{"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":"/task/action-classification","name":"Action Classification","slug":"action-classification","description_markdown":"Image source: [The Kinetics Human Action Video Dataset](https://arxiv.org/pdf/1705.06950.pdf)","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":457,"papers_with_code":251,"benchmarks":28,"benchmark_tables_in_archive":28,"benchmark_tables_shown":28,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":33,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/action-classification-on-kinetics-400","slug":"action-classification-on-kinetics-400","dataset":"Kinetics-400","dataset_url":"/dataset/kinetics","rows_in_archive":207,"metrics":["Acc@1","Acc@5","FLOPs (G) x views","Clip acc@1","Parameters (M)","Clip acc@5"],"first_row_in_archive_order":{"model":"OmniVec2","paper_title":"OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning","paper_url":"/paper/omnivec2-a-novel-transformer-based-network","paper_date":"2024-01-01","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/action-classification-on-kinetics-600","slug":"action-classification-on-kinetics-600","dataset":"Kinetics-600","dataset_url":"/dataset/kinetics-600","rows_in_archive":65,"metrics":["Top-1 Accuracy","Top-5 Accuracy","GFLOPs"],"first_row_in_archive_order":{"model":"InternVideo2-6B","paper_title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","paper_url":"/paper/internvideo2-scaling-video-foundation-models","paper_date":"2024-03-22","arxiv_id":"2403.15377","code_links":[{"title":"opengvlab/internvideo","url":"https://github.com/opengvlab/internvideo"},{"title":"opengvlab/internvideo2","url":"https://github.com/opengvlab/internvideo2"}],"syntology":null}},{"leaderboard":"/sota/action-classification-on-charades","slug":"action-classification-on-charades","dataset":"Charades","dataset_url":"/dataset/charades","rows_in_archive":49,"metrics":["MAP","FLOPs (G) x views"],"first_row_in_archive_order":{"model":"TokenLearner","paper_title":"TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?","paper_url":"/paper/tokenlearner-what-can-8-learned-tokens-do-for","paper_date":"2021-06-21","arxiv_id":"2106.11297","code_links":[{"title":"google-research/scenic","url":"https://github.com/google-research/scenic"},{"title":"keras-team/keras-io","url":"https://github.com/keras-team/keras-io/blob/master/examples/vision/token_learner.py"},{"title":"rish-16/tokenlearner-pytorch","url":"https://github.com/rish-16/tokenlearner-pytorch"},{"title":"ariG23498/TokenLearner","url":"https://github.com/ariG23498/TokenLearner"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/7/token_learner"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/4/token_learner"},{"title":"MindSpore-scientific/code-11","url":"https://github.com/MindSpore-scientific/code-11/tree/main/token_learner"},{"title":"MindSpore-scientific/code-1","url":"https://github.com/MindSpore-scientific/code-1/tree/main/token_learner"},{"title":"MindSpore-scientific/code-8","url":"https://github.com/MindSpore-scientific/code-8/tree/main/token_learner"},{"title":"MindSpore-scientific/code-10","url":"https://github.com/MindSpore-scientific/code-10/tree/main/token_learner"},{"title":"MindSpore-scientific-2/code-8","url":"https://github.com/MindSpore-scientific-2/code-8/tree/main/token_learner"}],"syntology":{"n":3,"n_ran":3,"n_constructed":1,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","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"}},"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"]}}}},{"leaderboard":"/sota/action-classification-on-kinetics-700","slug":"action-classification-on-kinetics-700","dataset":"Kinetics-700","dataset_url":"/dataset/kinetics-700","rows_in_archive":36,"metrics":["Top-1 Accuracy","Top-5 Accuracy"],"first_row_in_archive_order":{"model":"InternVideo2-6B","paper_title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","paper_url":"/paper/internvideo2-scaling-video-foundation-models","paper_date":"2024-03-22","arxiv_id":"2403.15377","code_links":[{"title":"opengvlab/internvideo","url":"https://github.com/opengvlab/internvideo"},{"title":"opengvlab/internvideo2","url":"https://github.com/opengvlab/internvideo2"}],"syntology":null}},{"leaderboard":"/sota/action-classification-on-moments-in-time","slug":"action-classification-on-moments-in-time","dataset":"MiT","dataset_url":null,"rows_in_archive":29,"metrics":["Top 1 Accuracy","Top 5 Accuracy"],"first_row_in_archive_order":{"model":"OmniVec2","paper_title":"OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning","paper_url":"/paper/omnivec2-a-novel-transformer-based-network","paper_date":"2024-01-01","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/action-classification-on-toyota-smarthome","slug":"action-classification-on-toyota-smarthome","dataset":"Toyota Smarthome dataset","dataset_url":"/dataset/toyota-smarthome","rows_in_archive":13,"metrics":["CS","CV1","CV2","Accuracy"],"first_row_in_archive_order":{"model":"π-ViT","paper_title":"Just Add $π$! Pose Induced Video Transformers for Understanding Activities of Daily Living","paper_url":"/paper/just-add-p-pose-induced-video-transformers","paper_date":"2023-11-30","arxiv_id":"2311.18840","code_links":[{"title":"dominickrei/pi-vit","url":"https://github.com/dominickrei/pi-vit"}],"syntology":null}},{"leaderboard":"/sota/action-classification-on-avid","slug":"action-classification-on-avid","dataset":"AViD","dataset_url":"/dataset/avid","rows_in_archive":10,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"TokenLearner","paper_title":"TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?","paper_url":"/paper/tokenlearner-what-can-8-learned-tokens-do-for","paper_date":"2021-06-21","arxiv_id":"2106.11297","code_links":[{"title":"google-research/scenic","url":"https://github.com/google-research/scenic"},{"title":"keras-team/keras-io","url":"https://github.com/keras-team/keras-io/blob/master/examples/vision/token_learner.py"},{"title":"rish-16/tokenlearner-pytorch","url":"https://github.com/rish-16/tokenlearner-pytorch"},{"title":"ariG23498/TokenLearner","url":"https://github.com/ariG23498/TokenLearner"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/7/token_learner"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/4/token_learner"},{"title":"MindSpore-scientific/code-11","url":"https://github.com/MindSpore-scientific/code-11/tree/main/token_learner"},{"title":"MindSpore-scientific/code-1","url":"https://github.com/MindSpore-scientific/code-1/tree/main/token_learner"},{"title":"MindSpore-scientific/code-8","url":"https://github.com/MindSpore-scientific/code-8/tree/main/token_learner"},{"title":"MindSpore-scientific/code-10","url":"https://github.com/MindSpore-scientific/code-10/tree/main/token_learner"},{"title":"MindSpore-scientific-2/code-8","url":"https://github.com/MindSpore-scientific-2/code-8/tree/main/token_learner"}],"syntology":{"n":3,"n_ran":3,"n_constructed":1,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","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"}},"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"]}}}},{"leaderboard":"/sota/action-classification-on-kinetics-sounds","slug":"action-classification-on-kinetics-sounds","dataset":"Kinetics-Sounds","dataset_url":"/dataset/kinetics","rows_in_archive":4,"metrics":["Top 1 Accuracy","Top 5 Accuracy"],"first_row_in_archive_order":{"model":"CA2ST(B/16)","paper_title":"CA^2ST: Cross-Attention in Audio, Space, and Time for Holistic Video Recognition","paper_url":"/paper/ca-2st-cross-attention-in-audio-space-and","paper_date":"2025-03-30","arxiv_id":"2503.23447","code_links":[],"syntology":null}},{"leaderboard":"/sota/action-classification-on-moments-in-time-2","slug":"action-classification-on-moments-in-time-2","dataset":"Moments in Time","dataset_url":null,"rows_in_archive":4,"metrics":["Top 1 Accuracy"],"first_row_in_archive_order":{"model":"OmniVec2","paper_title":"OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning","paper_url":"/paper/omnivec2-a-novel-transformer-based-network","paper_date":"2024-01-01","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/action-classification-on-activitynet-12","slug":"action-classification-on-activitynet-12","dataset":"ActivityNet-1.2","dataset_url":"/dataset/activitynet","rows_in_archive":3,"metrics":["mAP"],"first_row_in_archive_order":{"model":"W-TALC","paper_title":"W-TALC: Weakly-supervised Temporal Activity Localization and Classification","paper_url":"/paper/w-talc-weakly-supervised-temporal-activity","paper_date":"2018-07-27","arxiv_id":"1807.10418","code_links":[{"title":"sujoyp/wtalc-pytorch","url":"https://github.com/sujoyp/wtalc-pytorch"}],"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/w-talc-weakly-supervised-temporal-activity#ran","syntology_url":"https://syntology.ai/paper/1807.10418","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.10418"}},"official":{"repos":["sujoyp/wtalc-pytorch"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/action-classification-on-kinetics-700-2020","slug":"action-classification-on-kinetics-700-2020","dataset":"Kinetics-700-2020","dataset_url":"/dataset/kinetics-700-2020","rows_in_archive":3,"metrics":["Top 