{"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-recognition-in-videos-on-something","task":{"name":"Action Recognition","url":"/task/action-recognition-in-videos","note":null},"dataset":{"name":"Something-Something V2","url":"/dataset/something-something-v2"},"category":"Computer Vision","categories":["Computer Vision","Time Series"],"category_note":null,"description":"**Action Recognition** is a computer vision task that involves recognizing human actions in videos or images. The goal is to classify and categorize the actions being performed in the video or image into a predefined set of action classes.\r\n\r\nIn the video domain, it is an open question whether training an action classification network on a sufficiently large dataset, will give a similar boost in performance when applied to a different temporal task or dataset. The challenges of building video datasets has meant that most popular benchmarks for action recognition are small, having on the order of 10k videos. \r\n\r\nPlease note some benchmarks may be located in the [Action Classification](https://paperswithcode.com/task/action-classification) or [Video Classification](https://paperswithcode.com/task/video-classification) tasks, e.g. Kinetics-400.","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":["Top-1 Accuracy","Top-5 Accuracy","Parameters","GFLOPs"],"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":{"Top-1 Accuracy":"higher","Top-5 Accuracy":"higher","Parameters":null,"GFLOPs":null}},"counts":{"rows":123,"rows_with_code":103,"rows_with_paper_page":123,"rows_dated":123,"rows_using_additional_data":70},"rows":[{"rank_in_archive_order":1,"model":"MVD (Kinetics400 pretrain, ViT-H, 16 frame)","metrics":{"GFLOPs":"1192x6","Parameters":"633","Top-1 Accuracy":"77.3","Top-5 Accuracy":"95.7"},"uses_additional_data":true,"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":2,"model":"DejaVid","metrics":{"Top-1 Accuracy":"77.2","Top-5 Accuracy":"96.3"},"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":3,"model":"InternVideo","metrics":{"Top-1 Accuracy":"77.2"},"uses_additional_data":true,"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":4,"model":"InternVideo2-1B","metrics":{"Top-1 Accuracy":"77.1"},"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":5,"model":"VideoMAE V2-g","metrics":{"GFLOPs":"2544x6","Parameters":"1013","Top-1 Accuracy":"77.0","Top-5 Accuracy":"95.9"},"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":6,"model":"MVD (Kinetics400 pretrain, ViT-L, 16 frame)","metrics":{"GFLOPs":"597x6","Parameters":"305","Top-1 Accuracy":"76.7","Top-5 Accuracy":"95.5"},"uses_additional_data":true,"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":7,"model":"Hiera-L (no extra data)","metrics":{"Top-1 Accuracy":"76.5"},"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":8,"model":"TubeViT-L","metrics":{"Top-1 Accuracy":"76.1","Top-5 Accuracy":"95.2"},"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":9,"model":"VideoMAE (no extra data, ViT-L, 32x2)","metrics":{"GFLOPs":"1436x3","Parameters":"305","Top-1 Accuracy":"75.4","Top-5 Accuracy":"95.2"},"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":10,"model":"Side4Video (EVA ViT-E/14)","metrics":{"Top-1 Accuracy":"75.2","Top-5 Accuracy":"94.0"},"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":11,"model":"MaskFeat (Kinetics600 pretrain, MViT-L)","metrics":{"GFLOPs":"2828*3","Parameters":"218","Top-1 Accuracy":"75.0","Top-5 Accuracy":"95.0"},"uses_additional_data":true,"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":12,"model":"MAR (50% mask, ViT-L, 16x4)","metrics":{"GFLOPs":"276x6","Parameters":"311","Top-1 Accuracy":"74.7","Top-5 Accuracy":"94.9"},"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":13,"model":"ATM","metrics":{"Top-1 Accuracy":"74.6","Top-5 Accuracy":"94.4"},"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":14,"model":"MAWS (ViT-L)","metrics":{"Top-1 Accuracy":"74.4"},"uses_additional_data":true,"paper_date":"2023-03-23","paper":"/paper/the-effectiveness-of-mae-pre-pretraining-for","paper_url":"https://arxiv.org/abs/2303.13496v3","paper_title":"The effectiveness of MAE pre-pretraining for billion-scale pretraining","code":"https://github.com/facebookresearch/maws","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":15,"model":"VideoMAE (no extra data, ViT-L, 16frame)","metrics":{"GFLOPs":"597x6","Parameters":"305","Top-1 Accuracy":"74.3","Top-5 Accuracy":"94.6"},"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":16,"model":"MAR (75% mask, ViT-L, 16x4)","metrics":{"GFLOPs":"131x6","Parameters":"311","Top-1 Accuracy":"73.8","Top-5 Accuracy":"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":17,"model":"MVD (Kinetics400 pretrain, ViT-B, 16 frame)","metrics":{"GFLOPs":"180x6","Parameters":"87","Top-1 Accuracy":"73.7","Top-5 Accuracy":"94.0"},"uses_additional_data":true,"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":18,"model":"ViC-MAE (ViT-L)","metrics":{"Top-1 Accuracy":"73.7"},"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":19,"model":"TAdaFormer-L/14","metrics":{"Top-1 