{"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); 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,"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,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":0}},{"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,"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,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":0}},{"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,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0}},{"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,"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,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":0}},{"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,"syntology":{"n_ran":3,"n_unverified":5,"n_samples":8,"n_pointer_only_licence":0}},{"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,"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,"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,"syntology":{"n_ran":2,"n_unverified":4,"n_samples":6,"n_pointer_only_licence":0}},{"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,"syntology":{"n_ran":9,"n_unverified":10,"n_samples":19,"n_pointer_only_licence":0}},{"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,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":0}},{"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,"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,"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,"syntology":{"n_ran":9,"n_unverified":8,"n_samples":17,"n_pointer_only_licence":0}},{"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,"syntology":{"n_ran":2,"n_unverified":4,"n_samples":6,"n_pointer_only_licence":0}},{"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,"syntology":{"n_ran":0,"n_unverified":6,"n_samples":6,"n_pointer_only_licence":0}},{"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,"syntology":{"n_ran":9,"n_unverified":8,"n_samples":17,"n_pointer_only_licence":0}},{"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,"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,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3}},{"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,"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,"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,"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,"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,"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,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0}},{"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,"syntology":{"n_ran":7,"n_unverified":25,"n_samples":32,"n_pointer_only_licence":0}},{"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,"syntology":{"n_ran":14,"n_unverified":7,"n_samples":21,"n_pointer_only_licence":1}},{"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,"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,"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,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"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,"syntology":{"n_ran":8,"n_unverified":5,"n_samples":13,"n_pointer_only_licence":0}},{"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,"syntology":{"n_ran":14,"n_unverified":7,"n_samples":21,"n_pointer_only_licence":1}},{"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,"syntology":{"n_ran":7,"n_unverified":25,"n_samples":32,"n_pointer_only_licence":0}},{"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,"syntology":{"n_ran":13,"n_unverified":13,"n_samples":26,"n_pointer_only_licence":5}},{"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,"syntology":{"n_ran":5,"n_unverified":3,"n_samples":8,"n_pointer_only_licence":8}},{"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,"syntology":{"n_ran":8,"n_unverified":5,"n_samples":13,"n_pointer_only_licence":0}},{"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,"syntology":{"n_ran":13,"n_unverified":13,"n_samples":26,"n_pointer_only_licence":5}},{"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,"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,"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,"syntology":{"n_ran":14,"n_unverified":7,"n_samples":21,"n_pointer_only_licence":1}},{"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,"syntology":{"n_ran":8,"n_unverified":5,"n_samples":13,"n_pointer_only_licence":0}},{"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,"syntology":{"n_ran":13,"n_unverified":13,"n_samples":26,"n_pointer_only_licence":5}},{"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,"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,"syntology":{"n_ran":0,"n_unverified":10,"n_samples":10,"n_pointer_only_licence":0}},{"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,"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,"syntology":{"n_ran":8,"n_unverified":5,"n_samples":13,"n_pointer_only_licence":0}},{"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,"syntology":{"n_ran":0,"n_unverified":10,"n_samples":10,"n_pointer_only_licence":0}},{"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,"syntology":{"n_ran":8,"n_unverified":5,"n_samples":13,"n_pointer_only_licence":0}},{"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,"syntology":{"n_ran":0,"n_unverified":10,"n_samples":10,"n_pointer_only_licence":0}},{"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,"syntology":{"n_ran":0,"n_unverified":10,"n_samples":10,"n_pointer_only_licence":0}},{"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,"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,"syntology":{"n_ran":0,"n_unverified":10,"n_samples":10,"n_pointer_only_licence":0}},{"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,"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,"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,"syntology":{"n_ran":8,"n_unverified":5,"n_samples":13,"n_pointer_only_licence":0}},{"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,"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,"syntology":{"n_ran":8,"n_unverified":5,"n_samples":13,"n_pointer_only_licence":0}},{"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,"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,"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,"syntology":{"n_ran":8,"n_unverified":5,"n_samples":13,"n_pointer_only_licence":0}},{"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,"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,"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,"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,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N 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).","rows_with_graph_line":37,"rows_with_any_sample_ran":31,"distinct_papers_with_graph_line":17,"distinct_papers_with_any_sample_ran":15,"samples_over_distinct_papers":{"n_ran":82,"n_unverified":100,"n_samples":182,"n_pointer_only_licence":17,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":212,"n_unverified":256,"n_samples":468,"n_pointer_only_licence":29,"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"}}}