{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/sota/action-classification-on-kinetics-600","task":{"name":"Action Classification","url":"/task/action-classification","note":null},"dataset":{"name":"Kinetics-600","url":"/dataset/kinetics-600"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"Image source: [The Kinetics Human Action Video Dataset](https://arxiv.org/pdf/1705.06950.pdf)","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Top-1 Accuracy","Top-5 Accuracy","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","GFLOPs":null}},"counts":{"rows":65,"rows_with_code":55,"rows_with_paper_page":65,"rows_dated":65,"rows_using_additional_data":29},"rows":[{"rank_in_archive_order":1,"model":"InternVideo2-6B","metrics":{"Top-1 Accuracy":"91.9"},"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":2,"model":"TubeVit-H","metrics":{"Top-1 Accuracy":"91.8","Top-5 Accuracy":"98.9"},"uses_additional_data":true,"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":3,"model":"InternVideo2-1B","metrics":{"Top-1 Accuracy":"91.6"},"uses_additional_data":true,"paper_date":"2024-03-22","paper":"/paper/internvideo2-scaling-video-foundation-models","paper_url":"https://arxiv.org/abs/2403.15377v4","paper_title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","code":"https://github.com/opengvlab/internvideo","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":4,"model":"TubeVit-L","metrics":{"Top-1 Accuracy":"91.5","Top-5 Accuracy":"98.7"},"uses_additional_data":true,"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":5,"model":"InternVideo-T","metrics":{"Top-1 Accuracy":"91.3"},"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":6,"model":"🍷MerlotReserve-Large (+Audio)","metrics":{"Top-1 Accuracy":"91.1","Top-5 Accuracy":"97.1"},"uses_additional_data":true,"paper_date":"2022-01-07","paper":"/paper/merlot-reserve-neural-script-knowledge","paper_url":"https://arxiv.org/abs/2201.02639v4","paper_title":"MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":7,"model":"TubeVit-B","metrics":{"Top-1 Accuracy":"90.9","Top-5 Accuracy":"97.3"},"uses_additional_data":true,"paper_date":"2022-12-06","paper":"/paper/rethinking-video-vits-sparse-video-tubes-for","paper_url":"https://arxiv.org/abs/2212.03229v1","paper_title":"Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning","code":"https://github.com/daniel-code/TubeViT","n_code_links":1,"official":null,"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":1,"sample_list":"/paper/rethinking-video-vits-sparse-video-tubes-for#ran","syntology_url":"https://syntology.ai/paper/2212.03229","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.03229"}}}},{"rank_in_archive_order":8,"model":"UMT-L (ViT-L/16)","metrics":{"Top-1 Accuracy":"90.5","Top-5 Accuracy":"98.8"},"uses_additional_data":true,"paper_date":"2023-03-28","paper":"/paper/unmasked-teacher-towards-training-efficient","paper_url":"https://arxiv.org/abs/2303.16058v2","paper_title":"Unmasked Teacher: Towards Training-Efficient Video Foundation Models","code":"https://github.com/opengvlab/unmasked_teacher","n_code_links":1,"official":{"repos":["opengvlab/unmasked_teacher"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":0,"n_samples":8,"n_pointer_only_licence":3,"sample_list":"/paper/unmasked-teacher-towards-training-efficient#ran","syntology_url":"https://syntology.ai/paper/2303.16058","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.16058"}}}},{"rank_in_archive_order":9,"model":"MTV-H (WTS 60M)","metrics":{"Top-1 Accuracy":"90.3","Top-5 Accuracy":"98.5"},"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":10,"model":"UniFormerV2-L","metrics":{"Top-1 Accuracy":"90.1","Top-5 Accuracy":"98.5"},"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":11,"model":"VideoMAE V2-g (64x266x266)","metrics":{"Top-1 Accuracy":"89.9","Top-5 Accuracy":"98.5"},"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":12,"model":"mPLUG-2","metrics":{"Top-1 