model":"R[2+1]D-152 (IG-65M pretraining)","metrics":{"Acc@1":"81.3","Acc@5":"95.1"},"uses_additional_data":false,"paper_date":"2019-04-04","paper":"/paper/video-classification-with-channel-separated","paper_url":"https://arxiv.org/abs/1904.02811v4","paper_title":"Video Classification with Channel-Separated Convolutional Networks","code":"https://github.com/open-mmlab/mmaction2","n_code_links":7,"official":{"repos":["facebookresearch/VMZ"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":0,"sample_list":"/paper/video-classification-with-channel-separated#ran","syntology_url":"https://syntology.ai/paper/1904.02811","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.02811"}}}},{"rank_in_archive_order":86,"model":"LGD-3D Two-stream (ResNet-101)","metrics":{"Acc@1":"81.2","Acc@5":"95.2"},"uses_additional_data":false,"paper_date":"2019-06-13","paper":"/paper/learning-spatio-temporal-representation-with-3","paper_url":"https://arxiv.org/abs/1906.05571v1","paper_title":"Learning Spatio-Temporal Representation with Local and Global Diffusion","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":87,"model":"MViT-B, 64x3","metrics":{"Acc@1":"81.2","Acc@5":"95.1"},"uses_additional_data":false,"paper_date":"2021-04-22","paper":"/paper/multiscale-vision-transformers","paper_url":"https://arxiv.org/abs/2104.11227v1","paper_title":"Multiscale Vision Transformers","code":"https://github.com/facebookresearch/SlowFast","n_code_links":8,"official":{"repos":["facebookresearch/SlowFast"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":13,"n_constructed":10,"n_ran_checked":11,"n_instrument":2,"n_unverified":13,"n_samples":26,"n_pointer_only_licence":5,"sample_list":"/paper/multiscale-vision-transformers#ran","syntology_url":"https://syntology.ai/paper/2104.11227","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.11227"}}}},{"rank_in_archive_order":88,"model":"Motionformer-HR","metrics":{"Acc@1":"81.1","Acc@5":"95.2"},"uses_additional_data":false,"paper_date":"2021-06-09","paper":"/paper/keeping-your-eye-on-the-ball-trajectory","paper_url":"https://arxiv.org/abs/2106.05392v2","paper_title":"Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers","code":"https://github.com/facebookresearch/xformers","n_code_links":2,"official":{"repos":["facebookresearch/Motionformer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":2,"sample_list":"/paper/keeping-your-eye-on-the-ball-trajectory#ran","syntology_url":"https://syntology.ai/paper/2106.05392","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.05392"}}}},{"rank_in_archive_order":89,"model":"MVD (K400 pretrain, ViT-S, 16x224x224)","metrics":{"Acc@1":"81.0","Acc@5":"94.8"},"uses_additional_data":false,"paper_date":"2022-12-08","paper":"/paper/masked-video-distillation-rethinking-masked","paper_url":"https://arxiv.org/abs/2212.04500v2","paper_title":"Masked Video Distillation: Rethinking Masked Feature Modeling for Self-supervised Video Representation Learning","code":"https://github.com/ruiwang2021/mvd","n_code_links":4,"official":null,"syntology":null},{"rank_in_archive_order":90,"model":"MAR (50% mask, ViT-B, 16x4)","metrics":{"Acc@1":"81.0","Acc@5":"94.4"},"uses_additional_data":false,"paper_date":"2022-07-24","paper":"/paper/mar-masked-autoencoders-for-efficient-action","paper_url":"https://arxiv.org/abs/2207.11660v1","paper_title":"MAR: Masked Autoencoders for Efficient Action Recognition","code":"https://github.com/alibaba-mmai-research/masked-action-recognition","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":91,"model":"MoViNet-A5","metrics":{"Acc@1":"80.9","Acc@5":"94.9","FLOPs (G) x views":"281x1"},"uses_additional_data":false,"paper_date":"2021-03-21","paper":"/paper/movinets-mobile-video-networks-for-efficient","paper_url":"https://arxiv.org/abs/2103.11511v2","paper_title":"MoViNets: Mobile Video Networks for Efficient Video Recognition","code":"https://github.com/tensorflow/models","n_code_links":3,"official":{"repos":["tensorflow/models"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":9,"n_constructed":6,"n_ran_checked":8,"n_instrument":1,"n_unverified":4,"n_samples":13,"n_pointer_only_licence":0,"sample_list":"/paper/movinets-mobile-video-networks-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2103.11511","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.11511"}}}},{"rank_in_archive_order":92,"model":"MBT (AV)","metrics":{"Acc@1":"80.8","Acc@5":"94.6"},"uses_additional_data":false,"paper_date":"2021-06-30","paper":"/paper/attention-bottlenecks-for-multimodal-fusion","paper_url":"https://arxiv.org/abs/2107.00135v3","paper_title":"Attention Bottlenecks for Multimodal Fusion","code":"https://github.com/google-research/scenic/tree/main/scenic/projects/mbt","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":93,"model":"TimeSformer-L","metrics":{"Acc@1":"80.7","Acc@5":"94.7","FLOPs (G) x views":"7140x3","Parameters (M)":"121.4"},"uses_additional_data":false,"paper_date":"2021-02-09","paper":"/paper/is-space-time-attention-all-you-need-for","paper_url":"https://arxiv.org/abs/2102.05095v4","paper_title":"Is Space-Time Attention All You Need for Video Understanding?","code":"https://github.com/open-mmlab/mmaction2","n_code_links":16,"official":{"repos":["facebookresearch/TimeSformer"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"syntology":{"n_ran":35,"n_constructed":17,"n_ran_checked":21,"n_instrument":14,"n_unverified":8,"n_samples":43,"n_pointer_only_licence":14,"sample_list":"/paper/is-space-time-attention-all-you-need-for#ran","syntology_url":"https://syntology.ai/paper/2102.05095","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.05095"}}}},{"rank_in_archive_order":94,"model":"Swin-B (ImageNet-1k pretrain)","metrics":{"Acc@1":"80.6","Acc@5":"94.6"},"uses_additional_data":false,"paper_date":"2021-06-24","paper":"/paper/video-swin-transformer","paper_url":"https://arxiv.org/abs/2106.13230v1","paper_title":"Video Swin Transformer","code":"https://github.com/open-mmlab/mmaction2","n_code_links":15,"official":{"repos":["SwinTransformer/Video-Swin-Transformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":19,"n_constructed":0,"n_ran_checked":14,"n_instrument":5,"n_unverified":13,"n_samples":32,"n_pointer_only_licence":7,"sample_list":"/paper/video-swin-transformer#ran","syntology_url":"https://syntology.ai/paper/2106.13230","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.13230"}}}},{"rank_in_archive_order":95,"model":"Swin-S (ImageNet-1k pretrain)","metrics":{"Acc@1":"80.6","Acc@5":"94.5"},"uses_additional_data":false,"paper_date":"2021-06-24","paper":"/paper/video-swin-transformer","paper_url":"https://arxiv.org/abs/2106.13230v1","paper_title":"Video Swin Transformer","code":"https://github.com/open-mmlab/mmaction2","n_code_links":15,"official":{"repos":["SwinTransformer/Video-Swin-Transformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":19,"n_constructed":0,"n_ran_checked":14,"n_instrument":5,"n_unverified":13,"n_samples":32,"n_pointer_only_licence":7,"sample_list":"/paper/video-swin-transformer#ran","syntology_url":"https://syntology.ai/paper/2106.13230","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.13230"}}}},{"rank_in_archive_order":96,"model":"En-VidTr-L","metrics":{"Acc@1":"80.5","Acc@5":"94.6"},"uses_additional_data":false,"paper_date":"2021-04-23","paper":"/paper/vidtr-video-transformer-without-convolutions","paper_url":"https://arxiv.org/abs/2104.11746v2","paper_title":"VidTr: Video Transformer Without Convolutions","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":97,"model":"MoViNet-A4","metrics":{"Acc@1":"80.5","Acc@5":"94.5","FLOPs (G) x views":"105x1"},"uses_additional_data":false,"paper_date":"2021-03-21","paper":"/paper/movinets-mobile-video-networks-for-efficient","paper_url":"https://arxiv.org/abs/2103.11511v2","paper_title":"MoViNets: Mobile Video Networks for Efficient Video Recognition","code":"https://github.com/tensorflow/models","n_code_links":3,"official":{"repos":["tensorflow/models"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":9,"n_constructed":6,"n_ran_checked":8,"n_instrument":1,"n_unverified":4,"n_samples":13,"n_pointer_only_licence":0,"sample_list":"/paper/movinets-mobile-video-networks-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2103.11511","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.11511"}}}},{"rank_in_archive_order":98,"model":"OmniSource SlowOnly R101 8x8(ImageNet pretrain)","metrics":{"Acc@1":"80.5","Acc@5":"94.4"},"uses_additional_data":false,"paper_date":"2020-03-29","paper":"/paper/omni-sourced-webly-supervised-learning-for","paper_url":"https://arxiv.org/abs/2003.13042v2","paper_title":"Omni-sourced Webly-supervised Learning for Video Recognition","code":"https://github.com/open-mmlab/mmaction2","n_code_links":3,"official":{"repos":["open-mmlab/mmaction"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]},"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":3,"n_samples":13,"n_pointer_only_licence":0,"sample_list":"/paper/omni-sourced-webly-supervised-learning-for#ran","syntology_url":"https://syntology.ai/paper/2003.13042","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.13042"}}}},{"rank_in_archive_order":99,"model":"STAM (64 Frames)","metrics":{"Acc@1":"80.5","FLOPs (G) x views":"1040x1"},"uses_additional_data":false,"paper_date":"2021-03-25","paper":"/paper/an-image-is-worth-16x16-words-what-is-a-video","paper_url":"https://arxiv.org/abs/2103.13915v2","paper_title":"An Image is Worth 16x16 Words, What is a Video Worth?","code":"https://github.com/Alibaba-MIIL/STAM","n_code_links":2,"official":{"repos":["Alibaba-MIIL/STAM"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"syntology":{"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0,"sample_list":"/paper/an-image-is-worth-16x16-words-what-is-a-video#ran","syntology_url":"https://syntology.ai/paper/2103.13915","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.13915"}}}},{"rank_in_archive_order":100,"model":"X3D-XXL","metrics":{"Acc@1":"80.4","Acc@5":"94.6"},"uses_additional_data":false,"paper_date":"2020-04-09","paper":"/paper/x3d-expanding-architectures-for-efficient","paper_url":"https://arxiv.org/abs/2004.04730v1","paper_title":"X3D: