{"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-recognition-in-videos-2","name":"Action Recognition In Videos","slug":"action-recognition-in-videos-2","description_markdown":"**Action Recognition in Videos** is a task in computer vision and pattern recognition where the goal is to identify and categorize human actions performed in a video sequence. The task involves analyzing the spatiotemporal dynamics of the actions and mapping them to a predefined set of action classes, such as running, jumping, or swimming.","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":124,"papers_with_code":71,"benchmarks":17,"benchmark_tables_in_archive":17,"benchmark_tables_shown":17,"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":17,"subtasks":1,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/action-recognition-in-videos-on-jester-1","slug":"action-recognition-in-videos-on-jester-1","dataset":"Jester (Gesture Recognition)","dataset_url":"/dataset/jester-gesture-recognition","rows_in_archive":9,"metrics":["Val"],"first_row_in_archive_order":{"model":"CPNet Res34, 5 CP","paper_title":"Learning Video Representations from Correspondence Proposals","paper_url":"/paper/learning-video-representations-from","paper_date":"2019-05-20","arxiv_id":"1905.07853","code_links":[{"title":"xingyul/meteornet","url":"https://github.com/xingyul/meteornet"},{"title":"xingyul/cpnet","url":"https://github.com/xingyul/cpnet"}],"syntology":null}},{"leaderboard":"/sota/action-recognition-in-videos-on-pku-mmd","slug":"action-recognition-in-videos-on-pku-mmd","dataset":"PKU-MMD","dataset_url":"/dataset/pku-mmd","rows_in_archive":5,"metrics":["X-Sub","X-View"],"first_row_in_archive_order":{"model":"DSCNet (RGB + Pose)","paper_title":"A Dense-Sparse Complementary Network for Human Action Recognition based on RGB and Skeleton Modalities","paper_url":"/paper/a-dense-sparse-complementary-network-for","paper_date":"2023-12-28","arxiv_id":null,"code_links":[{"title":"Maxchengqin/DSCNet","url":"https://github.com/Maxchengqin/DSCNet"}],"syntology":null}},{"leaderboard":"/sota/action-recognition-in-videos-on-ucf101-2","slug":"action-recognition-in-videos-on-ucf101-2","dataset":"UCF101","dataset_url":"/dataset/ucf101","rows_in_archive":5,"metrics":["3-fold Accuracy"],"first_row_in_archive_order":{"model":"STM (ImageNet+Kinetics pretrain)","paper_title":"STM: SpatioTemporal and Motion Encoding for Action Recognition","paper_url":"/paper/stm-spatiotemporal-and-motion-encoding-for","paper_date":"2019-08-07","arxiv_id":"1908.02486","code_links":[],"syntology":null}},{"leaderboard":"/sota/action-recognition-in-videos-on-something-3","slug":"action-recognition-in-videos-on-something-3","dataset":"Something-Something V2","dataset_url":"/dataset/something-something-v2","rows_in_archive":4,"metrics":["Top-1 Accuracy","Top-5 Accuracy"],"first_row_in_archive_order":{"model":"STM (16 frames, ImageNet pretraining)","paper_title":"STM: SpatioTemporal and Motion Encoding for Action Recognition","paper_url":"/paper/stm-spatiotemporal-and-motion-encoding-for","paper_date":"2019-08-07","arxiv_id":"1908.02486","code_links":[],"syntology":null}},{"leaderboard":"/sota/action-recognition-in-videos-on-kinetics-400-1","slug":"action-recognition-in-videos-on-kinetics-400-1","dataset":"Kinetics-400","dataset_url":"/dataset/kinetics","rows_in_archive":3,"metrics":["Top-1 Accuracy","Top-5 Accuracy"],"first_row_in_archive_order":{"model":"Florence","paper_title":"Florence: A New Foundation Model for Computer Vision","paper_url":"/paper/florence-a-new-foundation-model-for-computer","paper_date":"2021-11-22","arxiv_id":"2111.11432","code_links":[{"title":"microsoft/unicl","url":"https://github.com/microsoft/unicl"},{"title":"MindCode-4/code-3","url":"https://github.com/MindCode-4/code-3/tree/main/florence2"}],"syntology":null}},{"leaderboard":"/sota/action-recognition-in-videos-on-something-2","slug":"action-recognition-in-videos-on-something-2","dataset":"Something-Something V1","dataset_url":"/dataset/something-something-v1","rows_in_archive":3,"metrics":["Top 1 Accuracy"],"first_row_in_archive_order":{"model":"STM (16 frames, ImageNet pretraining)","paper_title":"STM: SpatioTemporal and Motion Encoding for Action