Accuracy":"73.6"},"uses_additional_data":true,"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":20,"model":"TDS-CLIP-ViT-L/14(8frames)","metrics":{"Top-1 Accuracy":"73.4","Top-5 Accuracy":"93.8"},"uses_additional_data":false,"paper_date":"2024-08-20","paper":"/paper/tds-clip-temporal-difference-side-network-for","paper_url":"https://arxiv.org/abs/2408.10688v1","paper_title":"TDS-CLIP: Temporal Difference Side Network for Image-to-Video Transfer Learning","code":"https://github.com/BBYL9413/TDS-CLIP","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":21,"model":"MViTv2-L (IN-21K + Kinetics400 pretrain)","metrics":{"Parameters":"213.1","Top-1 Accuracy":"73.3","Top-5 Accuracy":"94.1"},"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},{"rank_in_archive_order":22,"model":"AMD(ViT-B/16)","metrics":{"GFLOPs":"180x6","Parameters":"87","Top-1 Accuracy":"73.3","Top-5 Accuracy":"94.0"},"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":23,"model":"UniFormerV2-L","metrics":{"GFLOPs":"5154","Top-1 Accuracy":"73.0","Top-5 Accuracy":"94.5"},"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":24,"model":"ST-Adapter (ViT-L, CLIP)","metrics":{"GFLOPs":"8248","Top-1 Accuracy":"72.3","Top-5 Accuracy":"93.9"},"uses_additional_data":true,"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":25,"model":"ZeroI2V ViT-L/14","metrics":{"Top-1 Accuracy":"72.2","Top-5 Accuracy":"93.0"},"uses_additional_data":true,"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":26,"model":"MViT-B (IN-21K + Kinetics400 pretrain)","metrics":{"GFLOPs":"225x3","Top-1 Accuracy":"72.1"},"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":27,"model":"CAST(ViT-B/16)","metrics":{"Top-1 Accuracy":"71.6"},"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":28,"model":"StructVit-B-4-1","metrics":{"Top-1 Accuracy":"71.5"},"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":29,"model":"OMNIVORE (Swin-B,  IN-21K+ Kinetics400 pretrain)","metrics":{"Top-1 Accuracy":"71.4","Top-5 Accuracy":"93.5"},"uses_additional_data":true,"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":30,"model":"BEVT (IN-1K + Kinetics400 pretrain)","metrics":{"GFLOPs":"321x3","Parameters":"89","Top-1 Accuracy":"71.4","Top-5 Accuracy":"-"},"uses_additional_data":true,"paper_date":"2021-12-02","paper":"/paper/bevt-bert-pretraining-of-video-transformers","paper_url":"https://arxiv.org/abs/2112.01529v3","paper_title":"BEVT: BERT Pretraining of Video Transformers","code":"https://github.com/xyzforever/bevt","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":31,"model":"UniFormer-B (IN-1K + Kinetics400 pretrain)","metrics":{"GFLOPs":"259x3","Parameters":"50.1","Top-1 Accuracy":"71.2","Top-5 Accuracy":"92.8"},"uses_additional_data":true,"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":32,"model":"TAdaConvNeXtV2-B","metrics":{"Top-1 Accuracy":"71.1"},"uses_additional_data":true,"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":33,"model":"MAR (50% mask, ViT-B, 16x4)","metrics":{"GFLOPs":"86x6","Parameters":"94","Top-1 Accuracy":"71.0","Top-5 Accuracy":"92.8"},"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":34,"model":"MVD (Kinetics400 pretrain, ViT-S, 16 frame)","metrics":{"GFLOPs":"57x6","Parameters":"22","Top-1 Accuracy":"70.9","Top-5 Accuracy":"92.8"},"uses_additional_data":true,"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":35,"model":"CoVeR(JFT-3B)","metrics":{"Top-1 Accuracy":"70.9","Top-5 Accuracy":"92.5"},"uses_additional_data":true,"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":36,"model":"VideoMAE (no extra data, ViT-B, 16frame)","metrics":{"GFLOPs":"180x6","Parameters":"87","Top-1 Accuracy":"70.8","Top-5 Accuracy":"92.4"},"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":"AMD(ViT-S/16)","metrics":{"GFLOPs":"57x6","Parameters":"22","Top-1 Accuracy":"70.2","Top-5 Accuracy":"92.5"},"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":38,"model":"ILA (ViT-L/14)","metrics":{"Top-1 Accuracy":"70.2","Top-5 Accuracy":"91.8"},"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":39,"model":"MorphMLP-B (IN-1K)","metrics":{"GFLOPs":"197x3","Parameters":"68.5","Top-1 Accuracy":"70.1","Top-5 Accuracy":"92.8"},"uses_additional_data":true,"paper_date":"2021-11-24","paper":"/paper/morphmlp-a-self-attention-free-mlp-like","paper_url":"https://arxiv.org/abs/2111.12527v3","paper_title":"MorphMLP: An Efficient MLP-Like Backbone for Spatial-Temporal Representation Learning","code":"https://github.com/liuruiyang98/Jittor-MLP","n_code_links":2,"official":{"repos":["MTLab/MorphMLP"],"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/morphmlp-a-self-attention-free-mlp-like#ran","syntology_url":"https://syntology.ai/paper/2111.12527","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.12527"}}}},{"rank_in_archive_order":40,"model":"CoVeR(JFT-300M)","metrics":{"Top-1 Accuracy":"69.8","Top-5 Accuracy":"91.9"},"uses_additional_data":true,"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":41,"model":"TPS","metrics":{"Top-1 Accuracy":"69.8"},"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":42,"model":"SIFA","metrics":{"Top-1 