Expanding Architectures for Efficient Video Recognition","code":"https://github.com/facebookresearch/SlowFast","n_code_links":8,"official":{"repos":["facebookresearch/SlowFast"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":4,"n_samples":15,"n_pointer_only_licence":0,"sample_list":"/paper/x3d-expanding-architectures-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2004.04730","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.04730"}}}},{"rank_in_archive_order":101,"model":"R3D-RS-200","metrics":{"Acc@1":"80.4","Acc@5":"94.4"},"uses_additional_data":false,"paper_date":"2021-09-03","paper":"/paper/revisiting-3d-resnets-for-video-recognition","paper_url":"https://arxiv.org/abs/2109.01696v1","paper_title":"Revisiting 3D ResNets for Video Recognition","code":"https://github.com/tensorflow/models","n_code_links":5,"official":null,"syntology":null},{"rank_in_archive_order":102,"model":"OmniSource SlowOnly R101 8x8 (Scratch)","metrics":{"Acc@1":"80.4","Acc@5":"94.4"},"uses_additional_data":false,"paper_date":"2020-03-29","paper":"/paper/omni-sourced-webly-supervised-learning-for","paper_url":"https://arxiv.org/abs/2003.13042v2","paper_title":"Omni-sourced Webly-supervised Learning for Video Recognition","code":"https://github.com/open-mmlab/mmaction2","n_code_links":3,"official":{"repos":["open-mmlab/mmaction"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]},"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":3,"n_samples":13,"n_pointer_only_licence":0,"sample_list":"/paper/omni-sourced-webly-supervised-learning-for#ran","syntology_url":"https://syntology.ai/paper/2003.13042","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.13042"}}}},{"rank_in_archive_order":103,"model":"MViT-B, 32x3","metrics":{"Acc@1":"80.2","Acc@5":"94.4"},"uses_additional_data":false,"paper_date":"2021-04-22","paper":"/paper/multiscale-vision-transformers","paper_url":"https://arxiv.org/abs/2104.11227v1","paper_title":"Multiscale Vision Transformers","code":"https://github.com/facebookresearch/SlowFast","n_code_links":8,"official":{"repos":["facebookresearch/SlowFast"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":13,"n_constructed":10,"n_ran_checked":11,"n_instrument":2,"n_unverified":13,"n_samples":26,"n_pointer_only_licence":5,"sample_list":"/paper/multiscale-vision-transformers#ran","syntology_url":"https://syntology.ai/paper/2104.11227","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.11227"}}}},{"rank_in_archive_order":104,"model":"AMD(ViT-S/16)","metrics":{"Acc@1":"80.1","Acc@5":"94.5","FLOPs (G) x views":"57X15","Parameters (M)":"22"},"uses_additional_data":false,"paper_date":"2023-11-06","paper":"/paper/asymmetric-masked-distillation-for-pre","paper_url":"https://arxiv.org/abs/2311.03149v2","paper_title":"Asymmetric Masked Distillation for Pre-Training Small Foundation Models","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":105,"model":"SlowFast 16x8 (ResNet-101 + NL)","metrics":{"Acc@1":"79.8"},"uses_additional_data":true,"paper_date":"2018-12-10","paper":"/paper/slowfast-networks-for-video-recognition","paper_url":"https://arxiv.org/abs/1812.03982v3","paper_title":"SlowFast Networks for Video Recognition","code":"https://github.com/facebookresearch/SlowFast","n_code_links":15,"official":{"repos":["facebookresearch/SlowFast"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"n_samples":10,"n_pointer_only_licence":1,"sample_list":"/paper/slowfast-networks-for-video-recognition#ran","syntology_url":"https://syntology.ai/paper/1812.03982","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.03982"}}}},{"rank_in_archive_order":106,"model":"CT-Net Ensemble","metrics":{"Acc@1":"79.8"},"uses_additional_data":false,"paper_date":"2021-06-03","paper":"/paper/ct-net-channel-tensorization-network-for-1","paper_url":"https://arxiv.org/abs/2106.01603v1","paper_title":"CT-Net: Channel Tensorization Network for Video Classification","code":"https://github.com/Andy1621/CT-Net","n_code_links":1,"official":{"repos":["Andy1621/CT-Net"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":11,"n_constructed":2,"n_ran_checked":4,"n_instrument":7,"n_unverified":2,"n_samples":13,"n_pointer_only_licence":0,"sample_list":"/paper/ct-net-channel-tensorization-network-for-1#ran","syntology_url":"https://syntology.ai/paper/2106.01603","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.01603"}}}},{"rank_in_archive_order":107,"model":"ViT-B-VTN+ ImageNet-21K (84.0 [10])","metrics":{"Acc@1":"79.8"},"uses_additional_data":false,"paper_date":"2021-02-01","paper":"/paper/video-transformer-network","paper_url":"https://arxiv.org/abs/2102.00719v3","paper_title":"Video Transformer Network","code":"https://github.com/bomri/SlowFast/blob/master/projects/vtn/README.md","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":108,"model":"TimeSformer-HR","metrics":{"Acc@1":"79.7","Acc@5":"94.4"},"uses_additional_data":false,"paper_date":"2021-02-09","paper":"/paper/is-space-time-attention-all-you-need-for","paper_url":"https://arxiv.org/abs/2102.05095v4","paper_title":"Is Space-Time Attention All You Need for Video Understanding?","code":"https://github.com/open-mmlab/mmaction2","n_code_links":16,"official":{"repos":["facebookresearch/TimeSformer"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"syntology":{"n_ran":35,"n_constructed":17,"n_ran_checked":21,"n_instrument":14,"n_unverified":8,"n_samples":43,"n_pointer_only_licence":14,"sample_list":"/paper/is-space-time-attention-all-you-need-for#ran","syntology_url":"https://syntology.ai/paper/2102.05095","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.05095"}}}},{"rank_in_archive_order":109,"model":"En-VidTr-M","metrics":{"Acc@1":"79.7","Acc@5":"94.2"},"uses_additional_data":false,"paper_date":"2021-04-23","paper":"/paper/vidtr-video-transformer-without-convolutions","paper_url":"https://arxiv.org/abs/2104.11746v2","paper_title":"VidTr: Video Transformer Without Convolutions","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":110,"model":"LGD-3D RGB (ResNet-101)","metrics":{"Acc@1":"79.4","Acc@5":"94.4"},"uses_additional_data":false,"paper_date":"2019-06-13","paper":"/paper/learning-spatio-temporal-representation-with-3","paper_url":"https://arxiv.org/abs/1906.05571v1","paper_title":"Learning Spatio-Temporal Representation with Local and Global Diffusion","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":111,"model":"TDN-ResNet101 (ensemble, ImageNet pretrained, RGB only)","metrics":{"Acc@1":"79.4","Acc@5":"94.4"},"uses_additional_data":false,"paper_date":"2020-12-18","paper":"/paper/tdn-temporal-difference-networks-for","paper_url":"https://arxiv.org/abs/2012.10071v2","paper_title":"TDN: Temporal Difference Networks for Efficient Action Recognition","code":"https://github.com/MCG-NJU/TDN","n_code_links":1,"official":{"repos":["MCG-NJU/TDN"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":0,"sample_list":"/paper/tdn-temporal-difference-networks-for#ran","syntology_url":"https://syntology.ai/paper/2012.10071","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.10071"}}}},{"rank_in_archive_order":112,"model":"En-VidTr-S","metrics":{"Acc@1":"79.4","Acc@5":"94"},"uses_additional_data":false,"paper_date":"2021-04-23","paper":"/paper/vidtr-video-transformer-without-convolutions","paper_url":"https://arxiv.org/abs/2104.11746v2","paper_title":"VidTr: Video Transformer Without Convolutions","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":113,"model":"MAR (75% mask, ViT-B, 16x4)","metrics":{"Acc@1":"79.4","Acc@5":"93.7"},"uses_additional_data":false,"paper_date":"2022-07-24","paper":"/paper/mar-masked-autoencoders-for-efficient-action","paper_url":"https://arxiv.org/abs/2207.11660v1","paper_title":"MAR: Masked Autoencoders for Efficient Action Recognition","code":"https://github.com/alibaba-mmai-research/masked-action-recognition","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":114,"model":"STAM (16 Frames)","metrics":{"Acc@1":"79.3","FLOPs (G) x views":"270x1"},"uses_additional_data":false,"paper_date":"2021-03-25","paper":"/paper/an-image-is-worth-16x16-words-what-is-a-video","paper_url":"https://arxiv.org/abs/2103.13915v2","paper_title":"An Image is Worth 16x16 Words, What is a Video Worth?","code":"https://github.com/Alibaba-MIIL/STAM","n_code_links":2,"official":{"repos":["Alibaba-MIIL/STAM"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"syntology":{"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0,"sample_list":"/paper/an-image-is-worth-16x16-words-what-is-a-video#ran","syntology_url":"https://syntology.ai/paper/2103.13915","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.13915"}}}},{"rank_in_archive_order":115,"model":"ip-CSN-152 (Sports-1M pretraining)","metrics":{"Acc@1":"79.2","Acc@5":"93.8"},"uses_additional_data":false,"paper_date":"2019-04-04","paper":"/paper/video-classification-with-channel-separated","paper_url":"https://arxiv.org/abs/1904.02811v4","paper_title":"Video Classification with Channel-Separated Convolutional Networks","code":"https://github.com/open-mmlab/mmaction2","n_code_links":7,"official":{"repos":["facebookresearch/VMZ"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":0,"sample_list":"/paper/video-classification-with-channel-separated#ran","syntology_url":"https://syntology.ai/paper/1904.02811","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.02811"}}}},{"rank_in_archive_order":116,"model":"CorrNet","metrics":{"Acc@1":"79.2"},"uses_additional_data":false,"paper_date":"2019-06-07","paper":"/paper/video-modeling-with-correlation-networks","paper_url":"https://arxiv.org/abs/1906.03349v2","paper_title":"Video Modeling with Correlation