1 Accuracy"],"first_row_in_archive_order":{"model":"ALIP-ViT B/32 LAION30M","paper_title":"ALIP: Adaptive Language-Image Pre-training with Synthetic Caption","paper_url":"/paper/alip-adaptive-language-image-pre-training","paper_date":"2023-08-16","arxiv_id":"2308.08428","code_links":[{"title":"deepglint/alip","url":"https://github.com/deepglint/alip"}],"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":10,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/alip-adaptive-language-image-pre-training#ran","syntology_url":"https://syntology.ai/paper/2308.08428","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.08428"}},"official":{"repos":["deepglint/alip"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/action-classification-on-thumos14","slug":"action-classification-on-thumos14","dataset":"THUMOS’14","dataset_url":"/dataset/thumos14-1","rows_in_archive":3,"metrics":["mAP"],"first_row_in_archive_order":{"model":"3C-Net","paper_title":"3C-Net: Category Count and Center Loss for Weakly-Supervised Action Localization","paper_url":"/paper/3c-net-category-count-and-center-loss-for","paper_date":"2019-08-22","arxiv_id":"1908.08216","code_links":[{"title":"naraysa/3c-net","url":"https://github.com/naraysa/3c-net"}],"syntology":null}},{"leaderboard":"/sota/action-classification-on-wigesture","slug":"action-classification-on-wigesture","dataset":"WiGesture","dataset_url":"/dataset/wigesture","rows_in_archive":3,"metrics":["Accuracy (% )"],"first_row_in_archive_order":{"model":"CSI-BERT2","paper_title":"Mining Limited Data Sufficiently: A BERT-inspired Approach for CSI Time Series Application in Wireless Communication and Sensing","paper_url":"/paper/mining-limited-data-sufficiently-a-bert","paper_date":"2024-12-09","arxiv_id":"2412.06861","code_links":[],"syntology":null}},{"leaderboard":"/sota/action-classification-on-mit","slug":"action-classification-on-mit","dataset":"MIT","dataset_url":null,"rows_in_archive":2,"metrics":["Top 1 Accuracy"],"first_row_in_archive_order":{"model":"InternVideo2-6B","paper_title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","paper_url":"/paper/internvideo2-scaling-video-foundation-models","paper_date":"2024-03-22","arxiv_id":"2403.15377","code_links":[{"title":"opengvlab/internvideo","url":"https://github.com/opengvlab/internvideo"},{"title":"opengvlab/internvideo2","url":"https://github.com/opengvlab/internvideo2"}],"syntology":null}},{"leaderboard":"/sota/action-classification-on-ttstroke-21","slug":"action-classification-on-ttstroke-21","dataset":"TTStroke-21 ME22","dataset_url":"/dataset/ttstroke-21","rows_in_archive":2,"metrics":["Acc"],"first_row_in_archive_order":{"model":"RGB and PRGB","paper_title":"Fine-Grained Action Detection with RGB and Pose Information using Two Stream Convolutional Networks","paper_url":"/paper/fine-grained-action-detection-with-rgb-and","paper_date":"2023-02-06","arxiv_id":"2302.02755","code_links":[{"title":"fidsinn/sporttaskme22","url":"https://github.com/fidsinn/sporttaskme22"}],"syntology":null}},{"leaderboard":"/sota/action-classification-on-activitynet","slug":"action-classification-on-activitynet","dataset":"ActivityNet","dataset_url":"/dataset/activitynet","rows_in_archive":1,"metrics":["Top 1 Accuracy","Top 5 Accuracy"],"first_row_in_archive_order":{"model":"UniFormerV2-L","paper_title":"UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer","paper_url":"/paper/uniformerv2-spatiotemporal-learning-by-arming","paper_date":"2022-09-22","arxiv_id":null,"code_links":[{"title":"OpenGVLab/UniFormerV2","url":"https://github.com/OpenGVLab/UniFormerV2"},{"title":"innat/UniFormerV2","url":"https://github.com/innat/UniFormerV2"}],"syntology":null}},{"leaderboard":"/sota/action-classification-on-babel","slug":"action-classification-on-babel","dataset":"BABEL","dataset_url":"/dataset/babel-1","rows_in_archive":1,"metrics":["CE Top-1","CE Top-1-norm","CE Top-5"],"first_row_in_archive_order":{"model":"2s-AGCN","paper_title":"BABEL: Bodies, Action and Behavior with English Labels","paper_url":"/paper/babel-bodies-action-and-behavior-with-english","paper_date":"2021-06-17","arxiv_id":"2106.09696","code_links":[{"title":"abhinanda-punnakkal/BABEL","url":"https://github.com/abhinanda-punnakkal/BABEL"}],"syntology":null}},{"leaderboard":"/sota/action-classification-on-celebv-hq","slug":"action-classification-on-celebv-hq","dataset":"CelebV-HQ","dataset_url":"/dataset/celebv-hq","rows_in_archive":1,"metrics":["AUC","Accuracy"],"first_row_in_archive_order":{"model":"MARLIN","paper_title":"MARLIN: Masked Autoencoder for facial video Representation LearnINg","paper_url":"/paper/marlin-masked-autoencoder-for-facial-video","paper_date":"2022-11-12","arxiv_id":"2211.06627","code_links":[{"title":"ControlNet/MARLIN","url":"https://github.com/ControlNet/MARLIN"}],"syntology":null}},{"leaderboard":"/sota/action-classification-on-diving-48","slug":"action-classification-on-diving-48","dataset":"Diving-48","dataset_url":null,"rows_in_archive":1,"metrics":["Acc@1"],"first_row_in_archive_order":{"model":"DualPath w/ ViT-B/16","paper_title":"Dual-path Adaptation from Image to Video Transformers","paper_url":"/paper/dual-path-adaptation-from-image-to-video","paper_date":"2023-03-17","arxiv_id":"2303.09857","code_links":[{"title":"park-jungin/dualpath","url":"https://github.com/park-jungin/dualpath"}],"syntology":null}},{"leaderboard":"/sota/action-classification-on-hmdb51","slug":"action-classification-on-hmdb51","dataset":"HMDB51","dataset_url":"/dataset/hmdb51","rows_in_archive":1,"metrics":["Acc@1"],"first_row_in_archive_order":{"model":"DualPath w/ ViT-B/16 MLPs.","paper_title":"Dual-path Adaptation from Image to Video Transformers","paper_url":"/paper/dual-path-adaptation-from-image-to-video","paper_date":"2023-03-17","arxiv_id":"2303.09857","code_links":[{"title":"park-jungin/dualpath","url":"https://github.com/park-jungin/dualpath"}],"syntology":null}},{"leaderboard":"/sota/action-classification-on-jester-test","slug":"action-classification-on-jester-test","dataset":"Jester test","dataset_url":"/dataset/jester-gesture-recognition","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"C2F","paper_title":"Towards Efficient Coarse-to-Fine Networks for Action and Gesture Recognition","paper_url":"/paper/towards-efficient-coarse-to-fine-networks-for","paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/action-classification-on-minikinetics","slug":"action-classification-on-minikinetics","dataset":"MiniKinetics","dataset_url":"/dataset/kinetics","rows_in_archive":1,"metrics":["Top-1 Accuracy"],"first_row_in_archive_order":{"model":"MARS+RGB+Flow (16 frames)","paper_title":"MARS: Motion-Augmented RGB Stream for Action Recognition","paper_url":"/paper/mars-motion-augmented-rgb-stream-for-action","paper_date":"2019-06-01","arxiv_id":null,"code_links":[{"title":"craston/MARS","url":"https://github.com/craston/MARS"}],"syntology":null}},{"leaderboard":"/sota/action-classification-on-something-something-2","slug":"action-classification-on-something-something-2","dataset":"Something-Something V2","dataset_url":"/dataset/something-something-v2","rows_in_archive":1,"metrics":["Acc@1","Acc@5"],"first_row_in_archive_order":{"model":"AdaMAE","paper_title":"AdaMAE: Adaptive Masking for Efficient Spatiotemporal Learning with Masked Autoencoders","paper_url":"/paper/adamae-adaptive-masking-for-efficient","paper_date":"2022-11-16","arxiv_id":"2211.09120","code_links":[{"title":"wgcban/adamae","url":"https://github.com/wgcban/adamae"},{"title":"Nithin-GK/UniteandConquer","url":"https://github.com/Nithin-GK/UniteandConquer"}],"syntology":{"n":25,"n_ran":18,"n_constructed":0,"n_ran_checked":13,"n_instrument":5,"n_unverified":7,"n_honours":1,"n_violates":0,"n_no_contract":12,"n_pointer_only":6,"phrase":"18 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 5 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/adamae-adaptive-masking-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2211.09120","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.09120"}},"official":{"repos":["wgcban/adamae"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["listed","official"]}}}},{"leaderboard":"/sota/action-classification-on-thumos-14","slug":"action-classification-on-thumos-14","dataset":"THUMOS'14","dataset_url":"/dataset/thumos14-1","rows_in_archive":1,"metrics":["mAP"],"first_row_in_archive_order":{"model":"3C-Net","paper_title":"3C-Net: Category Count and Center Loss for Weakly-Supervised