Accuracy":"69.8"},"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":43,"model":"Swin-B (IN-21K + Kinetics400 pretrain)","metrics":{"GFLOPs":"321x3","Parameters":"89","Top-1 Accuracy":"69.6","Top-5 Accuracy":"92.7"},"uses_additional_data":true,"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":44,"model":"TDN ResNet101 (one clip, three crop, 8+16 ensemble, ImageNet pretrained, RGB only)","metrics":{"GFLOPs":"198x3","Top-1 Accuracy":"69.6","Top-5 Accuracy":"92.2"},"uses_additional_data":true,"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":45,"model":"MAR (75% mask, ViT-B, 16x4)","metrics":{"GFLOPs":"41x6","Parameters":"94","Top-1 Accuracy":"69.5","Top-5 Accuracy":"91.9"},"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":46,"model":"ORViT Mformer-L (ORViT blocks)","metrics":{"GFLOPs":"N/A","Parameters":"N/A","Top-1 Accuracy":"69.5","Top-5 Accuracy":"91.5"},"uses_additional_data":true,"paper_date":"2021-10-13","paper":"/paper/object-region-video-transformers-1","paper_url":"https://arxiv.org/abs/2110.06915v3","paper_title":"Object-Region Video Transformers","code":"https://github.com/eladb3/orvit","n_code_links":1,"official":null,"syntology":{"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_samples":7,"n_pointer_only_licence":7,"sample_list":"/paper/object-region-video-transformers-1#ran","syntology_url":"https://syntology.ai/paper/2110.06915","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.06915"}}}},{"rank_in_archive_order":47,"model":"UniFormer-S (IN-1K + Kinetics600 pretrain)","metrics":{"GFLOPs":"41.8x3","Parameters":"21.4","Top-1 Accuracy":"69.4","Top-5 Accuracy":"92.1"},"uses_additional_data":true,"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":48,"model":"MML (ensemble)","metrics":{"Top-1 Accuracy":"69.02","Top-5 Accuracy":"92.70"},"uses_additional_data":true,"paper_date":"2020-11-04","paper":"/paper/mutual-modality-learning-for-video-action","paper_url":"https://arxiv.org/abs/2011.02543v1","paper_title":"Mutual Modality Learning for Video Action Classification","code":"https://github.com/papermsucode/mutual-modality-learning","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":49,"model":"MViT-B-24, 32x3","metrics":{"GFLOPs":"236x3","Parameters":"53.2M","Top-1 Accuracy":"68.7","Top-5 Accuracy":"91.5"},"uses_additional_data":true,"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":50,"model":"MTV-B","metrics":{"Top-1 Accuracy":"68.5","Top-5 Accuracy":"90.4"},"uses_additional_data":true,"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":51,"model":"MLP-3D","metrics":{"Top-1 Accuracy":"68.5"},"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":52,"model":"TDN ResNet101 (one clip, center crop, 8+16 ensemble, ImageNet pretrained, RGB only)","metrics":{"GFLOPs":"198x1","Top-1 Accuracy":"68.2","Top-5 Accuracy":"91.6"},"uses_additional_data":true,"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":53,"model":"MSMA (8+16frames)","metrics":{"Top-1 Accuracy":"68.2"},"uses_additional_data":false,"paper_date":"2023-02-19","paper":"/paper/multi-scale-motion-aware-module-for-video","paper_url":"https://link.springer.com/chapter/10.1007/978-3-031-25075-0_40","paper_title":"Multi-scale Motion-Aware Module for Video Action Recognition","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":54,"model":"Mformer-L","metrics":{"GFLOPs":"1181x3","Parameters":"N/A","Top-1 Accuracy":"68.1","Top-5 Accuracy":"91.2"},"uses_additional_data":true,"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":55,"model":"VIMPAC","metrics":{"Top-1 Accuracy":"68.1"},"uses_additional_data":true,"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":56,"model":"ORViT Mformer (ORViT blocks)","metrics":{"GFLOPs":"N/A","Parameters":"N/A","Top-1 Accuracy":"67.9","Top-5 Accuracy":"90.5"},"uses_additional_data":true,"paper_date":"2021-10-13","paper":"/paper/object-region-video-transformers-1","paper_url":"https://arxiv.org/abs/2110.06915v3","paper_title":"Object-Region Video Transformers","code":"https://github.com/eladb3/orvit","n_code_links":1,"official":null,"syntology":{"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_samples":7,"n_pointer_only_licence":7,"sample_list":"/paper/object-region-video-transformers-1#ran","syntology_url":"https://syntology.ai/paper/2110.06915","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.06915"}}}},{"rank_in_archive_order":57,"model":"MViT-B, 32x3(Kinetics600 pretrain)","metrics":{"GFLOPs":"170x3","Parameters":"36.6","Top-1 Accuracy":"67.8","Top-5 Accuracy":"91.3"},"uses_additional_data":true,"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":58,"model":"GC-TDN Ensemble (R50,8+16)","metrics":{"GFLOPs":"110.1","Parameters":"27.4","Top-1 Accuracy":"67.8","Top-5 Accuracy":"91.2"},"uses_additional_data":true,"paper_date":"2022-03-18","paper":"/paper/group-contextualization-for-video-recognition","paper_url":"https://arxiv.org/abs/2203.09694v1","paper_title":"Group Contextualization for Video