Accuracy":"89.8","Top-5 Accuracy":"98.3"},"uses_additional_data":true,"paper_date":"2023-02-01","paper":"/paper/mplug-2-a-modularized-multi-modal-foundation","paper_url":"https://arxiv.org/abs/2302.00402v1","paper_title":"mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video","code":"https://github.com/modelscope/modelscope","n_code_links":4,"official":{"repos":["alibaba/AliceMind"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":17,"n_constructed":0,"n_ran_checked":8,"n_instrument":9,"n_unverified":2,"n_samples":19,"n_pointer_only_licence":2,"sample_list":"/paper/mplug-2-a-modularized-multi-modal-foundation#ran","syntology_url":"https://syntology.ai/paper/2302.00402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.00402"}}}},{"rank_in_archive_order":13,"model":"EVA","metrics":{"Top-1 Accuracy":"89.8%"},"uses_additional_data":true,"paper_date":"2022-11-14","paper":"/paper/eva-exploring-the-limits-of-masked-visual","paper_url":"https://arxiv.org/abs/2211.07636v2","paper_title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":6,"official":{"repos":["baaivision/eva","rwightman/pytorch-image-models"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":0,"sample_list":"/paper/eva-exploring-the-limits-of-masked-visual#ran","syntology_url":"https://syntology.ai/paper/2211.07636","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.07636"}}}},{"rank_in_archive_order":14,"model":"🍷MerlotReserve-Base (+Audio)","metrics":{"Top-1 Accuracy":"89.7","Top-5 Accuracy":"96.6"},"uses_additional_data":true,"paper_date":"2022-01-07","paper":"/paper/merlot-reserve-neural-script-knowledge","paper_url":"https://arxiv.org/abs/2201.02639v4","paper_title":"MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":15,"model":"🍷MerlotReserve-Large (no Audio)","metrics":{"Top-1 Accuracy":"89.4","Top-5 Accuracy":"96.3"},"uses_additional_data":true,"paper_date":"2022-01-07","paper":"/paper/merlot-reserve-neural-script-knowledge","paper_url":"https://arxiv.org/abs/2201.02639v4","paper_title":"MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":16,"model":"CoCa (finetuned)","metrics":{"Top-1 Accuracy":"89.4"},"uses_additional_data":true,"paper_date":"2022-05-04","paper":"/paper/coca-contrastive-captioners-are-image-text","paper_url":"https://arxiv.org/abs/2205.01917v2","paper_title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","code":"https://github.com/mlfoundations/open_clip","n_code_links":6,"official":null,"syntology":{"n_ran":10,"n_constructed":5,"n_ran_checked":9,"n_instrument":1,"n_unverified":7,"n_samples":17,"n_pointer_only_licence":2,"sample_list":"/paper/coca-contrastive-captioners-are-image-text#ran","syntology_url":"https://syntology.ai/paper/2205.01917","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.01917"}}}},{"rank_in_archive_order":17,"model":"VideoMAE V2-g","metrics":{"Top-1 Accuracy":"88.8","Top-5 Accuracy":"98.2"},"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":18,"model":"Hiera-H (no extra data)","metrics":{"Top-1 Accuracy":"88.8"},"uses_additional_data":false,"paper_date":"2023-06-01","paper":"/paper/hiera-a-hierarchical-vision-transformer","paper_url":"https://arxiv.org/abs/2306.00989v1","paper_title":"Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles","code":"https://github.com/huggingface/pytorch-image-models","n_code_links":4,"official":{"repos":["facebookresearch/hiera"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_samples":6,"n_pointer_only_licence":0,"sample_list":"/paper/hiera-a-hierarchical-vision-transformer#ran","syntology_url":"https://syntology.ai/paper/2306.00989","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.00989"}}}},{"rank_in_archive_order":19,"model":"CoCa (frozen)","metrics":{"Top-1 