Networks","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":117,"model":"OmniVL","metrics":{"Acc@1":"79.1","Acc@5":"94.5"},"uses_additional_data":false,"paper_date":"2022-09-15","paper":"/paper/omnivl-one-foundation-model-for-image","paper_url":"https://arxiv.org/abs/2209.07526v2","paper_title":"OmniVL:One Foundation Model for Image-Language and Video-Language Tasks","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":118,"model":"X3D-XL","metrics":{"Acc@1":"79.1","Acc@5":"93.9"},"uses_additional_data":false,"paper_date":"2020-04-09","paper":"/paper/x3d-expanding-architectures-for-efficient","paper_url":"https://arxiv.org/abs/2004.04730v1","paper_title":"X3D: Expanding Architectures for Efficient Video Recognition","code":"https://github.com/facebookresearch/SlowFast","n_code_links":8,"official":{"repos":["facebookresearch/SlowFast"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":4,"n_samples":15,"n_pointer_only_licence":0,"sample_list":"/paper/x3d-expanding-architectures-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2004.04730","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.04730"}}}},{"rank_in_archive_order":119,"model":"MVFNet-ResNet101 (ensemble, ImageNet pretrained, RGB only)","metrics":{"Acc@1":"79.1","Acc@5":"93.8"},"uses_additional_data":false,"paper_date":"2020-12-13","paper":"/paper/mvfnet-multi-view-fusion-network-for","paper_url":"https://arxiv.org/abs/2012.06977v2","paper_title":"MVFNet: Multi-View Fusion Network for Efficient Video Recognition","code":"https://github.com/whwu95/MVFNet","n_code_links":3,"official":null,"syntology":null},{"rank_in_archive_order":120,"model":"TAdaConvNeXt-T","metrics":{"Acc@1":"79.1","Acc@5":"93.7"},"uses_additional_data":false,"paper_date":"2021-10-12","paper":"/paper/tada-temporally-adaptive-convolutions-for-1","paper_url":"https://arxiv.org/abs/2110.06178v4","paper_title":"TAda! Temporally-Adaptive Convolutions for Video Understanding","code":"https://github.com/alibaba-mmai-research/TAdaConv","n_code_links":2,"official":{"repos":["alibaba-mmai-research/pytorch-video-understanding"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]},"syntology":{"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0,"sample_list":"/paper/tada-temporally-adaptive-convolutions-for-1#ran","syntology_url":"https://syntology.ai/paper/2110.06178","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.06178"}}}},{"rank_in_archive_order":121,"model":"SlowFast 16x8 (ResNet-101)","metrics":{"Acc@1":"78.9","Acc@5":"93.5"},"uses_additional_data":false,"paper_date":"2018-12-10","paper":"/paper/slowfast-networks-for-video-recognition","paper_url":"https://arxiv.org/abs/1812.03982v3","paper_title":"SlowFast Networks for Video Recognition","code":"https://github.com/facebookresearch/SlowFast","n_code_links":15,"official":{"repos":["facebookresearch/SlowFast"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"n_samples":10,"n_pointer_only_licence":1,"sample_list":"/paper/slowfast-networks-for-video-recognition#ran","syntology_url":"https://syntology.ai/paper/1812.03982","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.03982"}}}},{"rank_in_archive_order":122,"model":"G-Blend (Sports-1M pretrain)","metrics":{"Acc@1":"78.9"},"uses_additional_data":false,"paper_date":"2019-05-29","paper":"/paper/what-makes-training-multi-modal-networks-hard","paper_url":"https://arxiv.org/abs/1905.12681v5","paper_title":"What Makes Training Multi-Modal Classification Networks Hard?","code":"https://github.com/facebookresearch/R2Plus1D","n_code_links":3,"official":null,"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":6,"n_samples":11,"n_pointer_only_licence":0,"sample_list":"/paper/what-makes-training-multi-modal-networks-hard#ran","syntology_url":"https://syntology.ai/paper/1905.12681","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.12681"}}}},{"rank_in_archive_order":123,"model":"Swin-T (ImageNet-1k pretrain)","metrics":{"Acc@1":"78.8","Acc@5":"93.6"},"uses_additional_data":false,"paper_date":"2021-06-24","paper":"/paper/video-swin-transformer","paper_url":"https://arxiv.org/abs/2106.13230v1","paper_title":"Video Swin Transformer","code":"https://github.com/open-mmlab/mmaction2","n_code_links":15,"official":{"repos":["SwinTransformer/Video-Swin-Transformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":19,"n_constructed":0,"n_ran_checked":14,"n_instrument":5,"n_unverified":13,"n_samples":32,"n_pointer_only_licence":7,"sample_list":"/paper/video-swin-transformer#ran","syntology_url":"https://syntology.ai/paper/2106.13230","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.13230"}}}},{"rank_in_archive_order":124,"model":"GB + DF + LB (ResNet 152, ImageNet pretrained)","metrics":{"Acc@1":"78.8"},"uses_additional_data":false,"paper_date":"2019-08-20","paper":"/paper/190807625","paper_url":"https://arxiv.org/abs/1908.07625v1","paper_title":"Action recognition with spatial-temporal discriminative filter banks","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":125,"model":"ViT-B-VTN (3 layers, ImageNet pretrain)","metrics":{"Acc@1":"78.6","Acc@5":"93.7"},"uses_additional_data":false,"paper_date":"2021-02-01","paper":"/paper/video-transformer-network","paper_url":"https://arxiv.org/abs/2102.00719v3","paper_title":"Video Transformer Network","code":"https://github.com/bomri/SlowFast/blob/master/projects/vtn/README.md","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":126,"model":"MViT-B, 16x4","metrics":{"Acc@1":"78.4","Acc@5":"93.5"},"uses_additional_data":false,"paper_date":"2021-04-22","paper":"/paper/multiscale-vision-transformers","paper_url":"https://arxiv.org/abs/2104.11227v1","paper_title":"Multiscale Vision Transformers","code":"https://github.com/facebookresearch/SlowFast","n_code_links":8,"official":{"repos":["facebookresearch/SlowFast"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":13,"n_constructed":10,"n_ran_checked":11,"n_instrument":2,"n_unverified":13,"n_samples":26,"n_pointer_only_licence":5,"sample_list":"/paper/multiscale-vision-transformers#ran","syntology_url":"https://syntology.ai/paper/2104.11227","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.11227"}}}},{"rank_in_archive_order":127,"model":"MoViNet-A3","metrics":{"Acc@1":"78.2","Acc@5":"93.8","FLOPs (G) x views":"56.9x1"},"uses_additional_data":false,"paper_date":"2021-03-21","paper":"/paper/movinets-mobile-video-networks-for-efficient","paper_url":"https://arxiv.org/abs/2103.11511v2","paper_title":"MoViNets: Mobile Video Networks for Efficient Video Recognition","code":"https://github.com/tensorflow/models","n_code_links":3,"official":{"repos":["tensorflow/models"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":9,"n_constructed":6,"n_ran_checked":8,"n_instrument":1,"n_unverified":4,"n_samples":13,"n_pointer_only_licence":0,"sample_list":"/paper/movinets-mobile-video-networks-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2103.11511","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.11511"}}}},{"rank_in_archive_order":128,"model":"TAda2D-En (ResNet-50, 8+16 frames)","metrics":{"Acc@1":"78.2","Acc@5":"93.5"},"uses_additional_data":false,"paper_date":"2021-10-12","paper":"/paper/tada-temporally-adaptive-convolutions-for-1","paper_url":"https://arxiv.org/abs/2110.06178v4","paper_title":"TAda! Temporally-Adaptive Convolutions for Video Understanding","code":"https://github.com/alibaba-mmai-research/TAdaConv","n_code_links":2,"official":{"repos":["alibaba-mmai-research/pytorch-video-understanding"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]},"syntology":{"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0,"sample_list":"/paper/tada-temporally-adaptive-convolutions-for-1#ran","syntology_url":"https://syntology.ai/paper/2110.06178","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.06178"}}}},{"rank_in_archive_order":129,"model":"SVT","metrics":{"Acc@1":"78.1"},"uses_additional_data":false,"paper_date":"2021-12-02","paper":"/paper/self-supervised-video-transformer","paper_url":"https://arxiv.org/abs/2112.01514v2","paper_title":"Self-supervised Video Transformer","code":"https://github.com/kahnchana/svt","n_code_links":1,"official":{"repos":["kahnchana/svt"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"syntology":{"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0,"sample_list":"/paper/self-supervised-video-transformer#ran","syntology_url":"https://syntology.ai/paper/2112.01514","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.01514"}}}},{"rank_in_archive_order":130,"model":"TimeSformer","metrics":{"Acc@1":"78","Acc@5":"93.7"},"uses_additional_data":false,"paper_date":"2021-02-09","paper":"/paper/is-space-time-attention-all-you-need-for","paper_url":"https://arxiv.org/abs/2102.05095v4","paper_title":"Is Space-Time Attention All You Need for Video Understanding?","code":"https://github.com/open-mmlab/mmaction2","n_code_links":16,"official":{"repos":["facebookresearch/TimeSformer"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"syntology":{"n_ran":35,"n_constructed":17,"n_ran_checked":21,"n_instrument":14,"n_unverified":8,"n_samples":43,"n_pointer_only_licence":14,"sample_list":"/paper/is-space-time-attention-all-you-need-for#ran","syntology_url":"https://syntology.ai/paper/2102.05095","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.05095"}}}},{"rank_in_archive_order":131,"model":"SlowFast 8x8 (ResNet-101)","metrics":{"Acc@1":"77.9","Acc@5":"93.2"},"uses_additional_data":false,"paper_date":"2018-12-10","paper":"/paper/slowfast-networks-for-video-recognition","paper_url":"https://arxiv.org/abs/1812.03982v3","paper_title":"SlowFast Networks for Video Recognition","code":"https://github.com/facebookresearch/SlowFast","n_code_links":15,"official":{"repos":["facebookresearch/SlowFast"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"n_samples":10,"n_pointer_only_licence":1,"sample_list":"/paper/slowfast-networks-for-video-recognition#ran","syntology_url":"https://syntology.ai/paper/1812.03982","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.03982"}}}},{"rank_in_archive_order":132,"model":"RepFlow-50 ([2+1]D CNN, FcF, Non-local