Recognition","code":"https://github.com/haoyanbin918/group-contextualization","n_code_links":1,"official":{"repos":["haoyanbin918/group-contextualization"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":5,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":5,"n_constructed":5,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":0,"sample_list":"/paper/group-contextualization-for-video-recognition#ran","syntology_url":"https://syntology.ai/paper/2203.09694","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.09694"}}}},{"rank_in_archive_order":59,"model":"CT-Net Ensemble (R50, 8+12+16+24)","metrics":{"GFLOPs":"280","Parameters":"83.8","Top-1 Accuracy":"67.8","Top-5 Accuracy":"91.1"},"uses_additional_data":true,"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":60,"model":"TCM (Ensemble)","metrics":{"Top-1 Accuracy":"67.8"},"uses_additional_data":false,"paper_date":"2022-02-24","paper":"/paper/slow-fast-visual-tempo-learning-for-video","paper_url":"https://arxiv.org/abs/2202.12116v2","paper_title":"Motion-driven Visual Tempo Learning for Video-based Action Recognition","code":"https://github.com/yzfly/tcm","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":61,"model":"SELFYNet-TSM-R50En (8+16 frames, ImageNet pretrained, 2 clips)","metrics":{"Top-1 Accuracy":"67.7","Top-5 Accuracy":"91.1"},"uses_additional_data":true,"paper_date":"2021-02-14","paper":"/paper/learning-self-similarity-in-space-and-time-as-1","paper_url":"https://arxiv.org/abs/2102.07092v3","paper_title":"Learning Self-Similarity in Space and Time as Generalized Motion for Video Action Recognition","code":"https://github.com/arunos728/SELFY","n_code_links":1,"official":{"repos":["arunos728/SELFY"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":4,"sample_list":"/paper/learning-self-similarity-in-space-and-time-as-1#ran","syntology_url":"https://syntology.ai/paper/2102.07092","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.07092"}}}},{"rank_in_archive_order":62,"model":"RSANet-R50 (8+16 frames, ImageNet pretrained, 2 clips","metrics":{"Top-1 Accuracy":"67.7","Top-5 Accuracy":"91.1"},"uses_additional_data":true,"paper_date":"2021-11-02","paper":"/paper/relational-self-attention-what-s-missing-in","paper_url":"https://arxiv.org/abs/2111.01673v1","paper_title":"Relational Self-Attention: What's Missing in Attention for Video Understanding","code":"https://github.com/KimManjin/RSA","n_code_links":1,"official":{"repos":["KimManjin/RSA"],"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":1,"sample_list":"/paper/relational-self-attention-what-s-missing-in#ran","syntology_url":"https://syntology.ai/paper/2111.01673","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.01673"}}}},{"rank_in_archive_order":63,"model":"GTDNet","metrics":{"Top-1 Accuracy":"67.6"},"uses_additional_data":false,"paper_date":"2022-11-23","paper":"/paper/global-temporal-difference-network-for-action","paper_url":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9961904","paper_title":"Global Temporal Difference Network for Action Recognition","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":64,"model":"SELFYNet-TSM-R50En (8+16 frames, ImageNet pretrained, a single clip)","metrics":{"Top-1 Accuracy":"67.4","Top-5 Accuracy":"91"},"uses_additional_data":true,"paper_date":"2021-02-14","paper":"/paper/learning-self-similarity-in-space-and-time-as-1","paper_url":"https://arxiv.org/abs/2102.07092v3","paper_title":"Learning Self-Similarity in Space and Time as Generalized Motion for Video Action Recognition","code":"https://github.com/arunos728/SELFY","n_code_links":1,"official":{"repos":["arunos728/SELFY"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":4,"sample_list":"/paper/learning-self-similarity-in-space-and-time-as-1#ran","syntology_url":"https://syntology.ai/paper/2102.07092","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.07092"}}}},{"rank_in_archive_order":65,"model":"VoV3D-L (32frames, Kinetics pretrained, single)","metrics":{"GFLOPs":"20.9x6","Parameters":"5.8M","Top-1 Accuracy":"67.35","Top-5 Accuracy":"90.50"},"uses_additional_data":true,"paper_date":"2020-12-01","paper":"/paper/diverse-temporal-aggregation-and-depthwise","paper_url":"https://arxiv.org/abs/2012.00317v3","paper_title":"Diverse Temporal Aggregation and Depthwise Spatiotemporal Factorization for Efficient Video Classification","code":"https://github.com/youngwanLEE/VoV3D","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":66,"model":"PLAR","metrics":{"Top-1 Accuracy":"67.3","Top-5 Accuracy":"91"},"uses_additional_data":false,"paper_date":"2023-05-21","paper":"/paper/prompt-learning-for-action-recognition","paper_url":"https://arxiv.org/abs/2305.12437v4","paper_title":"SCP: Soft Conditional Prompt Learning for Aerial Video Action Recognition","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":67,"model":"RSANet-R50 (8+16 frames, ImageNet pretrained, a single clip)","metrics":{"Top-1 Accuracy":"67.3","Top-5 Accuracy":"90.8"},"uses_additional_data":true,"paper_date":"2021-11-02","paper":"/paper/relational-self-attention-what-s-missing-in","paper_url":"https://arxiv.org/abs/2111.01673v1","paper_title":"Relational Self-Attention: What's Missing in Attention for Video