Action Localization","paper_url":"/paper/3c-net-category-count-and-center-loss-for","paper_date":"2019-08-22","arxiv_id":"1908.08216","code_links":[{"title":"naraysa/3c-net","url":"https://github.com/naraysa/3c-net"}],"syntology":null}},{"leaderboard":"/sota/action-classification-on-ttstroke-21-me21","slug":"action-classification-on-ttstroke-21-me21","dataset":"TTStroke-21 ME21","dataset_url":"/dataset/ttstroke-21-me21","rows_in_archive":1,"metrics":["Acc"],"first_row_in_archive_order":{"model":"STCNN","paper_title":"Spatio-Temporal CNN baseline method for the Sports Video Task of MediaEval 2021 benchmark","paper_url":"/paper/spatio-temporal-cnn-baseline-method-for-the","paper_date":"2021-12-16","arxiv_id":"2112.12074","code_links":[{"title":"ccp-eva/sporttaskme21","url":"https://github.com/ccp-eva/sporttaskme21"}],"syntology":null}},{"leaderboard":"/sota/action-classification-on-ucf101","slug":"action-classification-on-ucf101","dataset":"UCF101","dataset_url":"/dataset/ucf101","rows_in_archive":1,"metrics":["Top-1"],"first_row_in_archive_order":{"model":"Ours","paper_title":"SPAct: Self-supervised Privacy Preservation for Action Recognition","paper_url":"/paper/spact-self-supervised-privacy-preservation","paper_date":"2022-03-29","arxiv_id":"2203.15205","code_links":[{"title":"daveishan/spact","url":"https://github.com/daveishan/spact"}],"syntology":{"n":2,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/spact-self-supervised-privacy-preservation#ran","syntology_url":"https://syntology.ai/paper/2203.15205","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15205"}},"official":{"repos":["daveishan/spact"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/action-classification-on-wifall","slug":"action-classification-on-wifall","dataset":"WiFall","dataset_url":"/dataset/wifall","rows_in_archive":1,"metrics":["Accuracy (% )"],"first_row_in_archive_order":{"model":"CSI-BERT2","paper_title":"Mining Limited Data Sufficiently: A BERT-inspired Approach for CSI Time Series Application in Wireless Communication and Sensing","paper_url":"/paper/mining-limited-data-sufficiently-a-bert","paper_date":"2024-12-09","arxiv_id":"2412.06861","code_links":[],"syntology":null}},{"leaderboard":"/sota/action-classification-on-youcook2","slug":"action-classification-on-youcook2","dataset":"YouCook2","dataset_url":"/dataset/youcook2","rows_in_archive":1,"metrics":["Object Top 5 Accuracy","Object Top-1 Accuracy","Verb Top-1 Accuracy","Verb Top-5 Accuracy"],"first_row_in_archive_order":{"model":"VideoBERT (cross modal)","paper_title":"VideoBERT: A Joint Model for Video and Language Representation Learning","paper_url":"/paper/videobert-a-joint-model-for-video-and","paper_date":"2019-04-03","arxiv_id":"1904.01766","code_links":[{"title":"ammesatyajit/VideoBERT","url":"https://github.com/ammesatyajit/VideoBERT"},{"title":"MDSKUL/MasterProject","url":"https://github.com/MDSKUL/MasterProject"},{"title":"parkervg/allrecipes-bert","url":"https://github.com/parkervg/allrecipes-bert"}],"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/videobert-a-joint-model-for-video-and#ran","syntology_url":"https://syntology.ai/paper/1904.01766","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.01766"}},"official":null}}}],"datasets":[{"url":"/dataset/ucf101","name":"UCF101","full_name":"UCF101 Human Actions dataset","num_papers_in_archive":1863},{"url":"/dataset/kinetics","name":"Kinetics","full_name":"Kinetics Human Action Video Dataset","num_papers_in_archive":1341},{"url":"/dataset/hmdb51","name":"HMDB51","full_name":"","num_papers_in_archive":839},{"url":"/dataset/activitynet","name":"ActivityNet","full_name":"","num_papers_in_archive":807},{"url":"/dataset/kinetics-400-1","name":"Kinetics 400","full_name":"","num_papers_in_archive":712},{"url":"/dataset/charades","name":"Charades","full_name":"","num_papers_in_archive":428},{"url":"/dataset/thumos14-1","name":"THUMOS14","full_name":"","num_papers_in_archive":318},{"url":"/dataset/something-something-v2","name":"Something-Something V2","full_name":"","num_papers_in_archive":290},{"url":"/dataset/youcook2","name":"YouCook2","full_name":"","num_papers_in_archive":198},{"url":"/dataset/kinetics-600","name":"Kinetics-600","full_name":"","num_papers_in_archive":148},{"url":"/dataset/kinetics-700","name":"Kinetics-700","full_name":"Kinetics-700","num_papers_in_archive":95},{"url":"/dataset/babel-1","name":"BABEL","full_name":"","num_papers_in_archive":72},{"url":"/dataset/wlasl","name":"WLASL","full_name":"Word-Level American Sign Language","num_papers_in_archive":66},{"url":"/dataset/soccernet-v2","name":"SoccerNet-v2","full_name":"","num_papers_in_archive":58},{"url":"/dataset/soccernet","name":"SoccerNet","full_name":"","num_papers_in_archive":53},{"url":"/dataset/celebv-hq","name":"CelebV-HQ","full_name":"","num_papers_in_archive":36},{"url":"/dataset/toyota-smarthome","name":"Toyota Smarthome Dataset","full_name":"","num_papers_in_archive":31},{"url":"/dataset/toyota-smarthome-dataset","name":"Toyota Smarthome dataset","full_name":"Toyota Smarthome Trimmed","num_papers_in_archive":23},{"url":"/dataset/jester-gesture-recognition","name":"Jester (Gesture Recognition)","full_name":"","num_papers_in_archive":16},{"url":"/dataset/rwf-2000","name":"RWF-2000","full_name":"","num_papers_in_archive":16},{"url":"/dataset/haa500","name":"HAA500","full_name":"Human-Centric Atomic Action Dataset","num_papers_in_archive":14},{"url":"/dataset/mimetics","name":"Mimetics","full_name":"","num_papers_in_archive":11},{"url":"/dataset/avid","name":"AViD","full_name":"","num_papers_in_archive":9},{"url":"/dataset/kinetics-700-2020","name":"Kinetics-700-2020","full_name":"","num_papers_in_archive":9},{"url":"/dataset/sims4action","name":"Sims4Action","full_name":"","num_papers_in_archive":5},{"url":"/dataset/soccerdb","name":"SoccerDB","full_name":"","num_papers_in_archive":5},{"url":"/dataset/wigesture","name":"WiGesture","full_name":"Wireless Sensing Dataset for Gesture Recognition and People ID Identification with ESP32","num_papers_in_archive":5},{"url":"/dataset/ttstroke-21-me21","name":"TTStroke-21 ME21","full_name":"TTStroke-21 for MediaEval 2021","num_papers_in_archive":3},{"url":"/dataset/ttstroke-21","name":"TTStroke-21 ME22","full_name":"TTStroke-21 for MediaEval 2022","num_papers_in_archive":3},{"url":"/dataset/wifall","name":"WiFall","full_name":"Wireless Sensing Dataset for Fall Detection, Action Recognition and People ID Identification with ESP32-S3","num_papers_in_archive":2},{"url":"/dataset/mlb","name":"MLB","full_name":"Mouse Lockbox Dataset","num_papers_in_archive":1},{"url":"/dataset/win-fail-action-understanding","name":"Win-Fail Action Understanding","full_name":"Win-Fail Action Understanding","num_papers_in_archive":1},{"url":"/dataset/infiniterep","name":"InfiniteRep","full_name":"InfiniteRep","num_papers_in_archive":0}],"subtasks":[],"parent_tasks":[{"url":"/task/video","name":"Video"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":5,"rows_per_page":100,"shown":100,"of":457,"of_with_code":251,"tagged_in_all":457,"counts":{"archive_papers_tagged":457,"with_a_code_link":251,"where_syntology_ran_a_sample":83,"not_listed_spam_title":0,"listed":457,"listed_where_code_ran":83,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":75,"every_run_a_failure_of_syntologys_instrument":8,"listed_with_a_run_with_no_instrument_failure":75,"listed_every_run_a_failure_of_syntologys_instrument":8,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/high-quality-monocular-depth-estimation-via","slug":"high-quality-monocular-depth-estimation-via","title":"High Quality Monocular Depth Estimation via Transfer Learning","date":"2018-12-31","arxiv_id":"1812.11941","repositories_listed":45,"syntology":{"n":23,"n_ran":19,"n_constructed":0,"n_ran_checked":16,"n_instrument":3,"n_unverified":4,"n_honours":3,"n_violates":0,"n_no_contract":13,"n_pointer_only":4,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 3 honoured, 0 violated, 13 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/high-quality-monocular-depth-estimation-via#ran","syntology_url":"https://syntology.ai/paper/1812.11941","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.11941"}},"official":{"repos":["ialhashim/DenseDepth"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/quo-vadis-action-recognition-a-new-model-and","slug":"quo-vadis-action-recognition-a-new-model-and","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","date":"2017-05-22","arxiv_id":"1705.07750","repositories_listed":34,"syntology":{"n":28,"n_ran":16,"n_constructed":7,"n_ran_checked":10,"n_instrument":6,"n_unverified":12,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":7,"phrase":"16 ran (of which 7 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 6 where Syntology's instrument failed) · 12 