block)","metrics":{"Acc@1":"77.9"},"uses_additional_data":false,"paper_date":"2018-10-02","paper":"/paper/representation-flow-for-action-recognition","paper_url":"https://arxiv.org/abs/1810.01455v3","paper_title":"Representation Flow for Action Recognition","code":"https://github.com/piergiaj/representation-flow-cvpr19","n_code_links":5,"official":null,"syntology":null},{"rank_in_archive_order":133,"model":"ip-CSN-152","metrics":{"Acc@1":"77.8","Acc@5":"92.8"},"uses_additional_data":false,"paper_date":"2019-04-04","paper":"/paper/video-classification-with-channel-separated","paper_url":"https://arxiv.org/abs/1904.02811v4","paper_title":"Video Classification with Channel-Separated Convolutional Networks","code":"https://github.com/open-mmlab/mmaction2","n_code_links":7,"official":{"repos":["facebookresearch/VMZ"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":0,"sample_list":"/paper/video-classification-with-channel-separated#ran","syntology_url":"https://syntology.ai/paper/1904.02811","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.02811"}}}},{"rank_in_archive_order":134,"model":"I3D + NL","metrics":{"Acc@1":"77.7","Acc@5":"93.3"},"uses_additional_data":false,"paper_date":"2017-11-21","paper":"/paper/non-local-neural-networks","paper_url":"http://arxiv.org/abs/1711.07971v3","paper_title":"Non-local Neural Networks","code":"https://github.com/facebookresearch/detectron","n_code_links":32,"official":{"repos":["facebookresearch/video-nonlocal-net"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":4,"sample_list":"/paper/non-local-neural-networks#ran","syntology_url":"https://syntology.ai/paper/1711.07971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.07971"}}}},{"rank_in_archive_order":135,"model":"G-Blend","metrics":{"Acc@1":"77.7"},"uses_additional_data":false,"paper_date":"2019-05-29","paper":"/paper/what-makes-training-multi-modal-networks-hard","paper_url":"https://arxiv.org/abs/1905.12681v5","paper_title":"What Makes Training Multi-Modal Classification Networks Hard?","code":"https://github.com/facebookresearch/R2Plus1D","n_code_links":3,"official":null,"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":6,"n_samples":11,"n_pointer_only_licence":0,"sample_list":"/paper/what-makes-training-multi-modal-networks-hard#ran","syntology_url":"https://syntology.ai/paper/1905.12681","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.12681"}}}},{"rank_in_archive_order":136,"model":"HATNet (32 frames)","metrics":{"Acc@1":"77.6"},"uses_additional_data":false,"paper_date":"2019-04-25","paper":"/paper/holistic-large-scale-video-understanding","paper_url":"https://arxiv.org/abs/1904.11451v3","paper_title":"Large Scale Holistic Video Understanding","code":"https://github.com/holistic-video-understanding/HVU-Dataset","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":137,"model":"X3D-L","metrics":{"Acc@1":"77.5","Acc@5":"92.9"},"uses_additional_data":false,"paper_date":"2020-04-09","paper":"/paper/x3d-expanding-architectures-for-efficient","paper_url":"https://arxiv.org/abs/2004.04730v1","paper_title":"X3D: Expanding Architectures for Efficient Video Recognition","code":"https://github.com/facebookresearch/SlowFast","n_code_links":8,"official":{"repos":["facebookresearch/SlowFast"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":4,"n_samples":15,"n_pointer_only_licence":0,"sample_list":"/paper/x3d-expanding-architectures-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2004.04730","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.04730"}}}},{"rank_in_archive_order":138,"model":"CoST ResNet-101  (ImageNet pretrain)","metrics":{"Acc@1":"77.5"},"uses_additional_data":false,"paper_date":"2019-06-01","paper":"/paper/collaborative-spatiotemporal-feature-learning","paper_url":"http://openaccess.thecvf.com/content_CVPR_2019/html/Li_Collaborative_Spatiotemporal_Feature_Learning_for_Video_Action_Recognition_CVPR_2019_paper.html","paper_title":"Collaborative Spatiotemporal Feature Learning for Video Action Recognition","code":"https://github.com/hikvision-research/cost","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":139,"model":"TAda2D (ResNet-50, 16 frames)","metrics":{"Acc@1":"77.4","Acc@5":"93.1"},"uses_additional_data":false,"paper_date":"2021-10-12","paper":"/paper/tada-temporally-adaptive-convolutions-for-1","paper_url":"https://arxiv.org/abs/2110.06178v4","paper_title":"TAda! Temporally-Adaptive Convolutions for Video Understanding","code":"https://github.com/alibaba-mmai-research/TAdaConv","n_code_links":2,"official":{"repos":["alibaba-mmai-research/pytorch-video-understanding"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]},"syntology":{"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0,"sample_list":"/paper/tada-temporally-adaptive-convolutions-for-1#ran","syntology_url":"https://syntology.ai/paper/2110.06178","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.06178"}}}},{"rank_in_archive_order":140,"model":"EvaNet","metrics":{"Acc@1":"77.4"},"uses_additional_data":false,"paper_date":"2018-11-26","paper":"/paper/evolving-space-time-neural-architectures-for","paper_url":"https://arxiv.org/abs/1811.10636v2","paper_title":"Evolving Space-Time Neural Architectures for Videos","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":141,"model":"RNL+TSM Ensemble(ResNet50, 8 + 16 frames)","metrics":{"Acc@1":"77.4"},"uses_additional_data":false,"paper_date":"2020-07-17","paper":"/paper/region-based-non-local-operation-for-video","paper_url":"https://arxiv.org/abs/2007.09033v5","paper_title":"Region-based Non-local Operation for Video Classification","code":"https://github.com/guoxih/region-based-non-local-network","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":142,"model":"VIMPAC","metrics":{"Acc@1":"77.4"},"uses_additional_data":false,"paper_date":"2021-06-21","paper":"/paper/vimpac-video-pre-training-via-masked-token","paper_url":"https://arxiv.org/abs/2106.11250v1","paper_title":"VIMPAC: Video Pre-Training via Masked Token Prediction and Contrastive Learning","code":"https://github.com/airsplay/vimpac","n_code_links":1,"official":{"repos":["airsplay/vimpac"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1,"sample_list":"/paper/vimpac-video-pre-training-via-masked-token#ran","syntology_url":"https://syntology.ai/paper/2106.11250","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.11250"}}}},{"rank_in_archive_order":143,"model":"BQN (ResNet-50)","metrics":{"Acc@1":"77.3","Acc@5":"93.2"},"uses_additional_data":false,"paper_date":"2021-03-29","paper":"/paper/video-classification-with-finecoarse-networks","paper_url":"https://arxiv.org/abs/2103.15584v4","paper_title":"Busy-Quiet Video Disentangling for Video Classification","code":"https://github.com/guoxih/busy-quiet-net","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":144,"model":"S3D-G (RGB+Flow, ImageNet pretrained)","metrics":{"Acc@1":"77.2","Acc@5":"93"},"uses_additional_data":false,"paper_date":"2017-12-13","paper":"/paper/rethinking-spatiotemporal-feature-learning","paper_url":"http://arxiv.org/abs/1712.04851v2","paper_title":"Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification","code":"https://github.com/kylemin/S3D","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":145,"model":"SlowFast 8x8 (ResNet-50)","metrics":{"Acc@1":"77","Acc@5":"92.6"},"uses_additional_data":false,"paper_date":"2018-12-10","paper":"/paper/slowfast-networks-for-video-recognition","paper_url":"https://arxiv.org/abs/1812.03982v3","paper_title":"SlowFast Networks for Video Recognition","code":"https://github.com/facebookresearch/SlowFast","n_code_links":15,"official":{"repos":["facebookresearch/SlowFast"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"n_samples":10,"n_pointer_only_licence":1,"sample_list":"/paper/slowfast-networks-for-video-recognition#ran","syntology_url":"https://syntology.ai/paper/1812.03982","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.03982"}}}},{"rank_in_archive_order":146,"model":"TAda2D (ResNet-50, 8 frames)","metrics":{"Acc@1":"76.7","Acc@5":"92.6"},"uses_additional_data":false,"paper_date":"2021-10-12","paper":"/paper/tada-temporally-adaptive-convolutions-for-1","paper_url":"https://arxiv.org/abs/2110.06178v4","paper_title":"TAda! Temporally-Adaptive Convolutions for Video Understanding","code":"https://github.com/alibaba-mmai-research/TAdaConv","n_code_links":2,"official":{"repos":["alibaba-mmai-research/pytorch-video-understanding"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]},"syntology":{"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0,"sample_list":"/paper/tada-temporally-adaptive-convolutions-for-1#ran","syntology_url":"https://syntology.ai/paper/2110.06178","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.06178"}}}},{"rank_in_archive_order":147,"model":"D3D+S3D-G (RGB + RGB)","metrics":{"Acc@1":"76.5"},"uses_additional_data":false,"paper_date":"2018-12-19","paper":"/paper/d3d-distilled-3d-networks-for-video-action","paper_url":"http://arxiv.org/abs/1812.08249v2","paper_title":"D3D: Distilled 3D Networks for Video Action Recognition","code":"https://github.com/princeton-vl/d3dhelper","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":148,"model":"MSNet-R50 (16 frames, ImageNet pretrained)","metrics":{"Acc@1":"76.4"},"uses_additional_data":false,"paper_date":"2020-07-20","paper":"/paper/motionsqueeze-neural-motion-feature-learning","paper_url":"https://arxiv.org/abs/2007.09933v1","paper_title":"MotionSqueeze: Neural Motion Feature Learning for Video Understanding","code":"https://github.com/arunos728/MotionSqueeze","n_code_links":2,"official":null,"syntology":{"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":2,"n_samples":8,"n_pointer_only_licence":2,"sample_list":"/paper/motionsqueeze-neural-motion-feature-learning#ran","syntology_url":"https://syntology.ai/paper/2007.09933","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.09933"}}}},{"rank_in_archive_order":149,"model":"GloRe","metrics":{"Acc@1":"76.1"},"uses_additional_data":false,"paper_date":"2019-06-03","paper":"/paper/190600550","paper_url":"https://arxiv.org/abs/1906.00550v1","paper_title":"Global