Recognition","paper_url":"/paper/stm-spatiotemporal-and-motion-encoding-for","paper_date":"2019-08-07","arxiv_id":"1908.02486","code_links":[],"syntology":null}},{"leaderboard":"/sota/action-recognition-in-videos-on-ava-v2-2","slug":"action-recognition-in-videos-on-ava-v2-2","dataset":"AVA v2.2","dataset_url":"/dataset/ava","rows_in_archive":2,"metrics":["mAP (Val)"],"first_row_in_archive_order":{"model":"YOWO+LFB*","paper_title":"You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization","paper_url":"/paper/you-only-watch-once-a-unified-cnn","paper_date":"2019-11-15","arxiv_id":"1911.06644","code_links":[{"title":"wei-tim/YOWO","url":"https://github.com/wei-tim/YOWO"},{"title":"zwtu/YOWO-Paddle","url":"https://github.com/zwtu/YOWO-Paddle"},{"title":"BoChenUIUC/YOWO","url":"https://github.com/BoChenUIUC/YOWO"},{"title":"nuschandra/Tennis-Stroke-Detection","url":"https://github.com/nuschandra/Tennis-Stroke-Detection"},{"title":"Stepphonwol/my_yowo","url":"https://github.com/Stepphonwol/my_yowo"}],"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":5,"n_honours":1,"n_violates":2,"n_no_contract":4,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 2 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/you-only-watch-once-a-unified-cnn#ran","syntology_url":"https://syntology.ai/paper/1911.06644","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.06644"}},"official":{"repos":["wei-tim/YOWO"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/action-recognition-in-videos-on-fs-something","slug":"action-recognition-in-videos-on-fs-something","dataset":"FS-Something-Something V2-Small","dataset_url":null,"rows_in_archive":2,"metrics":["Top-1 Accuracy(5-Way-1-Shot)","Top-1 Accuracy(5-Way-5-Shot)"],"first_row_in_archive_order":{"model":"ITANet","paper_title":"Learning Implicit Temporal Alignment for Few-shot Video Classification","paper_url":"/paper/learning-implicit-temporal-alignment-for-few","paper_date":"2021-05-11","arxiv_id":"2105.04823","code_links":[{"title":"tonysy/PyAction","url":"https://github.com/tonysy/PyAction"}],"syntology":null}},{"leaderboard":"/sota/action-recognition-in-videos-on-fs-something-1","slug":"action-recognition-in-videos-on-fs-something-1","dataset":"FS-Something-Something V2-Full","dataset_url":null,"rows_in_archive":2,"metrics":["Top-1 Accuracy(5-Way-1-Shot)","Top-1 Accuracy(5-Way-5-Shot)"],"first_row_in_archive_order":{"model":"ITANet","paper_title":"Learning Implicit Temporal Alignment for Few-shot Video Classification","paper_url":"/paper/learning-implicit-temporal-alignment-for-few","paper_date":"2021-05-11","arxiv_id":"2105.04823","code_links":[{"title":"tonysy/PyAction","url":"https://github.com/tonysy/PyAction"}],"syntology":null}},{"leaderboard":"/sota/action-recognition-in-videos-on-sports-1m-1","slug":"action-recognition-in-videos-on-sports-1m-1","dataset":"Sports-1M","dataset_url":"/dataset/sports-1m","rows_in_archive":2,"metrics":["Video hit@1","Video hit@5"],"first_row_in_archive_order":{"model":"G-Blend","paper_title":"What Makes Training Multi-Modal Classification Networks Hard?","paper_url":"/paper/what-makes-training-multi-modal-networks-hard","paper_date":"2019-05-29","arxiv_id":"1905.12681","code_links":[{"title":"facebookresearch/R2Plus1D","url":"https://github.com/facebookresearch/R2Plus1D"},{"title":"facebookresearch/VMZ","url":"https://github.com/facebookresearch/VMZ"},{"title":"guide2157/ChulaXrayClassifier","url":"https://github.com/guide2157/ChulaXrayClassifier"}],"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}}},{"leaderboard":"/sota/action-recognition-in-videos-on-thumos14-1","slug":"action-recognition-in-videos-on-thumos14-1","dataset":"THUMOS’14","dataset_url":"/dataset/thumos14-1","rows_in_archive":2,"metrics":["mAP@0.1","mAP@0.2","mAP@0.3","mAP@0.4","mAP@0.5"],"first_row_in_archive_order":{"model":"Single-stream R-C3D (two-way buffer)","paper_title":"R-C3D: Region Convolutional 3D Network for Temporal Activity Detection","paper_url":"/paper/r-c3d-region-convolutional-3d-network-for","paper_date":"2017-03-22","arxiv_id":"1703.07814","code_links":[{"title":"VisionLearningGroup/R-C3D","url":"https://github.com/VisionLearningGroup/R-C3D"},{"title":"2023-MindSpore-4/Code8","url":"https://github.com/2023-MindSpore-4/Code8/tree/main/C3D"},{"title":"MindSpore-paper-code-3/code6","url":"https://github.com/MindSpore-paper-code-3/code6/tree/main/C3D"}],"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/r-c3d-region-convolutional-3d-network-for#ran","syntology_url":"https://syntology.ai/paper/1703.07814","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.07814"}},"official":{"repos":["VisionLearningGroup/R-C3D"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}}},{"leaderboard":"/sota/action-recognition-in-videos-on-activitynet-1","slug":"action-recognition-in-videos-on-activitynet-1","dataset":"ActivityNet","dataset_url":"/dataset/activitynet","rows_in_archive":1,"metrics":["mAP"],"first_row_in_archive_order":{"model":"LSTM + Pretrained on YT-8M","paper_title":"YouTube-8M: A Large-Scale Video Classification Benchmark","paper_url":"/paper/youtube-8m-a-large-scale-video-classification","paper_date":"2016-09-27","arxiv_id":"1609.08675","code_links":[{"title":"google/youtube-8m","url":"https://github.com/google/youtube-8m"},{"title":"AKASH2907/Content-based-Video-Recommendation","url":"https://github.com/AKASH2907/Content-based-Video-Recommendation"},{"title":"AKASH2907/Content-based-Video-Relevance-Prediction","url":"https://github.com/AKASH2907/Content-based-Video-Relevance-Prediction"},{"title":"taufikxu/youtube","url":"https://github.com/taufikxu/youtube"},{"title":"Cloud-Computing-IoT/speakEasy","url":"https://github.com/Cloud-Computing-IoT/speakEasy"},{"title":"Cloud-Computing-IoT/Cloud-Enabled-Smart-Speaker","url":"https://github.com/Cloud-Computing-IoT/Cloud-Enabled-Smart-Speaker"},{"title":"boseaslcohort/youtube-8m","url":"https://github.com/boseaslcohort/youtube-8m"}],"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/youtube-8m-a-large-scale-video-classification#ran","syntology_url":"https://syntology.ai/paper/1609.08675","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1609.08675"}},"official":null}}},{"leaderboard":"/sota/action-recognition-in-videos-on-ava-v2-1","slug":"action-recognition-in-videos-on-ava-v2-1","dataset":"AVA v2.1","dataset_url":"/dataset/ava","rows_in_archive":1,"metrics":["mAP (Val)"],"first_row_in_archive_order":{"model":"YOWO+LFB*","paper_title":"You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization","paper_url":"/paper/you-only-watch-once-a-unified-cnn","paper_date":"2019-11-15","arxiv_id":"1911.06644","code_links":[{"title":"wei-tim/YOWO","url":"https://github.com/wei-tim/YOWO"},{"title":"zwtu/YOWO-Paddle","url":"https://github.com/zwtu/YOWO-Paddle"},{"title":"BoChenUIUC/YOWO","url":"https://github.com/BoChenUIUC/YOWO"},{"title":"nuschandra/Tennis-Stroke-Detection","url":"https://github.com/nuschandra/Tennis-Stroke-Detection"},{"title":"Stepphonwol/my_yowo","url":"https://github.com/Stepphonwol/my_yowo"}],"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":5,"n_honours":1,"n_violates":2,"n_no_contract":4,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 2 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/you-only-watch-once-a-unified-cnn#ran","syntology_url":"https://syntology.ai/paper/1911.06644","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.06644"}},"official":{"repos":["wei-tim/YOWO"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/action-recognition-in-videos-on-hmdb-51-1","slug":"action-recognition-in-videos-on-hmdb-51-1","dataset":"HMDB-51","dataset_url":"/dataset/hmdb51","rows_in_archive":1,"metrics":["Average accuracy of 3 splits"],"first_row_in_archive_order":{"model":"STM (ImageNet+Kinetics pretrain)","paper_title":"STM: SpatioTemporal and Motion Encoding for Action Recognition","paper_url":"/paper/stm-spatiotemporal-and-motion-encoding-for","paper_date":"2019-08-07","arxiv_id":"1908.02486","code_links":[],"syntology":null}},{"leaderboard":"/sota/action-recognition-in-videos-on-kinetics-600","slug":"action-recognition-in-videos-on-kinetics-600","dataset":"Kinetics-600","dataset_url":"/dataset/kinetics-600","rows_in_archive":1,"metrics":["Top-1 Accuracy","Top-5 Accuracy"],"first_row_in_archive_order":{"model":"Florence","paper_title":"Florence: A New Foundation Model for Computer Vision","paper_url":"/paper/florence-a-new-foundation-model-for-computer","paper_date":"2021-11-22","arxiv_id":"2111.11432","code_links":[{"title":"microsoft/unicl","url":"https://github.com/microsoft/unicl"},{"title":"MindCode-4/code-3","url":"https://github.com/MindCode-4/code-3/tree/main/florence2"}],"syntology":null}},{"leaderboard":"/sota/action-recognition-in-videos-on-minisports-1","slug":"action-recognition-in-videos-on-minisports-1","dataset":"miniSports","dataset_url":null,"rows_in_archive":1,"metrics":["Clip