Understanding","code":"https://github.com/KimManjin/RSA","n_code_links":1,"official":{"repos":["KimManjin/RSA"],"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":1,"sample_list":"/paper/relational-self-attention-what-s-missing-in#ran","syntology_url":"https://syntology.ai/paper/2111.01673","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.01673"}}}},{"rank_in_archive_order":68,"model":"X-Vit (x16)","metrics":{"GFLOPs":"850x1","Parameters":"N/A","Top-1 Accuracy":"67.2","Top-5 Accuracy":"90.8"},"uses_additional_data":true,"paper_date":"2021-06-10","paper":"/paper/space-time-mixing-attention-for-video","paper_url":"https://arxiv.org/abs/2106.05968v2","paper_title":"Space-time Mixing Attention for Video Transformer","code":"https://github.com/1adrianb/video-transformers","n_code_links":1,"official":{"repos":["1adrianb/video-transformers"],"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":0,"sample_list":"/paper/space-time-mixing-attention-for-video#ran","syntology_url":"https://syntology.ai/paper/2106.05968","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.05968"}}}},{"rank_in_archive_order":69,"model":"TAda2D-En (ResNet-50, 8+16 frames)","metrics":{"Top-1 Accuracy":"67.2","Top-5 Accuracy":"89.8"},"uses_additional_data":true,"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":70,"model":"Mformer-HR","metrics":{"GFLOPs":"958.8x3","Parameters":"N/A","Top-1 Accuracy":"67.1","Top-5 Accuracy":"90.6"},"uses_additional_data":true,"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":71,"model":"TAdaConvNeXt-T","metrics":{"Top-1 Accuracy":"67.1","Top-5 Accuracy":"90.4"},"uses_additional_data":true,"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":72,"model":"MoDS (8+16frames)","metrics":{"Top-1 Accuracy":"67.1"},"uses_additional_data":false,"paper_date":"2022-07-15","paper":"/paper/action-recognition-with-motion","paper_url":"https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9831068","paper_title":"Action Recognition With Motion Diversification and Dynamic Selection","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":73,"model":"STPG (8+16frames)","metrics":{"Top-1 Accuracy":"67.0"},"uses_additional_data":false,"paper_date":"2022-08-09","paper":"/paper/spatial-temporal-pyramid-graph-reasoning-for","paper_url":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9852978","paper_title":"Spatial-Temporal Pyramid Graph Reasoning for Action Recognition","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":74,"model":"MML (single)","metrics":{"Top-1 Accuracy":"66.83","Top-5 Accuracy":"91.30"},"uses_additional_data":true,"paper_date":"2020-11-04","paper":"/paper/mutual-modality-learning-for-video-action","paper_url":"https://arxiv.org/abs/2011.02543v1","paper_title":"Mutual Modality Learning for Video Action Classification","code":"https://github.com/papermsucode/mutual-modality-learning","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":75,"model":"ILA (ViT-B/16)","metrics":{"Top-1 Accuracy":"66.8","Top-5 Accuracy":"90.3"},"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":76,"model":"TSM (RGB + Flow)","metrics":{"Top-1 Accuracy":"66.6","Top-5 Accuracy":"91.3"},"uses_additional_data":true,"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":77,"model":"MSNet-R50En (8+16 ensemble, ImageNet pretrained)","metrics":{"Top-1 Accuracy":"66.6","Top-5 Accuracy":"90.6"},"uses_additional_data":true,"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":78,"model":"PAN ResNet101 (RGB only, no Flow)","metrics":{"Top-1 Accuracy":"66.5","Top-5 Accuracy":"90.6"},"uses_additional_data":true,"paper_date":"2020-08-08","paper":"/paper/pan-towards-fast-action-recognition-via","paper_url":"https://arxiv.org/abs/2008.03462v1","paper_title":"PAN: Towards Fast Action Recognition via Learning Persistence of Appearance","code":"https://github.com/zhang-can/PAN-PyTorch","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":79,"model":"TSM+W3 (16 frames, RGB ResNet-50)","metrics":{"Top-1 Accuracy":"66.5","Top-5 Accuracy":"90.4"},"uses_additional_data":true,"paper_date":"2020-04-02","paper":"/paper/knowing-what-where-and-when-to-look-efficient","paper_url":"https://arxiv.org/abs/2004.01278v1","paper_title":"Knowing What, Where and When to Look: Efficient Video Action Modeling with Attention","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":80,"model":"Mformer","metrics":{"Top-1 Accuracy":"66.5","Top-5 Accuracy":"90.1"},"uses_additional_data":true,"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":81,"model":"MVFNet-ResNet50 (center crop, 8+16 ensemble, ImageNet pretrained, RGB only)","metrics":{"Top-1 Accuracy":"66.3"},"uses_additional_data":true,"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":82,"model":"MViT-B, 16x4","metrics":{"Top-1 Accuracy":"66.2","Top-5 Accuracy":"90.2"},"uses_additional_data":true,"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":83,"model":"RSANet-R50 (16 frames, ImageNet pretrained, a single clip)","metrics":{"Top-1 Accuracy":"66","Top-5 Accuracy":"89.8"},"uses_additional_data":true,"paper_date":"2021-11-02","paper":"/paper/relational-self-attention-what-s-missing-in","paper_url":"https://arxiv.org/abs/2111.01673v1","paper_title":"Relational