Accuracy":"88.5"},"uses_additional_data":true,"paper_date":"2022-05-04","paper":"/paper/coca-contrastive-captioners-are-image-text","paper_url":"https://arxiv.org/abs/2205.01917v2","paper_title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","code":"https://github.com/mlfoundations/open_clip","n_code_links":6,"official":null,"syntology":{"n_ran":10,"n_constructed":5,"n_ran_checked":9,"n_instrument":1,"n_unverified":7,"n_samples":17,"n_pointer_only_licence":2,"sample_list":"/paper/coca-contrastive-captioners-are-image-text#ran","syntology_url":"https://syntology.ai/paper/2205.01917","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.01917"}}}},{"rank_in_archive_order":20,"model":"MaskFeat (no extra data, MViT-L)","metrics":{"Top-1 Accuracy":"88.3","Top-5 Accuracy":"98.0"},"uses_additional_data":false,"paper_date":"2021-12-16","paper":"/paper/masked-feature-prediction-for-self-supervised","paper_url":"https://arxiv.org/abs/2112.09133v2","paper_title":"Masked Feature Prediction for Self-Supervised Visual Pre-Training","code":"https://github.com/facebookresearch/SlowFast","n_code_links":6,"official":null,"syntology":null},{"rank_in_archive_order":21,"model":"X-CLIP(ViT-L/14, CLIP)","metrics":{"Top-1 Accuracy":"88.3","Top-5 Accuracy":"97.7"},"uses_additional_data":true,"paper_date":"2022-08-04","paper":"/paper/expanding-language-image-pretrained-models","paper_url":"https://arxiv.org/abs/2208.02816v1","paper_title":"Expanding Language-Image Pretrained Models for General Video Recognition","code":"https://github.com/microsoft/videox","n_code_links":2,"official":{"repos":["microsoft/videox"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3,"sample_list":"/paper/expanding-language-image-pretrained-models#ran","syntology_url":"https://syntology.ai/paper/2208.02816","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.02816"}}}},{"rank_in_archive_order":22,"model":"🍷MerlotReserve-Base (no Audio)","metrics":{"Top-1 Accuracy":"88.1","Top-5 Accuracy":"95.8"},"uses_additional_data":true,"paper_date":"2022-01-07","paper":"/paper/merlot-reserve-neural-script-knowledge","paper_url":"https://arxiv.org/abs/2201.02639v4","paper_title":"MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":23,"model":"MViTv2-L (ImageNet-21k pretrain)","metrics":{"Top-1 Accuracy":"87.9","Top-5 Accuracy":"97.9"},"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":24,"model":"CoVeR (JFT-3B)","metrics":{"Top-1 Accuracy":"87.9","Top-5 Accuracy":"97.8"},"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":25,"model":"Florence (curated FLD-900M pretrain)","metrics":{"Top-1 Accuracy":"87.8","Top-5 Accuracy":"97.9"},"uses_additional_data":true,"paper_date":"2021-11-22","paper":"/paper/florence-a-new-foundation-model-for-computer","paper_url":"https://arxiv.org/abs/2111.11432v1","paper_title":"Florence: A New Foundation Model for Computer Vision","code":"https://github.com/microsoft/unicl","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":26,"model":"CoVeR (JFT-300M)","metrics":{"Top-1 Accuracy":"86.8","Top-5 Accuracy":"97.3"},"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":27,"model":"TokenLearner 16at18 w. Fuser (L/10)","metrics":{"Top-1 Accuracy":"86.3","Top-5 Accuracy":"97.0"},"uses_additional_data":true,"paper_date":"2021-06-21","paper":"/paper/tokenlearner-what-can-8-learned-tokens-do-for","paper_url":"https://arxiv.org/abs/2106.11297v4","paper_title":"TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?","code":"https://github.com/google-research/scenic","n_code_links":11,"official":{"repos":["google-research/scenic"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":3,"n_constructed":1,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0,"sample_list":"/paper/tokenlearner-what-can-8-learned-tokens-do-for#ran","syntology_url":"https://syntology.ai/paper/2106.11297","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.11297"}}}},{"rank_in_archive_order":28,"model":"Swin-L (384x384, ImageNet-21k pretrain)","metrics":{"Top-1 Accuracy":"86.1","Top-5 Accuracy":"97.3"},"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":29,"model":"ViViT-H/16x2 (JFT)","metrics":{"Top-1 Accuracy":"85.8","Top-5 Accuracy":"96.5"},"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":30,"model":"MViTv2-L (train from scratch)","metrics":{"Top-1 Accuracy":"85.5"},"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":31,"model":"UniFormer-B (ImageNet-1K)","metrics":{"GFLOPs":"259x4","Top-1 Accuracy":"84.8","Top-5 Accuracy":"96.7"},"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":"XViT (x16)","metrics":{"Top-1 Accuracy":"84.5","Top-5 Accuracy":"96.3"},"uses_additional_data":false,"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":33,"model":"MoViNet-A5 (AutoAugment)","metrics":{"GFLOPs":"281x1","Top-1 Accuracy":"84.3","Top-5 Accuracy":"96.4"},"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":34,"model":"ViViT-L/16x2","metrics":{"Top-1 Accuracy":"84.3","Top-5 Accuracy":"95.6"},"uses_additional_data":false,"paper_date":"2021-03-29","paper":"/paper/2103-15691","paper_url":"https://arxiv.org/abs/2103.15691v2","paper_title":"ViViT: A Video Vision Transformer","code":"https://github.com/google-research/scenic","n_code_links":10,"official":{"repos":["google-research/scenic"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"syntology":{"n_ran":14,"n_constructed":10,"n_ran_checked":13,"n_instrument":1,"n_unverified":7,"n_samples":21,"n_pointer_only_licence":1,"sample_list":"/paper/2103-15691#ran","syntology_url":"https://syntology.ai/paper/2103.15691","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.15691"}}}},{"rank_in_archive_order":35,"model":"Swin-B (ImageNet-21k pretrain)","metrics":{"Top-1 Accuracy":"84.0","Top-5 Accuracy":"96.5"},"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":36,"model":"MViT-B-24, 32x3","metrics":{"Top-1 Accuracy":"83.8","Top-5 Accuracy":"96.3"},"uses_additional_data":false,"paper_date":"2021-04-22","paper":"/paper/multiscale-vision-transformers","paper_url":"https://arxiv.org/abs/2104.11227v1","paper_title":"Multiscale Vision Transformers","code":"https://github.com/facebookresearch/SlowFast","n_code_links":8,"official":{"repos":["facebookresearch/SlowFast"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":13,"n_constructed":10,"n_ran_checked":11,"n_instrument":2,"n_unverified":13,"n_samples":26,"n_pointer_only_licence":5,"sample_list":"/paper/multiscale-vision-transformers#ran","syntology_url":"https://syntology.ai/paper/2104.11227","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.11227"}}}},{"rank_in_archive_order":37,"model":"VATT-Large","metrics":{"Top-1 Accuracy":"83.6","Top-5 Accuracy":"96.6"},"uses_additional_data":true,"paper_date":"2021-04-22","paper":"/paper/vatt-transformers-for-multimodal-self","paper_url":"https://arxiv.org/abs/2104.11178v3","paper_title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","code":"https://github.com/google-research/google-research/tree/master/vatt","n_code_links":5,"official":{"repos":["google-research/google-research"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":5,"n_constructed":4,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_samples":8,"n_pointer_only_licence":8,"sample_list":"/paper/vatt-transformers-for-multimodal-self#ran","syntology_url":"https://syntology.ai/paper/2104.11178","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.11178"}}}},{"rank_in_archive_order":38,"model":"MoViNet-A6","metrics":{"GFLOPs":"386x1","Top-1 Accuracy":"83.5","Top-5 Accuracy":"96.5"},"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":39,"model":"MViT-B, 32x3","metrics":{"Top-1 Accuracy":"83.4","Top-5 Accuracy":"96.3"},"uses_additional_data":false,"paper_date":"2021-04-22","paper":"/paper/multiscale-vision-transformers","paper_url":"https://arxiv.org/abs/2104.11227v1","paper_title":"Multiscale Vision