unverified","sample_list":"/paper/quo-vadis-action-recognition-a-new-model-and#ran","syntology_url":"https://syntology.ai/paper/1705.07750","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1705.07750"}},"official":null}},{"url":"/paper/non-local-neural-networks","slug":"non-local-neural-networks","title":"Non-local Neural Networks","date":"2017-11-21","arxiv_id":"1711.07971","repositories_listed":32,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/non-local-neural-networks#ran","syntology_url":"https://syntology.ai/paper/1711.07971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.07971"}},"official":{"repos":["facebookresearch/video-nonlocal-net"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/drop-an-octave-reducing-spatial-redundancy-in","slug":"drop-an-octave-reducing-spatial-redundancy-in","title":"Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution","date":"2019-04-10","arxiv_id":"1904.05049","repositories_listed":28,"syntology":{"n":34,"n_ran":24,"n_constructed":0,"n_ran_checked":11,"n_instrument":13,"n_unverified":10,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":9,"phrase":"24 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 13 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/drop-an-octave-reducing-spatial-redundancy-in#ran","syntology_url":"https://syntology.ai/paper/1904.05049","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.05049"}},"official":{"repos":["facebookresearch/OctConv"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/a-closer-look-at-spatiotemporal-convolutions","slug":"a-closer-look-at-spatiotemporal-convolutions","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","date":"2017-11-30","arxiv_id":"1711.11248","repositories_listed":24,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/a-closer-look-at-spatiotemporal-convolutions#ran","syntology_url":"https://syntology.ai/paper/1711.11248","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.11248"}},"official":{"repos":["facebookresearch/R2Plus1D"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/swin-transformer-v2-scaling-up-capacity-and","slug":"swin-transformer-v2-scaling-up-capacity-and","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","date":"2021-11-18","arxiv_id":"2111.09883","repositories_listed":23,"syntology":{"n":30,"n_ran":17,"n_constructed":0,"n_ran_checked":14,"n_instrument":3,"n_unverified":13,"n_honours":0,"n_violates":3,"n_no_contract":11,"n_pointer_only":4,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 3 violated, 11 with no contract checked; 3 where Syntology's instrument failed) · 13 unverified","sample_list":"/paper/swin-transformer-v2-scaling-up-capacity-and#ran","syntology_url":"https://syntology.ai/paper/2111.09883","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.09883"}},"official":{"repos":["microsoft/Swin-Transformer"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/temporal-segment-networks-towards-good","slug":"temporal-segment-networks-towards-good","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","date":"2016-08-02","arxiv_id":"1608.00859","repositories_listed":22,"syntology":{"n":24,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":14,"n_honours":2,"n_violates":0,"n_no_contract":8,"n_pointer_only":3,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 14 unverified","sample_list":"/paper/temporal-segment-networks-towards-good#ran","syntology_url":"https://syntology.ai/paper/1608.00859","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1608.00859"}},"official":{"repos":["yjxiong/caffe","yjxiong/temporal-segment-networks"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/is-space-time-attention-all-you-need-for","slug":"is-space-time-attention-all-you-need-for","title":"Is Space-Time Attention All You Need for Video Understanding?","date":"2021-02-09","arxiv_id":"2102.05095","repositories_listed":16,"syntology":{"n":43,"n_ran":35,"n_constructed":17,"n_ran_checked":21,"n_instrument":14,"n_unverified":8,"n_honours":0,"n_violates":1,"n_no_contract":20,"n_pointer_only":14,"phrase":"35 ran (of which 17 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 1 violated, 20 with no contract checked; 14 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/is-space-time-attention-all-you-need-for#ran","syntology_url":"https://syntology.ai/paper/2102.05095","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.05095"}},"official":{"repos":["facebookresearch/TimeSformer"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/video-swin-transformer","slug":"video-swin-transformer","title":"Video Swin Transformer","date":"2021-06-24","arxiv_id":"2106.13230","repositories_listed":15,"syntology":{"n":32,"n_ran":19,"n_constructed":0,"n_ran_checked":14,"n_instrument":5,"n_unverified":13,"n_honours":1,"n_violates":0,"n_no_contract":13,"n_pointer_only":7,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 0 violated, 13 with no contract checked; 5 where Syntology's instrument failed) · 13 unverified","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"}},"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"]}}},{"url":"/paper/slowfast-networks-for-video-recognition","slug":"slowfast-networks-for-video-recognition","title":"SlowFast Networks for Video Recognition","date":"2018-12-10","arxiv_id":"1812.03982","repositories_listed":15,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","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"}},"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"]}}},{"url":"/paper/temporal-shift-module-for-efficient-video","slug":"temporal-shift-module-for-efficient-video","title":"TSM: Temporal Shift Module for Efficient Video Understanding","date":"2018-11-20","arxiv_id":"1811.08383","repositories_listed":13,"syntology":{"n":16,"n_ran":10,"n_constructed":0,"n_ran_checked":5,"n_instrument":5,"n_unverified":6,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":6,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/temporal-shift-module-for-efficient-video#ran","syntology_url":"https://syntology.ai/paper/1811.08383","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.08383"}},"official":{"repos":["MIT-HAN-LAB/temporal-shift-module"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/the-kinetics-human-action-video-dataset","slug":"the-kinetics-human-action-video-dataset","title":"The Kinetics Human Action Video Dataset","date":"2017-05-19","arxiv_id":"1705.06950","repositories_listed":13,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/the-kinetics-human-action-video-dataset#ran","syntology_url":"https://syntology.ai/paper/1705.06950","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1705.06950"}},"official":null}},{"url":"/paper/tokenlearner-what-can-8-learned-tokens-do-for","slug":"tokenlearner-what-can-8-learned-tokens-do-for","title":"TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?","date":"2021-06-21","arxiv_id":"2106.11297","repositories_listed":11,"syntology":{"n":3,"n_ran":3,"n_constructed":1,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","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"}},"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"]}}},{"url":"/paper/temporal-segment-networks-for-action","slug":"temporal-segment-networks-for-action","title":"Temporal Segment Networks for Action Recognition in Videos","date":"2017-05-08","arxiv_id":"1705.02953","repositories_listed":11,"syntology":null},{"url":"/paper/2103-15691","slug":"2103-15691","title":"ViViT: A Video Vision Transformer","date":"2021-03-29","arxiv_id":"2103.15691","repositories_listed":10,"syntology":{"n":21,"n_ran":14,"n_constructed":10,"n_ran_checked":13,"n_instrument":1,"n_unverified":7,"n_honours":1,"n_violates":0,"n_no_contract":12,"n_pointer_only":1,"phrase":"14 ran (of which 10 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/2103-15691#ran","syntology_url":"https://syntology.ai/paper/2103.15691","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.15691"}},"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"]}}},{"url":"/paper/videomae-masked-autoencoders-are-data-1","slug":"videomae-masked-autoencoders-are-data-1","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","date":"2022-03-23","arxiv_id":"2203.12602","repositories_listed":9,"syntology":{"n":13,"n_ran":10,"n_constructed":6,"n_ran_checked":8,"n_instrument":2,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":12,"phrase":"10 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/videomae-masked-autoencoders-are-data-1#ran","syntology_url":"https://syntology.ai/paper/2203.12602","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.12602"}},"official":{"repos":["MCG-NJU/VideoMAE","MCG-NJU/VideoMAE-Action-Detection"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":6,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/improved-multiscale-vision-transformers-for","slug":"improved-multiscale-vision-transformers-for","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","date":"2021-12-02","arxiv_id":"2112.01526","repositories_listed":9,"syntology":null},{"url":"/paper/graph-based-global-reasoning-networks","slug":"graph-based-global-reasoning-networks","title":"Graph-Based