Self-Attention: What's Missing in Attention for Video Understanding","code":"https://github.com/KimManjin/RSA","n_code_links":1,"official":{"repos":["KimManjin/RSA"],"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":1,"sample_list":"/paper/relational-self-attention-what-s-missing-in#ran","syntology_url":"https://syntology.ai/paper/2111.01673","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.01673"}}}},{"rank_in_archive_order":84,"model":"VoV3D-L (32frames, from scratch, single)","metrics":{"GFLOPs":"20.9x6","Parameters":"5.8M","Top-1 Accuracy":"65.8","Top-5 Accuracy":"89.5"},"uses_additional_data":false,"paper_date":"2020-12-01","paper":"/paper/diverse-temporal-aggregation-and-depthwise","paper_url":"https://arxiv.org/abs/2012.00317v3","paper_title":"Diverse Temporal Aggregation and Depthwise Spatiotemporal Factorization for Efficient Video Classification","code":"https://github.com/youngwanLEE/VoV3D","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":85,"model":"E3D-L","metrics":{"GFLOPs":"18.3","Top-1 Accuracy":"65.7","Top-5 Accuracy":"89.8"},"uses_additional_data":false,"paper_date":"2023-03-05","paper":"/paper/maximizing-spatio-temporal-entropy-of-deep-3d","paper_url":"https://arxiv.org/abs/2303.02693v1","paper_title":"Maximizing Spatio-Temporal Entropy of Deep 3D CNNs for Efficient Video Recognition","code":"https://github.com/alibaba/lightweight-neural-architecture-search","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":86,"model":"SELFYNet-TSM-R50 (16 frames, ImageNet pretrained)","metrics":{"Top-1 Accuracy":"65.7","Top-5 Accuracy":"89.8"},"uses_additional_data":true,"paper_date":"2021-02-14","paper":"/paper/learning-self-similarity-in-space-and-time-as-1","paper_url":"https://arxiv.org/abs/2102.07092v3","paper_title":"Learning Self-Similarity in Space and Time as Generalized Motion for Video Action Recognition","code":"https://github.com/arunos728/SELFY","n_code_links":1,"official":{"repos":["arunos728/SELFY"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":4,"sample_list":"/paper/learning-self-similarity-in-space-and-time-as-1#ran","syntology_url":"https://syntology.ai/paper/2102.07092","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.07092"}}}},{"rank_in_archive_order":87,"model":"TAda2D (ResNet-50, 16 frames)","metrics":{"Top-1 Accuracy":"65.6","Top-5 Accuracy":"89.2"},"uses_additional_data":true,"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":88,"model":"ViViT-L/16x2 Fact. encoder","metrics":{"Top-1 Accuracy":"65.4","Top-5 Accuracy":"89.8"},"uses_additional_data":true,"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":89,"model":"VoV3D-M (32frames, Kinetics pretrained, single)","metrics":{"GFLOPs":"11.5x6","Parameters":"3.3M","Top-1 Accuracy":"65.24","Top-5 Accuracy":"89.48"},"uses_additional_data":true,"paper_date":"2020-12-01","paper":"/paper/diverse-temporal-aggregation-and-depthwise","paper_url":"https://arxiv.org/abs/2012.00317v3","paper_title":"Diverse Temporal Aggregation and Depthwise Spatiotemporal Factorization for Efficient Video Classification","code":"https://github.com/youngwanLEE/VoV3D","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":90,"model":"bLVNet","metrics":{"Top-1 Accuracy":"65.2"},"uses_additional_data":true,"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":91,"model":"DirecFormer","metrics":{"Top-1 Accuracy":"64.94","Top-5 Accuracy":"87.9"},"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":92,"model":"RSANet-R50 (8 frames, ImageNet pretrained, a single clip)","metrics":{"Top-1 Accuracy":"64.8","Top-5 Accuracy":"89.1"},"uses_additional_data":true,"paper_date":"2021-11-02","paper":"/paper/relational-self-attention-what-s-missing-in","paper_url":"https://arxiv.org/abs/2111.01673v1","paper_title":"Relational Self-Attention: What's Missing in Attention for Video Understanding","code":"https://github.com/KimManjin/RSA","n_code_links":1,"official":{"repos":["KimManjin/RSA"],"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":1,"sample_list":"/paper/relational-self-attention-what-s-missing-in#ran","syntology_url":"https://syntology.ai/paper/2111.01673","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.01673"}}}},{"rank_in_archive_order":93,"model":"MSNet-R50 (16 frames, ImageNet pretrained)","metrics":{"Top-1 Accuracy":"64.7","Top-5 Accuracy":"89.4"},"uses_additional_data":true,"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":94,"model":"AK-Net","metrics":{"Top-1 Accuracy":"64.3"},"uses_additional_data":false,"paper_date":"2022-01-17","paper":"/paper/action-keypoint-network-for-efficient-video","paper_url":"https://arxiv.org/abs/2201.06304v1","paper_title":"Action Keypoint Network for Efficient Video Recognition","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":95,"model":"VoV3D-M (32frames, from scratch, single)","metrics":{"GFLOPs":"11.5x6","Parameters":"3.3M","Top-1 Accuracy":"64.2","Top-5 Accuracy":"88.8"},"uses_additional_data":false,"paper_date":"2020-12-01","paper":"/paper/diverse-temporal-aggregation-and-depthwise","paper_url":"https://arxiv.org/abs/2012.00317v3","paper_title":"Diverse