Transformers","code":"https://github.com/facebookresearch/SlowFast","n_code_links":8,"official":{"repos":["facebookresearch/SlowFast"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":13,"n_constructed":10,"n_ran_checked":11,"n_instrument":2,"n_unverified":13,"n_samples":26,"n_pointer_only_licence":5,"sample_list":"/paper/multiscale-vision-transformers#ran","syntology_url":"https://syntology.ai/paper/2104.11227","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.11227"}}}},{"rank_in_archive_order":40,"model":"LGD-3D Two-stream","metrics":{"Top-1 Accuracy":"83.1","Top-5 Accuracy":"96.2"},"uses_additional_data":false,"paper_date":"2019-06-13","paper":"/paper/learning-spatio-temporal-representation-with-3","paper_url":"https://arxiv.org/abs/1906.05571v1","paper_title":"Learning Spatio-Temporal Representation with Local and Global Diffusion","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":41,"model":"R3D-RS-200","metrics":{"Top-1 Accuracy":"83.1"},"uses_additional_data":false,"paper_date":"2021-09-03","paper":"/paper/revisiting-3d-resnets-for-video-recognition","paper_url":"https://arxiv.org/abs/2109.01696v1","paper_title":"Revisiting 3D ResNets for Video Recognition","code":"https://github.com/tensorflow/models","n_code_links":5,"official":null,"syntology":null},{"rank_in_archive_order":42,"model":"ViViT-L/16x2 (320x320)","metrics":{"Top-1 Accuracy":"83.0","Top-5 Accuracy":"95.7"},"uses_additional_data":false,"paper_date":"2021-03-29","paper":"/paper/2103-15691","paper_url":"https://arxiv.org/abs/2103.15691v2","paper_title":"ViViT: A Video Vision Transformer","code":"https://github.com/google-research/scenic","n_code_links":10,"official":{"repos":["google-research/scenic"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"syntology":{"n_ran":14,"n_constructed":10,"n_ran_checked":13,"n_instrument":1,"n_unverified":7,"n_samples":21,"n_pointer_only_licence":1,"sample_list":"/paper/2103-15691#ran","syntology_url":"https://syntology.ai/paper/2103.15691","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.15691"}}}},{"rank_in_archive_order":43,"model":"MoViNet-A5","metrics":{"GFLOPs":"281x1","Top-1 Accuracy":"82.7","Top-5 Accuracy":"95.7"},"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":44,"model":"MViT-B, 16x4","metrics":{"Top-1 Accuracy":"82.1","Top-5 Accuracy":"95.7"},"uses_additional_data":false,"paper_date":"2021-04-22","paper":"/paper/multiscale-vision-transformers","paper_url":"https://arxiv.org/abs/2104.11227v1","paper_title":"Multiscale Vision Transformers","code":"https://github.com/facebookresearch/SlowFast","n_code_links":8,"official":{"repos":["facebookresearch/SlowFast"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":13,"n_constructed":10,"n_ran_checked":11,"n_instrument":2,"n_unverified":13,"n_samples":26,"n_pointer_only_licence":5,"sample_list":"/paper/multiscale-vision-transformers#ran","syntology_url":"https://syntology.ai/paper/2104.11227","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.11227"}}}},{"rank_in_archive_order":45,"model":"PERF-Net (distilled ResNet50-G)","metrics":{"Top-1 Accuracy":"82.0","Top-5 Accuracy":"95.7"},"uses_additional_data":false,"paper_date":"2020-09-28","paper":"/paper/perf-net-pose-empowered-rgb-flow-net","paper_url":"https://arxiv.org/abs/2009.13087v2","paper_title":"PERF-Net: Pose Empowered RGB-Flow Net","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":46,"model":"SlowFast 16x8 (ResNet-101 + NL)","metrics":{"Top-1 Accuracy":"81.8","Top-5 Accuracy":"95.1"},"uses_additional_data":false,"paper_date":"2018-12-10","paper":"/paper/slowfast-networks-for-video-recognition","paper_url":"https://arxiv.org/abs/1812.03982v3","paper_title":"SlowFast Networks for Video Recognition","code":"https://github.com/facebookresearch/SlowFast","n_code_links":15,"official":{"repos":["facebookresearch/SlowFast"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"n_samples":10,"n_pointer_only_licence":1,"sample_list":"/paper/slowfast-networks-for-video-recognition#ran","syntology_url":"https://syntology.ai/paper/1812.03982","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.03982"}}}},{"rank_in_archive_order":47,"model":"LGD-3D