Global Reasoning Networks","date":"2018-11-30","arxiv_id":"1811.12814","repositories_listed":9,"syntology":{"n":15,"n_ran":15,"n_constructed":0,"n_ran_checked":7,"n_instrument":8,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":7,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 8 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/graph-based-global-reasoning-networks#ran","syntology_url":"https://syntology.ai/paper/1811.12814","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.12814"}},"official":{"repos":["facebookresearch/GloRe"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/multiscale-vision-transformers","slug":"multiscale-vision-transformers","title":"Multiscale Vision Transformers","date":"2021-04-22","arxiv_id":"2104.11227","repositories_listed":8,"syntology":{"n":26,"n_ran":13,"n_constructed":10,"n_ran_checked":11,"n_instrument":2,"n_unverified":13,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":5,"phrase":"13 ran (of which 10 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 13 unverified","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"}},"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"]}}},{"url":"/paper/x3d-expanding-architectures-for-efficient","slug":"x3d-expanding-architectures-for-efficient","title":"X3D: Expanding Architectures for Efficient Video Recognition","date":"2020-04-09","arxiv_id":"2004.04730","repositories_listed":8,"syntology":{"n":15,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/x3d-expanding-architectures-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2004.04730","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.04730"}},"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"]}}},{"url":"/paper/video-classification-with-channel-separated","slug":"video-classification-with-channel-separated","title":"Video Classification with Channel-Separated Convolutional Networks","date":"2019-04-04","arxiv_id":"1904.02811","repositories_listed":7,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/video-classification-with-channel-separated#ran","syntology_url":"https://syntology.ai/paper/1904.02811","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.02811"}},"official":{"repos":["facebookresearch/VMZ"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/two-stream-convolutional-networks-for-action","slug":"two-stream-convolutional-networks-for-action","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","date":"2014-06-09","arxiv_id":"1406.2199","repositories_listed":7,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/two-stream-convolutional-networks-for-action#ran","syntology_url":"https://syntology.ai/paper/1406.2199","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1406.2199"}},"official":{"repos":["feichtenhofer/twostreamfusion"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/eva-exploring-the-limits-of-masked-visual","slug":"eva-exploring-the-limits-of-masked-visual","title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","date":"2022-11-14","arxiv_id":"2211.07636","repositories_listed":6,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","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"}},"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"]}}},{"url":"/paper/coca-contrastive-captioners-are-image-text","slug":"coca-contrastive-captioners-are-image-text","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","date":"2022-05-04","arxiv_id":"2205.01917","repositories_listed":6,"syntology":{"n":17,"n_ran":10,"n_constructed":5,"n_ran_checked":9,"n_instrument":1,"n_unverified":7,"n_honours":2,"n_violates":0,"n_no_contract":7,"n_pointer_only":2,"phrase":"10 ran (of which 5 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified","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"}},"official":null}},{"url":"/paper/masked-feature-prediction-for-self-supervised","slug":"masked-feature-prediction-for-self-supervised","title":"Masked Feature Prediction for Self-Supervised Visual Pre-Training","date":"2021-12-16","arxiv_id":"2112.09133","repositories_listed":6,"syntology":null},{"url":"/paper/eco-efficient-convolutional-network-for","slug":"eco-efficient-convolutional-network-for","title":"ECO: Efficient Convolutional Network for Online Video Understanding","date":"2018-04-24","arxiv_id":"1804.09066","repositories_listed":6,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/eco-efficient-convolutional-network-for#ran","syntology_url":"https://syntology.ai/paper/1804.09066","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.09066"}},"official":{"repos":["mzolfaghari/ECO-efficient-video-understanding"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/bidirectional-cross-modal-knowledge","slug":"bidirectional-cross-modal-knowledge","title":"Bidirectional Cross-Modal Knowledge Exploration for Video Recognition with Pre-trained Vision-Language Models","date":"2022-12-31","arxiv_id":"2301.00182","repositories_listed":5,"syntology":null},{"url":"/paper/transferring-textual-knowledge-for-visual","slug":"transferring-textual-knowledge-for-visual","title":"Revisiting Classifier: Transferring Vision-Language Models for Video Recognition","date":"2022-07-04","arxiv_id":"2207.01297","repositories_listed":5,"syntology":null},{"url":"/paper/revisiting-3d-resnets-for-video-recognition","slug":"revisiting-3d-resnets-for-video-recognition","title":"Revisiting 3D ResNets for Video Recognition","date":"2021-09-03","arxiv_id":"2109.01696","repositories_listed":5,"syntology":null},{"url":"/paper/vatt-transformers-for-multimodal-self","slug":"vatt-transformers-for-multimodal-self","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","date":"2021-04-22","arxiv_id":"2104.11178","repositories_listed":5,"syntology":{"n":8,"n_ran":5,"n_constructed":4,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":8,"phrase":"5 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","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"}},"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"]}}},{"url":"/paper/what-and-how-well-you-performed-a-multitask","slug":"what-and-how-well-you-performed-a-multitask","title":"What and How Well You Performed? A Multitask Learning Approach to Action Quality Assessment","date":"2019-04-08","arxiv_id":"1904.04346","repositories_listed":5,"syntology":null},{"url":"/paper/representation-flow-for-action-recognition","slug":"representation-flow-for-action-recognition","title":"Representation Flow for Action Recognition","date":"2018-10-02","arxiv_id":"1810.01455","repositories_listed":5,"syntology":null},{"url":"/paper/temporal-relational-reasoning-in-videos","slug":"temporal-relational-reasoning-in-videos","title":"Temporal Relational Reasoning in Videos","date":"2017-11-22","arxiv_id":"1711.08496","repositories_listed":5,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/temporal-relational-reasoning-in-videos#ran","syntology_url":"https://syntology.ai/paper/1711.08496","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.08496"}},"official":null}},{"url":"/paper/hiera-a-hierarchical-vision-transformer","slug":"hiera-a-hierarchical-vision-transformer","title":"Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles","date":"2023-06-01","arxiv_id":"2306.00989","repositories_listed":4,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","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"}},"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"]}}},{"url":"/paper/mplug-2-a-modularized-multi-modal-foundation","slug":"mplug-2-a-modularized-multi-modal-foundation","title":"mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video","date":"2023-02-01","arxiv_id":"2302.00402","repositories_listed":4,"syntology":{"n":19,"n_ran":17,"n_constructed":0,"n_ran_checked":8,"n_instrument":9,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":2,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 9 where Syntology's instrument failed) · 2 unverified","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"}},"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"]}}},{"url":"/paper/masked-video-distillation-rethinking-masked","slug":"masked-video-distillation-rethinking-masked","title":"Masked Video Distillation: Rethinking Masked Feature Modeling for Self-supervised Video Representation Learning","date":"2022-12-08","arxiv_id":"2212.04500","repositories_listed":4,"syntology":null},{"url":"/paper/long-term-feature-banks-for-detailed-video","slug":"long-term-feature-banks-for-detailed-video","title":"Long-Term Feature Banks for