Hit@1","Video hit@1","Video hit@5"],"first_row_in_archive_order":{"model":"G-Blend","paper_title":"What Makes Training Multi-Modal Classification Networks Hard?","paper_url":"/paper/what-makes-training-multi-modal-networks-hard","paper_date":"2019-05-29","arxiv_id":"1905.12681","code_links":[{"title":"facebookresearch/R2Plus1D","url":"https://github.com/facebookresearch/R2Plus1D"},{"title":"facebookresearch/VMZ","url":"https://github.com/facebookresearch/VMZ"},{"title":"guide2157/ChulaXrayClassifier","url":"https://github.com/guide2157/ChulaXrayClassifier"}],"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}}},{"leaderboard":"/sota/action-recognition-in-videos-on-ntu-rgb-d","slug":"action-recognition-in-videos-on-ntu-rgb-d","dataset":"NTU RGB+D","dataset_url":"/dataset/ntu-rgb-d","rows_in_archive":1,"metrics":["Accuracy (CS)"],"first_row_in_archive_order":{"model":"2D-3D-Softargmax (RGB only)","paper_title":"2D/3D Pose Estimation and Action Recognition using Multitask Deep Learning","paper_url":"/paper/2d3d-pose-estimation-and-action-recognition","paper_date":"2018-02-26","arxiv_id":"1802.09232","code_links":[{"title":"dluvizon/deephar","url":"https://github.com/dluvizon/deephar"},{"title":"pminhtam/2D-3D_Multitask_Deep_Learning","url":"https://github.com/pminhtam/2D-3D_Multitask_Deep_Learning"}],"syntology":{"n":25,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":20,"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) · 20 unverified","sample_list":"/paper/2d3d-pose-estimation-and-action-recognition#ran","syntology_url":"https://syntology.ai/paper/1802.09232","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.09232"}},"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/ntu-rgb-d","name":"NTU RGB+D","full_name":"","num_papers_in_archive":476},{"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/sports-1m","name":"Sports-1M","full_name":"","num_papers_in_archive":164},{"url":"/dataset/kinetics-600","name":"Kinetics-600","full_name":"","num_papers_in_archive":148},{"url":"/dataset/something-something-v1","name":"Something-Something V1","full_name":"","num_papers_in_archive":117},{"url":"/dataset/ava","name":"AVA","full_name":"Atomic Visual Actions","num_papers_in_archive":113},{"url":"/dataset/pku-mmd","name":"PKU-MMD","full_name":"PKU-MMD","num_papers_in_archive":72},{"url":"/dataset/mtl-aqa","name":"MTL-AQA","full_name":"","num_papers_in_archive":33},{"url":"/dataset/jester-gesture-recognition","name":"Jester (Gesture Recognition)","full_name":"","num_papers_in_archive":16},{"url":"/dataset/cvb-a-video-dataset-of-cattle-visual","name":"CVB","full_name":"Video Dataset of Cattle Visual Behaviors","num_papers_in_archive":2},{"url":"/dataset/win-fail-action-understanding","name":"Win-Fail Action Understanding","full_name":"Win-Fail Action Understanding","num_papers_in_archive":1}],"subtasks":[{"url":"/task/action-anticipation","name":"Action Anticipation"}],"parent_tasks":[{"url":"/task/action-recognition-in-videos","name":"Action Recognition"}],"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":2,"rows_per_page":100,"shown":100,"of":124,"of_with_code":71,"tagged_in_all":124,"counts":{"archive_papers_tagged":124,"with_a_code_link":71,"where_syntology_ran_a_sample":23,"not_listed_spam_title":0,"listed":124,"listed_where_code_ran":23,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":22,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":22,"listed_every_run_a_failure_of_syntologys_instrument":1,"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/learning-spatiotemporal-features-with-3d","slug":"learning-spatiotemporal-features-with-3d","title":"Learning Spatiotemporal Features with 3D Convolutional Networks","date":"2014-12-02","arxiv_id":"1412.0767","repositories_listed":29,"syntology":null},{"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/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-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/youtube-8m-a-large-scale-video-classification","slug":"youtube-8m-a-large-scale-video-classification","title":"YouTube-8M: A Large-Scale Video Classification