RGB","metrics":{"Top-1 Accuracy":"81.5","Top-5 Accuracy":"95.6"},"uses_additional_data":false,"paper_date":"2019-06-13","paper":"/paper/learning-spatio-temporal-representation-with-3","paper_url":"https://arxiv.org/abs/1906.05571v1","paper_title":"Learning Spatio-Temporal Representation with Local and Global Diffusion","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":48,"model":"MoViNet-A4","metrics":{"GFLOPs":"105x1","Top-1 Accuracy":"81.2","Top-5 Accuracy":"94.9"},"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":49,"model":"SlowFast 16x8 (ResNet-101)","metrics":{"Top-1 Accuracy":"81.1","Top-5 Accuracy":"95.1"},"uses_additional_data":false,"paper_date":"2018-12-10","paper":"/paper/slowfast-networks-for-video-recognition","paper_url":"https://arxiv.org/abs/1812.03982v3","paper_title":"SlowFast Networks for Video Recognition","code":"https://github.com/facebookresearch/SlowFast","n_code_links":15,"official":{"repos":["facebookresearch/SlowFast"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"n_samples":10,"n_pointer_only_licence":1,"sample_list":"/paper/slowfast-networks-for-video-recognition#ran","syntology_url":"https://syntology.ai/paper/1812.03982","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.03982"}}}},{"rank_in_archive_order":50,"model":"MoViNet-A3","metrics":{"GFLOPs":"56.9x1","Top-1 Accuracy":"80.8","Top-5 Accuracy":"80.8"},"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":51,"model":"SlowFast 8x8 (ResNet-101)","metrics":{"Top-1 Accuracy":"80.4","Top-5 Accuracy":"94.8"},"uses_additional_data":false,"paper_date":"2018-12-10","paper":"/paper/slowfast-networks-for-video-recognition","paper_url":"https://arxiv.org/abs/1812.03982v3","paper_title":"SlowFast Networks for Video Recognition","code":"https://github.com/facebookresearch/SlowFast","n_code_links":15,"official":{"repos":["facebookresearch/SlowFast"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"n_samples":10,"n_pointer_only_licence":1,"sample_list":"/paper/slowfast-networks-for-video-recognition#ran","syntology_url":"https://syntology.ai/paper/1812.03982","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.03982"}}}},{"rank_in_archive_order":52,"model":"SlowFast 8x8 (ResNet-50)","metrics":{"Top-1 Accuracy":"79.9","Top-5 Accuracy":"94.5"},"uses_additional_data":false,"paper_date":"2018-12-10","paper":"/paper/slowfast-networks-for-video-recognition","paper_url":"https://arxiv.org/abs/1812.03982v3","paper_title":"SlowFast Networks for Video Recognition","code":"https://github.com/facebookresearch/SlowFast","n_code_links":15,"official":{"repos":["facebookresearch/SlowFast"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"n_samples":10,"n_pointer_only_licence":1,"sample_list":"/paper/slowfast-networks-for-video-recognition#ran","syntology_url":"https://syntology.ai/paper/1812.03982","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.03982"}}}},{"rank_in_archive_order":53,"model":"D3D+S3D-G","metrics":{"Top-1 Accuracy":"79.1"},"uses_additional_data":false,"paper_date":"2018-12-19","paper":"/paper/d3d-distilled-3d-networks-for-video-action","paper_url":"http://arxiv.org/abs/1812.08249v2","paper_title":"D3D: Distilled 3D Networks for Video Action Recognition","code":"https://github.com/princeton-vl/d3dhelper","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":54,"model":"SlowFast 4x16 (ResNet-50)","metrics":{"Top-1 Accuracy":"78.8","Top-5 Accuracy":"94"},"uses_additional_data":false,"paper_date":"2018-12-10","paper":"/paper/slowfast-networks-for-video-recognition","paper_url":"https://arxiv.org/abs/1812.03982v3","paper_title":"SlowFast Networks for Video Recognition","code":"https://github.com/facebookresearch/SlowFast","n_code_links":15,"official":{"repos":["facebookresearch/SlowFast"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"n_samples":10,"n_pointer_only_licence":1,"sample_list":"/paper/slowfast-networks-for-video-recognition#ran","syntology_url":"https://syntology.ai/paper/1812.03982","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.03982"}}}},{"rank_in_archive_order":55,"model":"S3D-G (RGB+Flow)","metrics":{"Top-1 Accuracy":"78.6"},"uses_additional_data":false,"paper_date":"2017-12-13","paper":"/paper/rethinking-spatiotemporal-feature-learning","paper_url":"http://arxiv.org/abs/1712.04851v2","paper_title":"Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification","code":"https://github.com/kylemin/S3D","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":56,"model":"D3D","metrics":{"Top-1 Accuracy":"77.9"},"uses_additional_data":false,"paper_date":"2018-12-19","paper":"/paper/d3d-distilled-3d-networks-for-video-action","paper_url":"http://arxiv.org/abs/1812.08249v2","paper_title":"D3D: Distilled 3D Networks for Video Action Recognition","code":"https://github.com/princeton-vl/d3dhelper","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":57,"model":"MoViNet-A2","metrics":{"GFLOPs":"10.3x1","Top-1 Accuracy":"77.5","Top-5 Accuracy":"93.4"},"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":58,"model":"S3D-G (RGB)","metrics":{"Top-1 Accuracy":"76.6"},"uses_additional_data":false,"paper_date":"2017-12-13","paper":"/paper/rethinking-spatiotemporal-feature-learning","paper_url":"http://arxiv.org/abs/1712.04851v2","paper_title":"Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification","code":"https://github.com/kylemin/S3D","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":59,"model":"MoViNet-A1","metrics":{"GFLOPs":"6.0x1","Top-1 Accuracy":"76.0","Top-5 Accuracy":"92.6"},"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":60,"model":"LGD-3D Flow","metrics":{"Top-1 Accuracy":"75","Top-5 Accuracy":"92.4"},"uses_additional_data":false,"paper_date":"2019-06-13","paper":"/paper/learning-spatio-temporal-representation-with-3","paper_url":"https://arxiv.org/abs/1906.05571v1","paper_title":"Learning Spatio-Temporal Representation with Local and Global Diffusion","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":61,"model":"I3D (RGB)","metrics":{"Top-1 Accuracy":"73.6"},"uses_additional_data":false,"paper_date":"2018-08-03","paper":"/paper/a-short-note-about-kinetics-600","paper_url":"http://arxiv.org/abs/1808.01340v1","paper_title":"A Short Note about Kinetics-600","code":"https://github.com/rocksyne/kinetics-dataset-downloader","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":62,"model":"MoViNet-A0","metrics":{"GFLOPs":"2.7x1","Top-1 Accuracy":"71.5","Top-5 Accuracy":"90.4"},"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":63,"model":"S3D-G (Flow)","metrics":{"Top-1 Accuracy":"69.7"},"uses_additional_data":false,"paper_date":"2017-12-13","paper":"/paper/rethinking-spatiotemporal-feature-learning","paper_url":"http://arxiv.org/abs/1712.04851v2","paper_title":"Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification","code":"https://github.com/kylemin/S3D","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":64,"model":"MViTv2-B (train from scratch)","metrics":{"Top-5 Accuracy":"97.2"},"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":65,"model":"MViT-L (train from scratch)","metrics":{"GFLOPs":"206x5"},"uses_additional_data":false,"paper_date":"2021-12-02","paper":"/paper/improved-multiscale-vision-transformers-for","paper_url":"https://arxiv.org/abs/2112.01526v2","paper_title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":9,"official":null,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"adjudicator":"Claude Opus 5.5","adjudicator_from":"groundwork/59_code_with_papers/LB_EXTRACTOR_PREREG.md (not recorded in lb_measurement.json; the file's frozen_commit, measured_on and counts equal the run the pre-registration records)","adjudicator_sensitivity":[69,70],"adjudicator_specificity":[101,103],"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication by a model (adjudicator) of accepted entries on a held-out split of archive papers, rules frozen before the test; adjudicator_sensitivity and adjudicator_specificity are its own controls as [judged right, of]; it was not measured on the newer papers placed here","measurement_sentence":"Measured before publishing, on held-out archive papers: the extractor was given 883 of them and produced output for 881 (the other 2 had no title and were excluded before any model call, so they are not part of this measurement). A model adjudicator (Claude Opus 5.5), blind to which entries were real, judged 108 of 110 accepted entries correct on those held-out archive papers; its own controls: 69 of 70 archive-confirmed entries judged true, 101 of 103 corrupted copies judged false. It was not measured on the newer papers whose results are placed on this site.","coverage":{"sentence":"Syntology has checked 8,886 of the 18,637 papers on this site that are newer than the archive (for 3,717 of them no archive leaderboard matched the paper's tables, so there was nothing further to check); 733 were read and have nothing to place (arXiv has no HTML version of the paper, or that version has no tables), 41 could not be read (the extractor's reply could not be parsed), and results from the other 8,977 appear after they are checked.","complete":false,"papers_newer_than_archive":18637,"papers_checked":8886,"papers_checked_no_leaderboard_matched":3717,"papers_read_nothing_to_place":733,"papers_could_not_be_read":41,"papers_could_not_be_read_by_status":{"unparseable":41},"papers_extracted_not_yet_verified":0,"boards_without_verdict":3,"papers_not_yet_extracted":8975},"board_status":{"sentence":"Of the 8,888 newer papers whose tables Syntology has read (8,886 checked in full and 2 with a leaderboard still awaiting a verdict), 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 1 proposed a result, which gave no cell that passed the extractor's own checks; 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":65,"metric_columns":3,"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":1,"no_cell_passed_checks":1,"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; 1 newer paper judged to report on this board so far"},"judged_to_report":{"heading":"Newer papers whose tables Claude Sonnet 4.5 judged to report on this benchmark (a model's judgement, not a result; newest first by arXiv id)","judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"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":1,"shown_on_page":1,"no_cell_split":{"no_cell_passed_checks_in_ledger":1,"rows_refused_by_rule":1,"rows_no_cell_passed_checks":0},"rows":[{"arxiv_id":"2511.20928","outcome":"refused_by_rule","reason":"the row label the model quoted is not the row's label; the table's column header does not name the leaderboard's metric"}]},"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":37,"rows_with_any_sample_ran":37,"rows_with_a_run_with_no_instrument_failure":35,"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":32,"rows_whose_official_repository_has_a_sample_that_ran":11,"rows_whose_official_repository_has_a_run_with_no_instrument_failure":9,"rows_community_repositories_only":18,"rows_runs_from_other_or_unrecorded_repositories":3,"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":17,"distinct_papers_with_any_sample_ran":17,"distinct_papers_with_a_run_with_no_instrument_failure":15,"samples_over_distinct_papers":{"n_ran":125,"n_constructed":41,"n_ran_checked":100,"n_instrument":25,"n_unverified":57,"n_samples":182,"n_pointer_only_licence":33,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":315,"n_constructed":130,"n_ran_checked":269,"n_instrument":46,"n_unverified":153,"n_samples":468,"n_pointer_only_licence":60,"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":"b98eba21370fe01e7d5708d561d2881aa827e6e46f81180bb673a162991d1a53","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}