Detailed Video Understanding","date":"2018-12-12","arxiv_id":"1812.05038","repositories_listed":4,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/long-term-feature-banks-for-detailed-video#ran","syntology_url":"https://syntology.ai/paper/1812.05038","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.05038"}},"official":{"repos":["facebookresearch/video-long-term-feature-banks"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/ts-lstm-and-temporal-inception-exploiting","slug":"ts-lstm-and-temporal-inception-exploiting","title":"TS-LSTM and Temporal-Inception: Exploiting Spatiotemporal Dynamics for Activity Recognition","date":"2017-03-30","arxiv_id":"1703.10667","repositories_listed":4,"syntology":null},{"url":"/paper/learning-video-representations-from-large","slug":"learning-video-representations-from-large","title":"Learning Video Representations from Large Language Models","date":"2022-12-08","arxiv_id":"2212.04501","repositories_listed":3,"syntology":{"n":20,"n_ran":13,"n_constructed":0,"n_ran_checked":9,"n_instrument":4,"n_unverified":7,"n_honours":0,"n_violates":2,"n_no_contract":7,"n_pointer_only":20,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 2 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/learning-video-representations-from-large#ran","syntology_url":"https://syntology.ai/paper/2212.04501","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.04501"}},"official":{"repos":["facebookresearch/lavila"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/uniformer-unified-transformer-for-efficient","slug":"uniformer-unified-transformer-for-efficient","title":"UniFormer: Unified Transformer for Efficient Spatial-Temporal Representation Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/movinets-mobile-video-networks-for-efficient","slug":"movinets-mobile-video-networks-for-efficient","title":"MoViNets: Mobile Video Networks for Efficient Video Recognition","date":"2021-03-21","arxiv_id":"2103.11511","repositories_listed":3,"syntology":{"n":13,"n_ran":9,"n_constructed":6,"n_ran_checked":8,"n_instrument":1,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"9 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","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"}},"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"]}}},{"url":"/paper/revisiting-resnets-improved-training-and","slug":"revisiting-resnets-improved-training-and","title":"Revisiting ResNets: Improved Training and Scaling Strategies","date":"2021-03-13","arxiv_id":"2103.07579","repositories_listed":3,"syntology":null},{"url":"/paper/mvfnet-multi-view-fusion-network-for","slug":"mvfnet-multi-view-fusion-network-for","title":"MVFNet: Multi-View Fusion Network for Efficient Video Recognition","date":"2020-12-13","arxiv_id":"2012.06977","repositories_listed":3,"syntology":null},{"url":"/paper/pyramidal-convolution-rethinking","slug":"pyramidal-convolution-rethinking","title":"Pyramidal Convolution: Rethinking Convolutional Neural Networks for Visual Recognition","date":"2020-06-20","arxiv_id":"2006.11538","repositories_listed":3,"syntology":null},{"url":"/paper/omni-sourced-webly-supervised-learning-for","slug":"omni-sourced-webly-supervised-learning-for","title":"Omni-sourced Webly-supervised Learning for Video Recognition","date":"2020-03-29","arxiv_id":"2003.13042","repositories_listed":3,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/omni-sourced-webly-supervised-learning-for#ran","syntology_url":"https://syntology.ai/paper/2003.13042","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.13042"}},"official":{"repos":["open-mmlab/mmaction"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/audiovisual-slowfast-networks-for-video","slug":"audiovisual-slowfast-networks-for-video","title":"Audiovisual SlowFast Networks for Video Recognition","date":"2020-01-23","arxiv_id":"2001.08740","repositories_listed":3,"syntology":null},{"url":"/paper/word-level-deep-sign-language-recognition","slug":"word-level-deep-sign-language-recognition","title":"Word-level Deep Sign Language Recognition from Video: A New Large-scale Dataset and Methods Comparison","date":"2019-10-24","arxiv_id":"1910.11006","repositories_listed":3,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/word-level-deep-sign-language-recognition#ran","syntology_url":"https://syntology.ai/paper/1910.11006","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.11006"}},"official":{"repos":["dxli94/WLASL"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/video-action-classification-using-prednet","slug":"video-action-classification-using-prednet","title":"PredNet and Predictive Coding: A Critical Review","date":"2019-06-14","arxiv_id":"1906.11902","repositories_listed":3,"syntology":null},{"url":"/paper/what-makes-training-multi-modal-networks-hard","slug":"what-makes-training-multi-modal-networks-hard","title":"What Makes Training Multi-Modal Classification Networks Hard?","date":"2019-05-29","arxiv_id":"1905.12681","repositories_listed":3,"syntology":{"n":11,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/what-makes-training-multi-modal-networks-hard#ran","syntology_url":"https://syntology.ai/paper/1905.12681","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.12681"}},"official":null}},{"url":"/paper/large-scale-weakly-supervised-pre-training","slug":"large-scale-weakly-supervised-pre-training","title":"Large-scale weakly-supervised pre-training for video action recognition","date":"2019-05-02","arxiv_id":"1905.00561","repositories_listed":3,"syntology":{"n":21,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/large-scale-weakly-supervised-pre-training#ran","syntology_url":"https://syntology.ai/paper/1905.00561","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.00561"}},"official":null}},{"url":"/paper/videobert-a-joint-model-for-video-and","slug":"videobert-a-joint-model-for-video-and","title":"VideoBERT: A Joint Model for Video and Language Representation Learning","date":"2019-04-03","arxiv_id":"1904.01766","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/videobert-a-joint-model-for-video-and#ran","syntology_url":"https://syntology.ai/paper/1904.01766","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.01766"}},"official":null}},{"url":"/paper/timeception-for-complex-action-recognition","slug":"timeception-for-complex-action-recognition","title":"Timeception for Complex Action Recognition","date":"2018-12-04","arxiv_id":"1812.01289","repositories_listed":3,"syntology":null},{"url":"/paper/weakly-supervised-action-localization-by","slug":"weakly-supervised-action-localization-by","title":"Weakly Supervised Action Localization by Sparse Temporal Pooling Network","date":"2017-12-14","arxiv_id":"1712.05080","repositories_listed":3,"syntology":null},{"url":"/paper/hierarchical-video-generation-from-orthogonal","slug":"hierarchical-video-generation-from-orthogonal","title":"Hierarchical Video Generation from Orthogonal Information: Optical Flow and Texture","date":"2017-11-27","arxiv_id":"1711.09618","repositories_listed":3,"syntology":null},{"url":"/paper/internvideo2-scaling-video-foundation-models","slug":"internvideo2-scaling-video-foundation-models","title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","date":"2024-03-22","arxiv_id":"2403.15377","repositories_listed":2,"syntology":null},{"url":"/paper/videomamba-state-space-model-for-efficient","slug":"videomamba-state-space-model-for-efficient","title":"VideoMamba: State Space Model for Efficient Video Understanding","date":"2024-03-11","arxiv_id":"2403.06977","repositories_listed":2,"syntology":{"n":15,"n_ran":9,"n_constructed":5,"n_ran_checked":6,"n_instrument":3,"n_unverified":6,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"9 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/videomamba-state-space-model-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2403.06977","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.06977"}},"official":{"repos":["opengvlab/videomamba"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/side4video-spatial-temporal-side-network-for","slug":"side4video-spatial-temporal-side-network-for","title":"Side4Video: Spatial-Temporal Side Network for Memory-Efficient Image-to-Video Transfer Learning","date":"2023-11-27","arxiv_id":"2311.15769","repositories_listed":2,"syntology":null},{"url":"/paper/zeroi2v-zero-cost-adaptation-of-pre-trained","slug":"zeroi2v-zero-cost-adaptation-of-pre-trained","title":"ZeroI2V: Zero-Cost Adaptation of Pre-trained Transformers from Image to Video","date":"2023-10-02","arxiv_id":"2310.01324","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/zeroi2v-zero-cost-adaptation-of-pre-trained#ran","syntology_url":"https://syntology.ai/paper/2310.01324","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.01324"}},"official":{"repos":["mcg-nju/zeroi2v","leexinhao/ZeroI2V"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/what-can-simple-arithmetic-operations-do-for","slug":"what-can-simple-arithmetic-operations-do-for","title":"What