Benchmark","date":"2016-09-27","arxiv_id":"1609.08675","repositories_listed":7,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/youtube-8m-a-large-scale-video-classification#ran","syntology_url":"https://syntology.ai/paper/1609.08675","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1609.08675"}},"official":null}},{"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/ucf101-a-dataset-of-101-human-actions-classes","slug":"ucf101-a-dataset-of-101-human-actions-classes","title":"UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild","date":"2012-12-03","arxiv_id":"1212.0402","repositories_listed":7,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"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: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ucf101-a-dataset-of-101-human-actions-classes#ran","syntology_url":"https://syntology.ai/paper/1212.0402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1212.0402"}},"official":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/you-only-watch-once-a-unified-cnn","slug":"you-only-watch-once-a-unified-cnn","title":"You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization","date":"2019-11-15","arxiv_id":"1911.06644","repositories_listed":5,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":5,"n_honours":1,"n_violates":2,"n_no_contract":4,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 2 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/you-only-watch-once-a-unified-cnn#ran","syntology_url":"https://syntology.ai/paper/1911.06644","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.06644"}},"official":{"repos":["wei-tim/YOWO"],"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/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/towards-good-practices-for-very-deep-two","slug":"towards-good-practices-for-very-deep-two","title":"Towards Good Practices for Very Deep Two-Stream ConvNets","date":"2015-07-08","arxiv_id":"1507.02159","repositories_listed":5,"syntology":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/simba-mamba-augmented-u-shiftgcn-for-skeletal","slug":"simba-mamba-augmented-u-shiftgcn-for-skeletal","title":"Simba: Mamba augmented U-ShiftGCN for Skeletal Action Recognition in Videos","date":"2024-04-11","arxiv_id":"2404.07645","repositories_listed":3,"syntology":null},{"url":"/paper/gating-revisited-deep-multi-layer-rnns-that-1","slug":"gating-revisited-deep-multi-layer-rnns-that-1","title":"Gating Revisited: Deep Multi-layer RNNs That Can Be Trained","date":"2019-11-25","arxiv_id":"1911.11033","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/r-c3d-region-convolutional-3d-network-for","slug":"r-c3d-region-convolutional-3d-network-for","title":"R-C3D: Region Convolutional 3D Network for Temporal Activity Detection","date":"2017-03-22","arxiv_id":"1703.07814","repositories_listed":3,"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/r-c3d-region-convolutional-3d-network-for#ran","syntology_url":"https://syntology.ai/paper/1703.07814","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.07814"}},"official":{"repos":["VisionLearningGroup/R-C3D"],"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/video-action-recognition-collaborative","slug":"video-action-recognition-collaborative","title":"Video Action Recognition Collaborative Learning with Dynamics via PSO-ConvNet Transformer","date":"2023-02-17","arxiv_id":"2302.09187","repositories_listed":2,"syntology":null},{"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/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/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/self-supervised-video-representation-learning-3","slug":"self-supervised-video-representation-learning-3","title":"Self-supervised Video Representation Learning Using Inter-intra Contrastive Framework","date":"2020-08-06","arxiv_id":"2008.02531","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/self-supervised-video-representation-learning-3#ran","syntology_url":"https://syntology.ai/paper/2008.02531","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.02531"}},"official":{"repos":["BestJuly/Inter-intra-video-contrastive-learning"],"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/integralaction-pose-driven-feature","slug":"integralaction-pose-driven-feature","title":"IntegralAction: Pose-driven Feature Integration for Robust Human Action Recognition in Videos","date":"2020-07-13","arxiv_id":"2007.06317","repositories_listed":2,"syntology":null},{"url":"/paper/learning-video-representations-from","slug":"learning-video-representations-from","title":"Learning