Textual Relation Embedding for Relational Understanding","code":"https://github.com/czyssrs/GloREPlus","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":150,"model":"X3D-M","metrics":{"Acc@1":"76","Acc@5":"92.3"},"uses_additional_data":false,"paper_date":"2020-04-09","paper":"/paper/x3d-expanding-architectures-for-efficient","paper_url":"https://arxiv.org/abs/2004.04730v1","paper_title":"X3D: Expanding Architectures for Efficient Video Recognition","code":"https://github.com/facebookresearch/SlowFast","n_code_links":8,"official":{"repos":["facebookresearch/SlowFast"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":4,"n_samples":15,"n_pointer_only_licence":0,"sample_list":"/paper/x3d-expanding-architectures-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2004.04730","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.04730"}}}},{"rank_in_archive_order":151,"model":"MViT-S","metrics":{"Acc@1":"76","Acc@5":"92.1"},"uses_additional_data":false,"paper_date":"2021-04-22","paper":"/paper/multiscale-vision-transformers","paper_url":"https://arxiv.org/abs/2104.11227v1","paper_title":"Multiscale Vision Transformers","code":"https://github.com/facebookresearch/SlowFast","n_code_links":8,"official":{"repos":["facebookresearch/SlowFast"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":13,"n_constructed":10,"n_ran_checked":11,"n_instrument":2,"n_unverified":13,"n_samples":26,"n_pointer_only_licence":5,"sample_list":"/paper/multiscale-vision-transformers#ran","syntology_url":"https://syntology.ai/paper/2104.11227","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.11227"}}}},{"rank_in_archive_order":152,"model":"CMA iter1 (16 frames)","metrics":{"Acc@1":"75.98"},"uses_additional_data":false,"paper_date":"2019-08-01","paper":"/paper/two-stream-video-classification-with-cross","paper_url":"https://arxiv.org/abs/1908.00497v1","paper_title":"Two-Stream Video Classification with Cross-Modality Attention","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":153,"model":"D3D (RGB)","metrics":{"Acc@1":"75.9"},"uses_additional_data":false,"paper_date":"2018-12-19","paper":"/paper/d3d-distilled-3d-networks-for-video-action","paper_url":"http://arxiv.org/abs/1812.08249v2","paper_title":"D3D: Distilled 3D Networks for Video Action Recognition","code":"https://github.com/princeton-vl/d3dhelper","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":154,"model":"Oct-I3D + NL","metrics":{"Acc@1":"75.7"},"uses_additional_data":false,"paper_date":"2019-04-10","paper":"/paper/drop-an-octave-reducing-spatial-redundancy-in","paper_url":"https://arxiv.org/abs/1904.05049v3","paper_title":"Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution","code":"https://github.com/osmr/imgclsmob","n_code_links":28,"official":{"repos":["facebookresearch/OctConv"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":24,"n_constructed":0,"n_ran_checked":11,"n_instrument":13,"n_unverified":10,"n_samples":34,"n_pointer_only_licence":9,"sample_list":"/paper/drop-an-octave-reducing-spatial-redundancy-in#ran","syntology_url":"https://syntology.ai/paper/1904.05049","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.05049"}}}},{"rank_in_archive_order":155,"model":"SlowFast 4x16 (ResNet-50)","metrics":{"Acc@1":"75.6","Acc@5":"92.1"},"uses_additional_data":false,"paper_date":"2018-12-10","paper":"/paper/slowfast-networks-for-video-recognition","paper_url":"https://arxiv.org/abs/1812.03982v3","paper_title":"SlowFast Networks for Video Recognition","code":"https://github.com/facebookresearch/SlowFast","n_code_links":15,"official":{"repos":["facebookresearch/SlowFast"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"n_samples":10,"n_pointer_only_licence":1,"sample_list":"/paper/slowfast-networks-for-video-recognition#ran","syntology_url":"https://syntology.ai/paper/1812.03982","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.03982"}}}},{"rank_in_archive_order":156,"model":"R[2+1]D-Flow (Sports-1M pretrain)","metrics":{"Acc@1":"75.4","Acc@5":"91.9"},"uses_additional_data":false,"paper_date":"2017-11-30","paper":"/paper/a-closer-look-at-spatiotemporal-convolutions","paper_url":"http://arxiv.org/abs/1711.11248v3","paper_title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","code":"https://github.com/microsoft/computervision-recipes","n_code_links":24,"official":{"repos":["facebookresearch/R2Plus1D"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":3,"n_samples":4,"n_pointer_only_licence":4,"sample_list":"/paper/a-closer-look-at-spatiotemporal-convolutions#ran","syntology_url":"https://syntology.ai/paper/1711.11248","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.11248"}}}},{"rank_in_archive_order":157,"model":"FASTER32","metrics":{"Acc@1":"75.1"},"uses_additional_data":false,"paper_date":"2019-06-10","paper":"/paper/faster-recurrent-networks-for-video","paper_url":"https://arxiv.org/abs/1906.04226v2","paper_title":"FASTER Recurrent Networks for Efficient Video Classification","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":158,"model":"MoViNet-A2","metrics":{"Acc@1":"75.0","Acc@5":"92.3","FLOPs (G) x views":"10.3x1"},"uses_additional_data":false,"paper_date":"2021-03-21","paper":"/paper/movinets-mobile-video-networks-for-efficient","paper_url":"https://arxiv.org/abs/2103.11511v2","paper_title":"MoViNets: Mobile Video Networks for Efficient Video Recognition","code":"https://github.com/tensorflow/models","n_code_links":3,"official":{"repos":["tensorflow/models"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":9,"n_constructed":6,"n_ran_checked":8,"n_instrument":1,"n_unverified":4,"n_samples":13,"n_pointer_only_licence":0,"sample_list":"/paper/movinets-mobile-video-networks-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2103.11511","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.11511"}}}},{"rank_in_archive_order":159,"model":"MARS+RGB+Flow (64 frames)","metrics":{"Acc@1":"74.9"},"uses_additional_data":false,"paper_date":"2019-06-01","paper":"/paper/mars-motion-augmented-rgb-stream-for-action","paper_url":"http://openaccess.thecvf.com/content_CVPR_2019/html/Crasto_MARS_Motion-Augmented_RGB_Stream_for_Action_Recognition_CVPR_2019_paper.html","paper_title":"MARS: Motion-Augmented RGB Stream for Action Recognition","code":"https://github.com/craston/MARS","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":160,"model":"S3D-G (RGB, ImageNet pretrained)","metrics":{"Acc@1":"74.7","Acc@5":"93.4"},"uses_additional_data":false,"paper_date":"2017-12-13","paper":"/paper/rethinking-spatiotemporal-feature-learning","paper_url":"http://arxiv.org/abs/1712.04851v2","paper_title":"Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification","code":"https://github.com/kylemin/S3D","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":161,"model":"TSM","metrics":{"Acc@1":"74.7"},"uses_additional_data":false,"paper_date":"2018-11-20","paper":"/paper/temporal-shift-module-for-efficient-video","paper_url":"https://arxiv.org/abs/1811.08383v3","paper_title":"TSM: Temporal Shift Module for Efficient Video Understanding","code":"https://github.com/open-mmlab/mmaction2","n_code_links":13,"official":{"repos":["MIT-HAN-LAB/temporal-shift-module"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","unlocated"]},"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":5,"n_instrument":5,"n_unverified":6,"n_samples":16,"n_pointer_only_licence":6,"sample_list":"/paper/temporal-shift-module-for-efficient-video#ran","syntology_url":"https://syntology.ai/paper/1811.08383","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.08383"}}}},{"rank_in_archive_order":162,"model":"A2 Net","metrics":{"Acc@1":"74.6","Acc@5":"91.5"},"uses_additional_data":false,"paper_date":"2018-10-27","paper":"/paper/a2-nets-double-attention-networks","paper_url":"http://arxiv.org/abs/1810.11579v1","paper_title":"$A^2$-Nets: Double Attention Networks","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":163,"model":"R[2+1]D-RGB (Sports-1M pretrain)","metrics":{"Acc@1":"74.3","Acc@5":"91.4"},"uses_additional_data":false,"paper_date":"2017-11-30","paper":"/paper/a-closer-look-at-spatiotemporal-convolutions","paper_url":"http://arxiv.org/abs/1711.11248v3","paper_title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","code":"https://github.com/microsoft/computervision-recipes","n_code_links":24,"official":{"repos":["facebookresearch/R2Plus1D"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":3,"n_samples":4,"n_pointer_only_licence":4,"sample_list":"/paper/a-closer-look-at-spatiotemporal-convolutions#ran","syntology_url":"https://syntology.ai/paper/1711.11248","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.11248"}}}},{"rank_in_archive_order":164,"model":"TSN","metrics":{"Acc@1":"73.9","Acc@5":"91.1"},"uses_additional_data":false,"paper_date":"2016-08-02","paper":"/paper/temporal-segment-networks-towards-good","paper_url":"http://arxiv.org/abs/1608.00859v1","paper_title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","code":"https://github.com/open-mmlab/mmaction2","n_code_links":22,"official":{"repos":["yjxiong/caffe","yjxiong/temporal-segment-networks"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":14,"n_samples":24,"n_pointer_only_licence":3,"sample_list":"/paper/temporal-segment-networks-towards-good#ran","syntology_url":"https://syntology.ai/paper/1608.00859","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1608.00859"}}}},{"rank_in_archive_order":165,"model":"R[2+1]D-Two-Stream","metrics":{"Acc@1":"73.9","Acc@5":"90.9"},"uses_additional_data":false,"paper_date":"2017-11-30","paper":"/paper/a-closer-look-at-spatiotemporal-convolutions","paper_url":"http://arxiv.org/abs/1711.11248v3","paper_title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","code":"https://github.com/microsoft/computervision-recipes","n_code_links":24,"official":{"repos":["facebookresearch/R2Plus1D"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":3,"n_samples":4,"n_pointer_only_licence":4,"sample_list":"/paper/a-closer-look-at-spatiotemporal-convolutions#ran","syntology_url":"https://syntology.ai/paper/1711.11248","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.11248"}}}},{"rank_in_archive_order":166,"model":"TSN","metrics":{"Acc@1":"73.9"},"uses_additional_data":false,"paper_date":"2017-08-16","paper":"/paper/convnet-architecture-search-for","paper_url":"http://arxiv.org/abs/1708.05038v1","paper_title":"ConvNet