Can Simple Arithmetic Operations Do for Temporal Modeling?","date":"2023-07-18","arxiv_id":"2307.08908","repositories_listed":2,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/what-can-simple-arithmetic-operations-do-for#ran","syntology_url":"https://syntology.ai/paper/2307.08908","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.08908"}},"official":{"repos":["whwu95/ATM"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/one-peace-exploring-one-general","slug":"one-peace-exploring-one-general","title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","date":"2023-05-18","arxiv_id":"2305.11172","repositories_listed":2,"syntology":{"n":7,"n_ran":5,"n_constructed":2,"n_ran_checked":4,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/one-peace-exploring-one-general#ran","syntology_url":"https://syntology.ai/paper/2305.11172","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11172"}},"official":{"repos":["OFA-Sys/ONE-PEACE"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/visual-representation-learning-from-unlabeled","slug":"visual-representation-learning-from-unlabeled","title":"ViC-MAE: Self-Supervised Representation Learning from Images and Video with Contrastive Masked Autoencoders","date":"2023-03-21","arxiv_id":"2303.12001","repositories_listed":2,"syntology":null},{"url":"/paper/internvideo-general-video-foundation-models","slug":"internvideo-general-video-foundation-models","title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","date":"2022-12-06","arxiv_id":"2212.03191","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","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"}},"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"]}}},{"url":"/paper/adamae-adaptive-masking-for-efficient","slug":"adamae-adaptive-masking-for-efficient","title":"AdaMAE: Adaptive Masking for Efficient Spatiotemporal Learning with Masked Autoencoders","date":"2022-11-16","arxiv_id":"2211.09120","repositories_listed":2,"syntology":{"n":25,"n_ran":18,"n_constructed":0,"n_ran_checked":13,"n_instrument":5,"n_unverified":7,"n_honours":1,"n_violates":0,"n_no_contract":12,"n_pointer_only":6,"phrase":"18 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 5 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/adamae-adaptive-masking-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2211.09120","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.09120"}},"official":{"repos":["wgcban/adamae"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/uniformerv2-spatiotemporal-learning-by-arming","slug":"uniformerv2-spatiotemporal-learning-by-arming","title":"UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer","date":"2022-09-22","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/frozen-clip-models-are-efficient-video","slug":"frozen-clip-models-are-efficient-video","title":"Frozen CLIP Models are Efficient Video Learners","date":"2022-08-06","arxiv_id":"2208.03550","repositories_listed":2,"syntology":{"n":10,"n_ran":5,"n_constructed":3,"n_ran_checked":5,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":10,"phrase":"5 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/frozen-clip-models-are-efficient-video#ran","syntology_url":"https://syntology.ai/paper/2208.03550","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.03550"}},"official":{"repos":["opengvlab/efficient-video-recognition"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":3,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/expanding-language-image-pretrained-models","slug":"expanding-language-image-pretrained-models","title":"Expanding Language-Image Pretrained Models for General Video Recognition","date":"2022-08-04","arxiv_id":"2208.02816","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","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"}},"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"]}}},{"url":"/paper/proformer-learning-data-efficient","slug":"proformer-learning-data-efficient","title":"Delving Deep into One-Shot Skeleton-based Action Recognition with Diverse Occlusions","date":"2022-02-23","arxiv_id":"2202.11423","repositories_listed":2,"syntology":null},{"url":"/paper/omnivore-a-single-model-for-many-visual","slug":"omnivore-a-single-model-for-many-visual","title":"Omnivore: A Single Model for Many Visual Modalities","date":"2022-01-20","arxiv_id":"2201.08377","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/omnivore-a-single-model-for-many-visual#ran","syntology_url":"https://syntology.ai/paper/2201.08377","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.08377"}},"official":{"repos":["facebookresearch/omnivore"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/florence-a-new-foundation-model-for-computer","slug":"florence-a-new-foundation-model-for-computer","title":"Florence: A New Foundation Model for Computer Vision","date":"2021-11-22","arxiv_id":"2111.11432","repositories_listed":2,"syntology":null},{"url":"/paper/tada-temporally-adaptive-convolutions-for-1","slug":"tada-temporally-adaptive-convolutions-for-1","title":"TAda! Temporally-Adaptive Convolutions for Video Understanding","date":"2021-10-12","arxiv_id":"2110.06178","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/tada-temporally-adaptive-convolutions-for-1#ran","syntology_url":"https://syntology.ai/paper/2110.06178","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.06178"}},"official":{"repos":["alibaba-mmai-research/pytorch-video-understanding"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"url":"/paper/actionclip-a-new-paradigm-for-video-action","slug":"actionclip-a-new-paradigm-for-video-action","title":"ActionCLIP: A New Paradigm for Video Action Recognition","date":"2021-09-17","arxiv_id":"2109.08472","repositories_listed":2,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/actionclip-a-new-paradigm-for-video-action#ran","syntology_url":"https://syntology.ai/paper/2109.08472","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.08472"}},"official":{"repos":["sallymmx/actionclip"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/tnt-text-conditioned-network-with","slug":"tnt-text-conditioned-network-with","title":"TNT: Text-Conditioned Network with Transductive Inference for Few-Shot Video Classification","date":"2021-06-21","arxiv_id":"2106.11173","repositories_listed":2,"syntology":null},{"url":"/paper/keeping-your-eye-on-the-ball-trajectory","slug":"keeping-your-eye-on-the-ball-trajectory","title":"Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers","date":"2021-06-09","arxiv_id":"2106.05392","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/keeping-your-eye-on-the-ball-trajectory#ran","syntology_url":"https://syntology.ai/paper/2106.05392","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.05392"}},"official":{"repos":["facebookresearch/Motionformer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/video-classification-with-finecoarse-networks","slug":"video-classification-with-finecoarse-networks","title":"Busy-Quiet Video Disentangling for Video Classification","date":"2021-03-29","arxiv_id":"2103.15584","repositories_listed":2,"syntology":null},{"url":"/paper/an-image-is-worth-16x16-words-what-is-a-video","slug":"an-image-is-worth-16x16-words-what-is-a-video","title":"An Image is Worth 16x16 Words, What is a Video Worth?","date":"2021-03-25","arxiv_id":"2103.13915","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/an-image-is-worth-16x16-words-what-is-a-video#ran","syntology_url":"https://syntology.ai/paper/2103.13915","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.13915"}},"official":{"repos":["Alibaba-MIIL/STAM"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/motionsqueeze-neural-motion-feature-learning","slug":"motionsqueeze-neural-motion-feature-learning","title":"MotionSqueeze: Neural Motion Feature Learning for Video Understanding","date":"2020-07-20","arxiv_id":"2007.09933","repositories_listed":2,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/motionsqueeze-neural-motion-feature-learning#ran","syntology_url":"https://syntology.ai/paper/2007.09933","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.09933"}},"official":null}},{"url":"/paper/background-modeling-via-uncertainty","slug":"background-modeling-via-uncertainty","title":"Weakly-supervised Temporal Action Localization by Uncertainty Modeling","date":"2020-06-12","arxiv_id":"2006.07006","repositories_listed":2,"syntology":null},{"url":"/paper/hallucinet-ing-spatiotemporal-representations","slug":"hallucinet-ing-spatiotemporal-representations","title":"HalluciNet-ing Spatiotemporal Representations Using a 