Temporal Aggregation and Depthwise Spatiotemporal Factorization for Efficient Video Classification","code":"https://github.com/youngwanLEE/VoV3D","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":96,"model":"VoV3D-L (16frames, from scratch, single)","metrics":{"GFLOPs":"9.3x6","Parameters":"5.8M","Top-1 Accuracy":"64.1","Top-5 Accuracy":"88.6"},"uses_additional_data":false,"paper_date":"2020-12-01","paper":"/paper/diverse-temporal-aggregation-and-depthwise","paper_url":"https://arxiv.org/abs/2012.00317v3","paper_title":"Diverse Temporal Aggregation and Depthwise Spatiotemporal Factorization for Efficient Video Classification","code":"https://github.com/youngwanLEE/VoV3D","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":97,"model":"TAda2D (ResNet-50, 8 frames)","metrics":{"Top-1 Accuracy":"64.0","Top-5 Accuracy":"88.0"},"uses_additional_data":true,"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":98,"model":"MoViNet-A2","metrics":{"GFLOPs":"10.3x1","Parameters":"4.8M","Top-1 Accuracy":"63.5","Top-5 Accuracy":"89.0"},"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":99,"model":"VoV3D-M (16frames, from scratch, single)","metrics":{"GFLOPs":"5.7x6","Parameters":"3.3M","Top-1 Accuracy":"63.2","Top-5 Accuracy":"88.2"},"uses_additional_data":false,"paper_date":"2020-12-01","paper":"/paper/diverse-temporal-aggregation-and-depthwise","paper_url":"https://arxiv.org/abs/2012.00317v3","paper_title":"Diverse Temporal Aggregation and Depthwise Spatiotemporal Factorization for Efficient Video Classification","code":"https://github.com/youngwanLEE/VoV3D","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":100,"model":"MSNet-R50 (8 frames, ImageNet pretrained)","metrics":{"Top-1 Accuracy":"63","Top-5 Accuracy":"88.4"},"uses_additional_data":true,"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":101,"model":"MoViNet-A1","metrics":{"GFLOPs":"6.0x1","Parameters":"4.6M","Top-1 Accuracy":"62.7","Top-5 Accuracy":"89.0"},"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":102,"model":"OmniVL","metrics":{"Top-1 Accuracy":"62.5","Top-5 Accuracy":"86.2"},"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":103,"model":"TimeSformer-HR","metrics":{"Top-1 Accuracy":"62.5"},"uses_additional_data":true,"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":104,"model":"TimeSformer-L","metrics":{"Top-1 Accuracy":"62.3"},"uses_additional_data":true,"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":105,"model":"TRG (ResNet-50)","metrics":{"Top-1 Accuracy":"62.2","Top-5 Accuracy":"90.3"},"uses_additional_data":false,"paper_date":"2019-08-27","paper":"/paper/temporal-reasoning-graph-for-activity","paper_url":"https://arxiv.org/abs/1908.09995v1","paper_title":"Temporal Reasoning Graph for Activity Recognition","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":106,"model":"TPN (TSM-50)","metrics":{"Top-1 Accuracy":"62.0"},"uses_additional_data":false,"paper_date":"2020-04-07","paper":"/paper/temporal-pyramid-network-for-action","paper_url":"https://arxiv.org/abs/2004.03548v2","paper_title":"Temporal Pyramid Network for Action Recognition","code":"https://github.com/open-mmlab/mmaction2","n_code_links":3,"official":{"repos":["decisionforce/TPN"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0,"sample_list":"/paper/temporal-pyramid-network-for-action#ran","syntology_url":"https://syntology.ai/paper/2004.03548","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.03548"}}}},{"rank_in_archive_order":107,"model":"Multigrid","metrics":{"Top-1 Accuracy":"61.7"},"uses_additional_data":true,"paper_date":"2019-12-02","paper":"/paper/a-multigrid-method-for-efficiently-training","paper_url":"https://arxiv.org/abs/1912.00998v2","paper_title":"A Multigrid Method for Efficiently Training Video Models","code":"https://github.com/facebookresearch/SlowFast","n_code_links":3,"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":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":4,"n_samples":10,"n_pointer_only_licence":3,"sample_list":"/paper/a-multigrid-method-for-efficiently-training#ran","syntology_url":"https://syntology.ai/paper/1912.00998","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.00998"}}}},{"rank_in_archive_order":108,"model":"SlowFast","metrics":{"Top-1 Accuracy":"61.7"},"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":109,"model":"TRG (Inception-V3)","metrics":{"Top-1 Accuracy":"61.3","Top-5 Accuracy":"91.4"},"uses_additional_data":false,"paper_date":"2019-08-27","paper":"/paper/temporal-reasoning-graph-for-activity","paper_url":"https://arxiv.org/abs/1908.09995v1","paper_title":"Temporal Reasoning Graph for Activity Recognition","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":110,"model":"MoViNet-A0","metrics":{"GFLOPs":"2.7x1","Parameters":"3.1M","Top-1 Accuracy":"61.3","Top-5 Accuracy":"88.2"},"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":111,"model":"CCS + two-stream + TRN","metrics":{"Top-1 Accuracy":"61.2","Top-5 Accuracy":"89.3"},"uses_additional_data":false,"paper_date":"2019-08-27","paper":"/paper/cooperative-cross-stream-network-for","paper_url":"https://arxiv.org/abs/1908.10136v1","paper_title":"Cooperative