Architecture Search for Spatiotemporal Feature Learning","code":"https://github.com/farazahmeds/Classification-of-brain-tumor-using-Spatiotemporal-models","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":167,"model":"STM (ResNet-50)","metrics":{"Acc@1":"73.7"},"uses_additional_data":false,"paper_date":"2019-08-07","paper":"/paper/stm-spatiotemporal-and-motion-encoding-for","paper_url":"https://arxiv.org/abs/1908.02486v2","paper_title":"STM: SpatioTemporal and Motion Encoding for Action Recognition","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":168,"model":"bLVNet Fan et al. (2019)","metrics":{"Acc@1":"73.5","Acc@5":"91.2"},"uses_additional_data":false,"paper_date":"2019-12-02","paper":"/paper/more-is-less-learning-efficient-video-1","paper_url":"https://arxiv.org/abs/1912.00869v1","paper_title":"More Is Less: Learning Efficient Video Representations by Big-Little Network and Depthwise Temporal Aggregation","code":"https://github.com/IBM/bLVNet-TAM","n_code_links":1,"official":{"repos":["IBM/bLVNet-TAM"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":5,"ran_from_kinds":["official"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":5,"n_samples":6,"n_pointer_only_licence":0,"sample_list":"/paper/more-is-less-learning-efficient-video-1#ran","syntology_url":"https://syntology.ai/paper/1912.00869","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.00869"}}}},{"rank_in_archive_order":169,"model":"Co Slow_64","metrics":{"Acc@1":"73.05","FLOPs (G) x views":"6.90x1","Parameters (M)":"32.45"},"uses_additional_data":false,"paper_date":"2021-05-31","paper":"/paper/continual-3d-convolutional-neural-networks","paper_url":"https://arxiv.org/abs/2106.00050v3","paper_title":"Continual 3D Convolutional Neural Networks for Real-time Processing of Videos","code":"https://github.com/LukasHedegaard/co3d","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":170,"model":"Inception-ResNet","metrics":{"Acc@1":"73.0","Acc@5":"90.9"},"uses_additional_data":false,"paper_date":"2017-08-12","paper":"/paper/revisiting-the-effectiveness-of-off-the-shelf","paper_url":"http://arxiv.org/abs/1708.03805v1","paper_title":"Revisiting the Effectiveness of Off-the-shelf Temporal Modeling Approaches for Large-scale Video Classification","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":171,"model":"MFNet","metrics":{"Acc@1":"72.8","Acc@5":"90.4"},"uses_additional_data":false,"paper_date":"2018-07-30","paper":"/paper/multi-fiber-networks-for-video-recognition","paper_url":"http://arxiv.org/abs/1807.11195v3","paper_title":"Multi-Fiber Networks for Video Recognition","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":172,"model":"MoViNet-A1","metrics":{"Acc@1":"72.7","Acc@5":"91.2","FLOPs (G) x views":"6.0x1"},"uses_additional_data":false,"paper_date":"2021-03-21","paper":"/paper/movinets-mobile-video-networks-for-efficient","paper_url":"https://arxiv.org/abs/2103.11511v2","paper_title":"MoViNets: Mobile Video Networks for Efficient Video Recognition","code":"https://github.com/tensorflow/models","n_code_links":3,"official":{"repos":["tensorflow/models"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":9,"n_constructed":6,"n_ran_checked":8,"n_instrument":1,"n_unverified":4,"n_samples":13,"n_pointer_only_licence":0,"sample_list":"/paper/movinets-mobile-video-networks-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2103.11511","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.11511"}}}},{"rank_in_archive_order":173,"model":"ARTNet","metrics":{"Acc@1":"72.4","Acc@5":"90.4"},"uses_additional_data":false,"paper_date":"2017-11-24","paper":"/paper/appearance-and-relation-networks-for-video","paper_url":"http://arxiv.org/abs/1711.09125v2","paper_title":"Appearance-and-Relation Networks for Video Classification","code":"https://github.com/wanglimin/ARTNet","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":174,"model":"LGD-3D Flow (ResNet-101)","metrics":{"Acc@1":"72.3","Acc@5":"90.9"},"uses_additional_data":false,"paper_date":"2019-06-13","paper":"/paper/learning-spatio-temporal-representation-with-3","paper_url":"https://arxiv.org/abs/1906.05571v1","paper_title":"Learning Spatio-Temporal Representation with Local and Global Diffusion","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":175,"model":"R[2+1]D","metrics":{"Acc@1":"72","Acc@5":"90"},"uses_additional_data":false,"paper_date":"2017-11-30","paper":"/paper/a-closer-look-at-spatiotemporal-convolutions","paper_url":"http://arxiv.org/abs/1711.11248v3","paper_title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","code":"https://github.com/microsoft/computervision-recipes","n_code_links":24,"official":{"repos":["facebookresearch/R2Plus1D"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":3,"n_samples":4,"n_pointer_only_licence":4,"sample_list":"/paper/a-closer-look-at-spatiotemporal-convolutions#ran","syntology_url":"https://syntology.ai/paper/1711.11248","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.11248"}}}},{"rank_in_archive_order":176,"model":"R[2+1]D-RGB","metrics":{"Acc@1":"72","Acc@5":"90"},"uses_additional_data":false,"paper_date":"2017-11-30","paper":"/paper/a-closer-look-at-spatiotemporal-convolutions","paper_url":"http://arxiv.org/abs/1711.11248v3","paper_title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","code":"https://github.com/microsoft/computervision-recipes","n_code_links":24,"official":{"repos":["facebookresearch/R2Plus1D"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":3,"n_samples":4,"n_pointer_only_licence":4,"sample_list":"/paper/a-closer-look-at-spatiotemporal-convolutions#ran","syntology_url":"https://syntology.ai/paper/1711.11248","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.11248"}}}},{"rank_in_archive_order":177,"model":"FASTER16 w/o sp","metrics":{"Acc@1":"71.7"},"uses_additional_data":false,"paper_date":"2019-06-10","paper":"/paper/faster-recurrent-networks-for-video","paper_url":"https://arxiv.org/abs/1906.04226v2","paper_title":"FASTER Recurrent Networks for Efficient Video Classification","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":178,"model":"Co X3D-L_64","metrics":{"Acc@1":"71.61","FLOPs (G) x views":"1.25x1","Parameters (M)":"6.15"},"uses_additional_data":false,"paper_date":"2021-05-31","paper":"/paper/continual-3d-convolutional-neural-networks","paper_url":"https://arxiv.org/abs/2106.00050v3","paper_title":"Continual 3D Convolutional Neural Networks for Real-time Processing of Videos","code":"https://github.com/LukasHedegaard/co3d","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":179,"model":"I3D","metrics":{"Acc@1":"71.1","Acc@5":"89.3"},"uses_additional_data":false,"paper_date":"2017-05-22","paper":"/paper/quo-vadis-action-recognition-a-new-model-and","paper_url":"http://arxiv.org/abs/1705.07750v3","paper_title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","code":"https://github.com/open-mmlab/mmaction2","n_code_links":34,"official":null,"syntology":{"n_ran":16,"n_constructed":7,"n_ran_checked":10,"n_instrument":6,"n_unverified":12,"n_samples":28,"n_pointer_only_licence":7,"sample_list":"/paper/quo-vadis-action-recognition-a-new-model-and#ran","syntology_url":"https://syntology.ai/paper/1705.07750","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1705.07750"}}}},{"rank_in_archive_order":180,"model":"Co X3D-M_64","metrics":{"Acc@1":"71.03","FLOPs (G) x views":"0.33x1","Parameters (M)":"3.79"},"uses_additional_data":false,"paper_date":"2021-05-31","paper":"/paper/continual-3d-convolutional-neural-networks","paper_url":"https://arxiv.org/abs/2106.00050v3","paper_title":"Continual 3D Convolutional Neural Networks for Real-time Processing of Videos","code":"https://github.com/LukasHedegaard/co3d","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":181,"model":"X3D-L","metrics":{"Acc@1":"69.29","FLOPs (G) x views":"19.17x1","Parameters (M)":"6.15"},"uses_additional_data":false,"paper_date":"2021-05-31","paper":"/paper/continual-3d-convolutional-neural-networks","paper_url":"https://arxiv.org/abs/2106.00050v3","paper_title":"Continual 3D Convolutional Neural Networks for Real-time Processing of Videos","code":"https://github.com/LukasHedegaard/co3d","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":182,"model":"MARS+RGB+Flow (16 frames)","metrics":{"Acc@1":"68.9"},"uses_additional_data":false,"paper_date":"2019-06-01","paper":"/paper/mars-motion-augmented-rgb-stream-for-action","paper_url":"http://openaccess.thecvf.com/content_CVPR_2019/html/Crasto_MARS_Motion-Augmented_RGB_Stream_for_Action_Recognition_CVPR_2019_paper.html","paper_title":"MARS: Motion-Augmented RGB Stream for Action Recognition","code":"https://github.com/craston/MARS","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":183,"model":"SlowFast-8×8-R50","metrics":{"Acc@1":"68.45","FLOPs (G) x views":"66.25x1","Parameters (M)":"66.25"},"uses_additional_data":false,"paper_date":"2021-05-31","paper":"/paper/continual-3d-convolutional-neural-networks","paper_url":"https://arxiv.org/abs/2106.00050v3","paper_title":"Continual 3D Convolutional Neural Networks for Real-time Processing of Videos","code":"https://github.com/LukasHedegaard/co3d","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":184,"model":"S3D-G (Flow, ImageNet