2D-CNN","date":"2019-12-10","arxiv_id":"1912.04430","repositories_listed":2,"syntology":null},{"url":"/paper/deep-concept-wise-temporal-convolutional","slug":"deep-concept-wise-temporal-convolutional","title":"Deep Concept-wise Temporal Convolutional Networks for Action Localization","date":"2019-08-26","arxiv_id":"1908.09442","repositories_listed":2,"syntology":null},{"url":"/paper/an-evaluation-of-action-recognition-models-on","slug":"an-evaluation-of-action-recognition-models-on","title":"An Evaluation of Action Recognition Models on EPIC-Kitchens","date":"2019-08-02","arxiv_id":"1908.00867","repositories_listed":2,"syntology":null},{"url":"/paper/assemblenet-searching-for-multi-stream-neural","slug":"assemblenet-searching-for-multi-stream-neural","title":"AssembleNet: Searching for Multi-Stream Neural Connectivity in Video Architectures","date":"2019-05-30","arxiv_id":"1905.13209","repositories_listed":2,"syntology":null},{"url":"/paper/a2-nets-double-attention-networks-1","slug":"a2-nets-double-attention-networks-1","title":"A^2-Nets: Double Attention Networks","date":"2018-12-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/soccernet-a-scalable-dataset-for-action","slug":"soccernet-a-scalable-dataset-for-action","title":"SoccerNet: A Scalable Dataset for Action Spotting in Soccer Videos","date":"2018-04-12","arxiv_id":"1804.04527","repositories_listed":2,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/soccernet-a-scalable-dataset-for-action#ran","syntology_url":"https://syntology.ai/paper/1804.04527","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.04527"}},"official":null}},{"url":"/paper/hacs-human-action-clips-and-segments-dataset","slug":"hacs-human-action-clips-and-segments-dataset","title":"HACS: Human Action Clips and Segments Dataset for Recognition and Temporal Localization","date":"2017-12-26","arxiv_id":"1712.09374","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/hacs-human-action-clips-and-segments-dataset#ran","syntology_url":"https://syntology.ai/paper/1712.09374","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1712.09374"}},"official":null}},{"url":"/paper/rethinking-spatiotemporal-feature-learning","slug":"rethinking-spatiotemporal-feature-learning","title":"Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification","date":"2017-12-13","arxiv_id":"1712.04851","repositories_listed":2,"syntology":null},{"url":"/paper/asynchronous-temporal-fields-for-action","slug":"asynchronous-temporal-fields-for-action","title":"Asynchronous Temporal Fields for Action Recognition","date":"2016-12-19","arxiv_id":"1612.06371","repositories_listed":2,"syntology":null},{"url":"/paper/ntu-rgbd-a-large-scale-dataset-for-3d-human","slug":"ntu-rgbd-a-large-scale-dataset-for-3d-human","title":"NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis","date":"2016-04-11","arxiv_id":"1604.02808","repositories_listed":2,"syntology":null},{"url":"/paper/visual-semantic-role-labeling","slug":"visual-semantic-role-labeling","title":"Visual Semantic Role Labeling","date":"2015-05-17","arxiv_id":"1505.04474","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/visual-semantic-role-labeling#ran","syntology_url":"https://syntology.ai/paper/1505.04474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1505.04474"}},"official":null}},{"url":"/paper/from-play-to-replay-composed-video-retrieval","slug":"from-play-to-replay-composed-video-retrieval","title":"From Play to Replay: Composed Video Retrieval for Temporally Fine-Grained Videos","date":"2025-06-05","arxiv_id":"2506.05274","repositories_listed":1,"syntology":null},{"url":"/paper/spatio-temporal-joint-density-driven-learning","slug":"spatio-temporal-joint-density-driven-learning","title":"Spatio-Temporal Joint Density Driven Learning for Skeleton-Based Action Recognition","date":"2025-05-29","arxiv_id":"2505.23012","repositories_listed":1,"syntology":null},{"url":"/paper/make-your-training-flexible-towards","slug":"make-your-training-flexible-towards","title":"Make Your Training Flexible: Towards Deployment-Efficient Video Models","date":"2025-03-18","arxiv_id":"2503.14237","repositories_listed":1,"syntology":{"n":17,"n_ran":17,"n_constructed":0,"n_ran_checked":17,"n_instrument":0,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":14,"n_pointer_only":6,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 3 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/make-your-training-flexible-towards#ran","syntology_url":"https://syntology.ai/paper/2503.14237","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.14237"}},"official":{"repos":["opengvlab/fluxvit"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":17,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/dejavid-encoder-agnostic-learned-temporal","slug":"dejavid-encoder-agnostic-learned-temporal","title":"DejaVid: Encoder-Agnostic Learned Temporal Matching for Video Classification","date":"2025-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/temporal-action-localization-with-cross-layer","slug":"temporal-action-localization-with-cross-layer","title":"Temporal Action Localization with Cross Layer Task Decoupling and Refinement","date":"2024-12-12","arxiv_id":"2412.09202","repositories_listed":1,"syntology":null},{"url":"/paper/knn-mmd-cross-domain-wi-fi-sensing-based-on","slug":"knn-mmd-cross-domain-wi-fi-sensing-based-on","title":"KNN-MMD: Cross Domain Wireless Sensing via Local Distribution Alignment","date":"2024-12-06","arxiv_id":"2412.04783","repositories_listed":1,"syntology":null},{"url":"/paper/towards-universal-soccer-video-understanding","slug":"towards-universal-soccer-video-understanding","title":"Towards Universal Soccer Video Understanding","date":"2024-12-02","arxiv_id":"2412.01820","repositories_listed":1,"syntology":null},{"url":"/paper/multilevel-semantic-and-adaptive-actionness","slug":"multilevel-semantic-and-adaptive-actionness","title":"Multilevel semantic and adaptive actionness learning for weakly supervised temporal action localization","date":"2024-11-24","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/occludenet-a-causal-journey-into-mixed-view","slug":"occludenet-a-causal-journey-into-mixed-view","title":"OccludeNet: A Causal Journey into Mixed-View Actor-Centric Video Action Recognition under Occlusions","date":"2024-11-24","arxiv_id":"2411.15729","repositories_listed":1,"syntology":null},{"url":"/paper/person-segmentation-and-action-classification","slug":"person-segmentation-and-action-classification","title":"Person Segmentation and Action Classification for Multi-Channel Hemisphere Field of View LiDAR Sensors","date":"2024-11-17","arxiv_id":"2411.11151","repositories_listed":1,"syntology":null},{"url":"/paper/autoregressive-adaptive-hypergraph","slug":"autoregressive-adaptive-hypergraph","title":"Autoregressive Adaptive Hypergraph Transformer for Skeleton-based Activity Recognition","date":"2024-11-08","arxiv_id":"2411.05692","repositories_listed":1,"syntology":null},{"url":"/paper/multi-class-activity-classification-in-videos","slug":"multi-class-activity-classification-in-videos","title":"Multi class activity classification in videos using Motion History Image generation","date":"2024-10-13","arxiv_id":"2410.09902","repositories_listed":1,"syntology":null}],"syntology_records":53,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"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)"},"since_archive_judged":{"papers":1,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"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; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/action-classification-on-kinetics-600","since_archive":"/sota/action-classification-on-kinetics-600#since-judged","papers_judged":1,"placed":0}]},"papers_where_code_ran":83,"papers_where_code_ran_first_page":"/task/action-classification/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":5,"url":"/task/action-classification/papers/2","json":"/task/action-classification/papers/2.json","rows":100},{"order":"archive","page":3,"of":5,"url":"/task/action-classification/papers/3","json":"/task/action-classification/papers/3.json","rows":100},{"order":"archive","page":4,"of":5,"url":"/task/action-classification/papers/4","json":"/task/action-classification/papers/4.json","rows":100},{"order":"archive","page":5,"of":5,"url":"/task/action-classification/papers/5","json":"/task/action-classification/papers/5.json","rows":57},{"order":"ran","page":1,"of":1,"url":"/task/action-classification/papers/ran/1","json":"/task/action-classification/papers/ran/1.json","rows":83}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper 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"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"da6eecef5bcc9caea96bfb9d9913deeefccbd23116fde5280703c0664e862f65","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}