Cross-Stream Network for Discriminative Action Representation","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":112,"model":"VidTr-L","metrics":{"Top-1 Accuracy":"60.2"},"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":113,"model":"TimeSformer","metrics":{"Top-1 Accuracy":"59.5"},"uses_additional_data":true,"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":114,"model":"SVT","metrics":{"Top-1 Accuracy":"59.2"},"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":115,"model":"TAM (5-shot)","metrics":{"Top-1 Accuracy":"52.3"},"uses_additional_data":false,"paper_date":"2019-06-27","paper":"/paper/few-shot-video-classification-via-temporal","paper_url":"https://arxiv.org/abs/1906.11415v1","paper_title":"Few-Shot Video Classification via Temporal Alignment","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":116,"model":"model3D_1 with left-right augmentation and fps jitter","metrics":{"Top-1 Accuracy":"51.33","Top-5 Accuracy":"80.46"},"uses_additional_data":false,"paper_date":"2017-06-13","paper":"/paper/the-something-something-video-database-for","paper_url":"http://arxiv.org/abs/1706.04261v2","paper_title":"The \"something something\" video database for learning and evaluating visual common sense","code":"https://github.com/jayleicn/singularity","n_code_links":5,"official":null,"syntology":null},{"rank_in_archive_order":117,"model":"Prob-Distill","metrics":{"Top-1 Accuracy":"49.9","Top-5 Accuracy":"79.1"},"uses_additional_data":false,"paper_date":"2019-04-05","paper":"/paper/paying-more-attention-to-motion-attention","paper_url":"https://arxiv.org/abs/1904.03249v2","paper_title":"Attention Distillation for Learning Video Representations","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":118,"model":"STM + TRNMultiscale","metrics":{"Top-1 Accuracy":"47.73"},"uses_additional_data":false,"paper_date":"2019-09-11","paper":"/paper/comparative-analysis-of-cnn-based","paper_url":"https://arxiv.org/abs/1909.05165v2","paper_title":"Comparative Analysis of CNN-based Spatiotemporal Reasoning in Videos","code":"https://github.com/fubel/stmodeling","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":119,"model":"InternVideo2-6B","metrics":{"GFLOPs":"13321","Parameters":"2131","Top-1 Accuracy":"1","Top-5 Accuracy":"12"},"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":120,"model":"MViTv2-B (IN-21K + Kinetics400 pretrain)","metrics":{"Parameters":"51.1","Top-5 Accuracy":"93.4"},"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},{"rank_in_archive_order":121,"model":"RSANet-R50 (8+16 frames, ImageNet pretrained, 2 clips)","metrics":{"Top-5 Accuracy":"91.1"},"uses_additional_data":false,"paper_date":"2021-11-02","paper":"/paper/relational-self-attention-what-s-missing-in","paper_url":"https://arxiv.org/abs/2111.01673v1","paper_title":"Relational Self-Attention: What's Missing in Attention for Video Understanding","code":"https://github.com/KimManjin/RSA","n_code_links":1,"official":{"repos":["KimManjin/RSA"],"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":1,"sample_list":"/paper/relational-self-attention-what-s-missing-in#ran","syntology_url":"https://syntology.ai/paper/2111.01673","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.01673"}}}},{"rank_in_archive_order":122,"model":"MoViNet-A3","metrics":{"GFLOPs":"23.7x1","Parameters":"5.3M"},"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":123,"model":"MViT-L (IN-21K + Kinetics400 pretrain)","metrics":{"GFLOPs":"2828x3"},"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}],"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), 1 had this board among the leaderboards the extractor considered for their tables (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), and none proposed a result, so none await a verdict and none were placed.","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":123,"metric_columns":4,"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":1,"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":63,"rows_with_any_sample_ran":58,"rows_with_a_run_with_no_instrument_failure":51,"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":56,"rows_whose_official_repository_has_a_sample_that_ran":37,"rows_whose_official_repository_has_a_run_with_no_instrument_failure":30,"rows_community_repositories_only":9,"rows_runs_from_other_or_unrecorded_repositories":4,"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":37,"distinct_papers_with_any_sample_ran":35,"distinct_papers_with_a_run_with_no_instrument_failure":31,"samples_over_distinct_papers":{"n_ran":218,"n_constructed":66,"n_ran_checked":159,"n_instrument":59,"n_unverified":96,"n_samples":314,"n_pointer_only_licence":100,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":397,"n_constructed":161,"n_ran_checked":286,"n_instrument":111,"n_unverified":172,"n_samples":569,"n_pointer_only_licence":193,"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":"e9c14b70b0c5afdcc6c43a7421d371989945e5307488c57128dd42f395ab1d55","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}