pretrained)","metrics":{"Acc@1":"68","Acc@5":"87.6"},"uses_additional_data":false,"paper_date":"2017-12-13","paper":"/paper/rethinking-spatiotemporal-feature-learning","paper_url":"http://arxiv.org/abs/1712.04851v2","paper_title":"Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification","code":"https://github.com/kylemin/S3D","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":185,"model":"R[2+1]D-Flow","metrics":{"Acc@1":"67.5","Acc@5":"87.2"},"uses_additional_data":false,"paper_date":"2017-11-30","paper":"/paper/a-closer-look-at-spatiotemporal-convolutions","paper_url":"http://arxiv.org/abs/1711.11248v3","paper_title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","code":"https://github.com/microsoft/computervision-recipes","n_code_links":24,"official":{"repos":["facebookresearch/R2Plus1D"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":3,"n_samples":4,"n_pointer_only_licence":4,"sample_list":"/paper/a-closer-look-at-spatiotemporal-convolutions#ran","syntology_url":"https://syntology.ai/paper/1711.11248","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.11248"}}}},{"rank_in_archive_order":186,"model":"Slow-8x8-R50","metrics":{"Acc@1":"67.42","FLOPs (G) x views":"54.87x1","Parameters (M)":"32.45"},"uses_additional_data":false,"paper_date":"2021-05-31","paper":"/paper/continual-3d-convolutional-neural-networks","paper_url":"https://arxiv.org/abs/2106.00050v3","paper_title":"Continual 3D Convolutional Neural Networks for Real-time Processing of Videos","code":"https://github.com/LukasHedegaard/co3d","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":187,"model":"Co X3D-S_64","metrics":{"Acc@1":"67.33","FLOPs (G) x views":"0.17x1","Parameters (M)":"3.79"},"uses_additional_data":false,"paper_date":"2021-05-31","paper":"/paper/continual-3d-convolutional-neural-networks","paper_url":"https://arxiv.org/abs/2106.00050v3","paper_title":"Continual 3D Convolutional Neural Networks for Real-time Processing of Videos","code":"https://github.com/LukasHedegaard/co3d","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":188,"model":"X3D-M","metrics":{"Acc@1":"67.24","FLOPs (G) x views":"4.97x1","Parameters (M)":"3.79"},"uses_additional_data":false,"paper_date":"2021-05-31","paper":"/paper/continual-3d-convolutional-neural-networks","paper_url":"https://arxiv.org/abs/2106.00050v3","paper_title":"Continual 3D Convolutional Neural Networks for Real-time Processing of Videos","code":"https://github.com/LukasHedegaard/co3d","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":189,"model":"SlowFast-4×16-R50","metrics":{"Acc@1":"67.06","FLOPs (G) x views":"36.46x1","Parameters (M)":"34.48"},"uses_additional_data":false,"paper_date":"2021-05-31","paper":"/paper/continual-3d-convolutional-neural-networks","paper_url":"https://arxiv.org/abs/2106.00050v3","paper_title":"Continual 3D Convolutional Neural Networks for Real-time Processing of Videos","code":"https://github.com/LukasHedegaard/co3d","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":190,"model":"Co Slow_8","metrics":{"Acc@1":"65.90","FLOPs (G) x views":"6.90x1","Parameters (M)":"32.45"},"uses_additional_data":false,"paper_date":"2021-05-31","paper":"/paper/continual-3d-convolutional-neural-networks","paper_url":"https://arxiv.org/abs/2106.00050v3","paper_title":"Continual 3D Convolutional Neural Networks for Real-time Processing of Videos","code":"https://github.com/LukasHedegaard/co3d","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":191,"model":"MoViNet-A0","metrics":{"Acc@1":"65.8","Acc@5":"87.4","FLOPs (G) x views":"2.7x1"},"uses_additional_data":false,"paper_date":"2021-03-21","paper":"/paper/movinets-mobile-video-networks-for-efficient","paper_url":"https://arxiv.org/abs/2103.11511v2","paper_title":"MoViNets: Mobile Video Networks for Efficient Video Recognition","code":"https://github.com/tensorflow/models","n_code_links":3,"official":{"repos":["tensorflow/models"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":9,"n_constructed":6,"n_ran_checked":8,"n_instrument":1,"n_unverified":4,"n_samples":13,"n_pointer_only_licence":0,"sample_list":"/paper/movinets-mobile-video-networks-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2103.11511","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.11511"}}}},{"rank_in_archive_order":192,"model":"X3D-S","metrics":{"Acc@1":"64.71","FLOPs (G) x views":"2.06x1","Parameters (M)":"3.79"},"uses_additional_data":false,"paper_date":"2021-05-31","paper":"/paper/continual-3d-convolutional-neural-networks","paper_url":"https://arxiv.org/abs/2106.00050v3","paper_title":"Continual 3D Convolutional Neural Networks for Real-time Processing of Videos","code":"https://github.com/LukasHedegaard/co3d","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":193,"model":"I3D-R50","metrics":{"Acc@1":"63.98","FLOPs (G) x views":"28.61x1","Parameters (M)":"28.04"},"uses_additional_data":false,"paper_date":"2021-05-31","paper":"/paper/continual-3d-convolutional-neural-networks","paper_url":"https://arxiv.org/abs/2106.00050v3","paper_title":"Continual 3D Convolutional Neural Networks for Real-time Processing of Videos","code":"https://github.com/LukasHedegaard/co3d","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":194,"model":"Co X3D-L_16","metrics":{"Acc@1":"63.03","FLOPs (G) x views":"1.25x1","Parameters (M)":"6.15"},"uses_additional_data":false,"paper_date":"2021-05-31","paper":"/paper/continual-3d-convolutional-neural-networks","paper_url":"https://arxiv.org/abs/2106.00050v3","paper_title":"Continual 3D Convolutional Neural Networks for Real-time Processing of Videos","code":"https://github.com/LukasHedegaard/co3d","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":195,"model":"Co X3D-M_16","metrics":{"Acc@1":"62.80","FLOPs (G) x views":"0.33x1","Parameters (M)":"3.79"},"uses_additional_data":false,"paper_date":"2021-05-31","paper":"/paper/continual-3d-convolutional-neural-networks","paper_url":"https://arxiv.org/abs/2106.00050v3","paper_title":"Continual 3D Convolutional Neural Networks for Real-time Processing of Videos","code":"https://github.com/LukasHedegaard/co3d","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":196,"model":"Co X3D-S_13","metrics":{"Acc@1":"60.18","FLOPs (G) x views":"0.17x1","Parameters (M)":"3.79"},"uses_additional_data":false,"paper_date":"2021-05-31","paper":"/paper/continual-3d-convolutional-neural-networks","paper_url":"https://arxiv.org/abs/2106.00050v3","paper_title":"Continual 3D Convolutional Neural Networks for Real-time Processing of Videos","code":"https://github.com/LukasHedegaard/co3d","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":197,"model":"Co I3D_8","metrics":{"Acc@1":"59.58","FLOPs (G) x views":"5.68x1","Parameters (M)":"28.04"},"uses_additional_data":false,"paper_date":"2021-05-31","paper":"/paper/continual-3d-convolutional-neural-networks","paper_url":"https://arxiv.org/abs/2106.00050v3","paper_title":"Continual 3D Convolutional Neural Networks for Real-time Processing of Videos","code":"https://github.com/LukasHedegaard/co3d","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":198,"model":"R(2+1)D-18_16","metrics":{"Acc@1":"59.52","FLOPs (G) x views":"40.71x1","Parameters (M)":"31.51"},"uses_additional_data":false,"paper_date":"2021-05-31","paper":"/paper/continual-3d-convolutional-neural-networks","paper_url":"https://arxiv.org/abs/2106.00050v3","paper_title":"Continual 3D Convolutional Neural Networks for Real-time Processing of Videos","code":"https://github.com/LukasHedegaard/co3d","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":199,"model":"X3D-XS","metrics":{"Acc@1":"59.37","FLOPs (G) x views":"0.64x1","Parameters (M)":"3.79"},"uses_additional_data":false,"paper_date":"2021-05-31","paper":"/paper/continual-3d-convolutional-neural-networks","paper_url":"https://arxiv.org/abs/2106.00050v3","paper_title":"Continual 3D Convolutional Neural Networks for Real-time Processing of Videos","code":"https://github.com/LukasHedegaard/co3d","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":200,"model":"Co I3D_64","metrics":{"Acc@1":"56.86","FLOPs (G) x views":"5.68x1","Parameters (M)":"28.04"},"uses_additional_data":false,"paper_date":"2021-05-31","paper":"/paper/continual-3d-convolutional-neural-networks","paper_url":"https://arxiv.org/abs/2106.00050v3","paper_title":"Continual 3D Convolutional Neural Networks for Real-time Processing of Videos","code":"https://github.com/LukasHedegaard/co3d","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":201,"model":"R(2+1)D-18_8","metrics":{"Acc@1":"53.52","FLOPs (G) x views":"20.35x1","Parameters (M)":"31.51"},"uses_additional_data":false,"paper_date":"2021-05-31","paper":"/paper/continual-3d-convolutional-neural-networks","paper_url":"https://arxiv.org/abs/2106.00050v3","paper_title":"Continual 3D Convolutional Neural Networks for Real-time Processing of Videos","code":"https://github.com/LukasHedegaard/co3d","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":202,"model":"RCU_8","metrics":{"Acc@1":"53.40","FLOPs (G) x views":"4.71x1","Parameters (M)":"12.80"},"uses_additional_data":false,"paper_date":"2021-05-31","paper":"/paper/continual-3d-convolutional-neural-networks","paper_url":"https://arxiv.org/abs/2106.00050v3","paper_title":"Continual 3D Convolutional Neural Networks for Real-time Processing of Videos","code":"https://github.com/LukasHedegaard/co3d","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":203,"model":"ViViT-L/16x2 320","metrics":{"Acc@5":"94.7"},"uses_additional_data":false,"paper_date":"2021-03-29","paper":"/paper/2103-15691","paper_url":"https://arxiv.org/abs/2103.15691v2","paper_title":"ViViT: A Video Vision Transformer","code":"https://github.com/google-research/scenic","n_code_links":10,"official":{"repos":["google-research/scenic"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"syntology":{"n_ran":14,"n_constructed":10,"n_ran_checked":13,"n_instrument":1,"n_unverified":7,"n_samples":21,"n_pointer_only_licence":1,"sample_list":"/paper/2103-15691#ran","syntology_url":"https://syntology.ai/paper/2103.15691","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.15691"}}}},{"rank_in_archive_order":204,"model":"ViT-B-VTN+ ImageNet-21K (84.0 [10])","metrics":{"Acc@5":"94.2"},"uses_additional_data":false,"paper_date":"2021-02-01","paper":"/paper/video-transformer-network","paper_url":"https://arxiv.org/abs/2102.00719v3","paper_title":"Video Transformer Network","code":"https://github.com/bomri/SlowFast/blob/master/projects/vtn/README.md","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":205,"model":"SlowFast 16x8 (ResNet-101 + NL)","metrics":{"Acc@5":"93.9"},"uses_additional_data":false,"paper_date":"2018-12-10","paper":"/paper/slowfast-networks-for-video-recognition","paper_url":"https://arxiv.org/abs/1812.03982v3","paper_title":"SlowFast Networks for Video Recognition","code":"https://github.com/facebookresearch/SlowFast","n_code_links":15,"official":{"repos":["facebookresearch/SlowFast"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"n_samples":10,"n_pointer_only_licence":1,"sample_list":"/paper/slowfast-networks-for-video-recognition#ran","syntology_url":"https://syntology.ai/paper/1812.03982","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.03982"}}}},{"rank_in_archive_order":206,"model":"ViT-B-VTN (1 layer, ImageNet pretrain)","metrics":{"Acc@5":"93.4"},"uses_additional_data":false,"paper_date":"2021-02-01","paper":"/paper/video-transformer-network","paper_url":"https://arxiv.org/abs/2102.00719v3","paper_title":"Video Transformer Network","code":"https://github.com/bomri/SlowFast/blob/master/projects/vtn/README.md","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":207,"model":"MViT-B (train from scratch)","metrics":{"FLOPs (G) x views":"225x5"},"uses_additional_data":false,"paper_date":"2021-12-02","paper":"/paper/improved-multiscale-vision-transformers-for","paper_url":"https://arxiv.org/abs/2112.01526v2","paper_title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":9,"official":null,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"adjudicator":"Claude Opus 5.5","adjudicator_from":"groundwork/59_code_with_papers/LB_EXTRACTOR_PREREG.md (not recorded in lb_measurement.json; the file's frozen_commit, measured_on and counts equal the run the pre-registration records)","adjudicator_sensitivity":[69,70],"adjudicator_specificity":[101,103],"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication by a model (adjudicator) of accepted entries on a held-out split of archive papers, rules frozen before the test; adjudicator_sensitivity and adjudicator_specificity are its own controls as [judged right, of]; it was not measured on the newer papers placed here","measurement_sentence":"Measured before publishing, on held-out archive papers: the extractor was given 883 of them and produced output for 881 (the other 2 had no title and were excluded before any model call, so they are not part of this measurement). A model adjudicator (Claude Opus 5.5), blind to which entries were real, judged 108 of 110 accepted entries correct on those held-out archive papers; its own controls: 69 of 70 archive-confirmed entries judged true, 101 of 103 corrupted copies judged false. It was not measured on the newer papers whose results are placed on this site.","coverage":{"sentence":"Syntology has checked 8,886 of the 18,637 papers on this site that are newer than the archive (for 3,717 of them no archive leaderboard matched the paper's tables, so there was nothing further to check); 733 were read and have nothing to place (arXiv has no HTML version of the paper, or that version has no tables), 41 could not be read (the extractor's reply could not be parsed), and results from the other 8,977 appear after they are checked.","complete":false,"papers_newer_than_archive":18637,"papers_checked":8886,"papers_checked_no_leaderboard_matched":3717,"papers_read_nothing_to_place":733,"papers_could_not_be_read":41,"papers_could_not_be_read_by_status":{"unparseable":41},"papers_extracted_not_yet_verified":0,"boards_without_verdict":3,"papers_not_yet_extracted":8975},"board_status":{"sentence":"Of the 8,888 newer papers whose tables Syntology has read (8,886 checked in full and 2 with a leaderboard still awaiting a verdict), none had this board among the leaderboards the extractor considered for their tables yet (it keeps at most 10 boards per paper and 4 per dataset; the lists of 1,596 of the 8,888 were already full without this board, so if it was crowded out of them it is not counted), so none await a verdict here.","note":"papers, from the extractor's own records, over the newer papers whose tables were read; proposed = no_cell_passed_checks + rejected_by_independent_check + accepted_not_placed + awaiting_verdict + placed; counts, never a rate","eligible":true,"eligible_note":"false when the extractor never considers this board: it loads only boards with archive rows and at least one metric column (lb_extract.py Boards), so no newer paper can be proposed here; archive_rows and metric_columns say which","archive_rows":207,"metric_columns":6,"papers_read":8888,"papers_read_checked":8886,"papers_read_awaiting_verdict":2,"papers_read_verified":8888,"papers_read_not_yet_verified":0,"papers_read_at_candidate_cap":1596,"papers_read_list_full_without_this_board":1596,"candidates":0,"candidates_capped_note":"candidates = papers that had this board among the leaderboards the extractor considered for their tables; the extractor keeps at most 10 per paper and 4 per dataset, so a board crowded out of a paper's list is not counted and candidates is a floor; papers_read_list_full_without_this_board counts the read papers whose list did not hold this board and had reached 10, or held 4 boards of this board's dataset (the only papers that could have crowded it out); papers_read_at_candidate_cap counts, over every board, the papers whose list reached 10","proposed":0,"no_cell_passed_checks":0,"rejected_by_independent_check":0,"accepted_not_placed":0,"awaiting_verdict":0,"placed":0,"placed_entries_listed":0,"file_lines_unreadable_as_read":0,"since_line":"Since the archive (Syntology): none placed; no newer paper judged to report on this board so far"},"judged_to_report":{"heading":"Newer papers whose tables a model judged to report on this benchmark (a model's judgement, not a result; newest first by arXiv id)","judged_by":{"model":"a model","models_as_recorded":[],"a_record_without_a_model":false,"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here","order":"newest first by arXiv id (the identifier's order, not a rank)","outcomes":{"placed":"placed","no_cell_passed_checks":"no cell passed the extractor's checks","refused_by_rule":"refused by a rule","rejected":"rejected by the independent check","accepted_not_placed":"accepted by the independent check but not placed by this site","awaiting":"awaiting a verdict"},"reason_note":"for refused_by_rule, the rules' plain words for the reason codes the record gives (never the quoted or the actual cell text); null for every other outcome","total":0,"shown_on_page":0,"no_cell_split":{"no_cell_passed_checks_in_ledger":0,"rows_refused_by_rule":0,"rows_no_cell_passed_checks":0},"rows":[]},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per row: of M harvested code samples from that row's paper, n_ran executed on a synthesized fixture (n_ran = n_ran_checked + n_instrument; n_instrument counts failures of Syntology's instrument, not of the code); the other M - n_ran are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"rows_with_graph_line":109,"rows_with_any_sample_ran":102,"rows_with_a_run_with_no_instrument_failure":91,"official":{"state_rule":"the archive's official repositories have samples for this paper that ran: 'official (archive's flag): N ran' (N counts them, instrument failures included); they have samples, none ran: 'official: harvested, nothing ran'; they have no sample for this paper and another sample ran: 'community repositories only' when every sample that ran came from a repository the archive lists for the paper but neither marks official nor records as mentioned in it, or one Syntology harvested outside the archive's links, else 'official: no sample here; runs from other or unrecorded repositories' (a repository named in the paper or found in its text by Syntology, or no repository recorded); otherwise 'official: harvested for another paper' or 'official: not harvested'. Absent when the archive marks no repository official. Official is the archive's is_official flag, not an authorship verdict","flag":"the archive's is_official flag for the paper's code link; not a verdict on who wrote the code","rows_with_an_archive_official_repository":98,"rows_whose_official_repository_has_a_sample_that_ran":53,"rows_whose_official_repository_has_a_run_with_no_instrument_failure":43,"rows_community_repositories_only":32,"rows_runs_from_other_or_unrecorded_repositories":5,"note":"rows[].official, per row with a graph line: repos (marked official in the archive), state, n_ran and n_unverified (samples from those repositories), and ran_from_kinds (the kinds of repository the paper's samples that ran came from; 'unlocated' is no repository recorded)"},"filters":{"ran_modes":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"the page's filters hide rows and never renumber them; they read the Ran cell's counts, the same figures rows[].syntology and rows[].official carry"},"row_route":"rows[].syntology carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","distinct_papers_with_graph_line":54,"distinct_papers_with_any_sample_ran":51,"distinct_papers_with_a_run_with_no_instrument_failure":46,"samples_over_distinct_papers":{"n_ran":410,"n_constructed":87,"n_ran_checked":301,"n_instrument":109,"n_unverified":204,"n_samples":614,"n_pointer_only_licence":161,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":893,"n_constructed":230,"n_ran_checked":689,"n_instrument":204,"n_unverified":434,"n_samples":1327,"n_pointer_only_licence":335,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}},"record_sha256":"de3bffab73fa72668041a08da62ed14d86e32c27030ed433866e2748be605fe5","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}