Video Representations from Correspondence Proposals","date":"2019-05-20","arxiv_id":"1905.07853","repositories_listed":2,"syntology":null},{"url":"/paper/resource-efficient-3d-convolutional-neural","slug":"resource-efficient-3d-convolutional-neural","title":"Resource Efficient 3D Convolutional Neural Networks","date":"2019-04-04","arxiv_id":"1904.02422","repositories_listed":2,"syntology":null},{"url":"/paper/2d3d-pose-estimation-and-action-recognition","slug":"2d3d-pose-estimation-and-action-recognition","title":"2D/3D Pose Estimation and Action Recognition using Multitask Deep Learning","date":"2018-02-26","arxiv_id":"1802.09232","repositories_listed":2,"syntology":{"n":25,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":20,"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) · 20 unverified","sample_list":"/paper/2d3d-pose-estimation-and-action-recognition#ran","syntology_url":"https://syntology.ai/paper/1802.09232","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.09232"}},"official":null}},{"url":"/paper/convolutional-two-stream-network-fusion-for","slug":"convolutional-two-stream-network-fusion-for","title":"Convolutional Two-Stream Network Fusion for Video Action Recognition","date":"2016-04-22","arxiv_id":"1604.06573","repositories_listed":2,"syntology":null},{"url":"/paper/action-recognition-using-visual-attention","slug":"action-recognition-using-visual-attention","title":"Action Recognition using Visual Attention","date":"2015-11-12","arxiv_id":"1511.04119","repositories_listed":2,"syntology":null},{"url":"/paper/body-hand-modality-expertized-networks-with","slug":"body-hand-modality-expertized-networks-with","title":"Body-Hand Modality Expertized Networks with Cross-attention for Fine-grained Skeleton Action Recognition","date":"2025-03-19","arxiv_id":"2503.14960","repositories_listed":1,"syntology":null},{"url":"/paper/epam-net-an-efficient-pose-driven-attention","slug":"epam-net-an-efficient-pose-driven-attention","title":"EPAM-Net: An Efficient Pose-driven Attention-guided Multimodal Network for Video Action Recognition","date":"2024-08-10","arxiv_id":"2408.05421","repositories_listed":1,"syntology":null},{"url":"/paper/actnetformer-transformer-resnet-hybrid-method","slug":"actnetformer-transformer-resnet-hybrid-method","title":"ActNetFormer: Transformer-ResNet Hybrid Method for Semi-Supervised Action Recognition in Videos","date":"2024-04-09","arxiv_id":"2404.06243","repositories_listed":1,"syntology":null},{"url":"/paper/haltingvt-adaptive-token-halting-transformer","slug":"haltingvt-adaptive-token-halting-transformer","title":"HaltingVT: Adaptive Token Halting Transformer for Efficient Video Recognition","date":"2024-01-10","arxiv_id":"2401.04975","repositories_listed":1,"syntology":null},{"url":"/paper/a-dense-sparse-complementary-network-for","slug":"a-dense-sparse-complementary-network-for","title":"A Dense-Sparse Complementary Network for Human Action Recognition based on RGB and Skeleton Modalities","date":"2023-12-28","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/dvanet-disentangling-view-and-action-features","slug":"dvanet-disentangling-view-and-action-features","title":"DVANet: Disentangling View and Action Features for Multi-View Action Recognition","date":"2023-12-10","arxiv_id":"2312.05719","repositories_listed":1,"syntology":null},{"url":"/paper/cast-cross-attention-in-space-and-time-for-1","slug":"cast-cross-attention-in-space-and-time-for-1","title":"CAST: Cross-Attention in Space and Time for Video Action Recognition","date":"2023-11-30","arxiv_id":"2311.18825","repositories_listed":1,"syntology":{"n":17,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":6,"n_honours":2,"n_violates":0,"n_no_contract":9,"n_pointer_only":17,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 2 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/cast-cross-attention-in-space-and-time-for-1#ran","syntology_url":"https://syntology.ai/paper/2311.18825","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.18825"}},"official":null}},{"url":"/paper/msqnet-actor-agnostic-action-recognition-with","slug":"msqnet-actor-agnostic-action-recognition-with","title":"Actor-agnostic Multi-label Action Recognition with Multi-modal Query","date":"2023-07-20","arxiv_id":"2307.10763","repositories_listed":1,"syntology":null},{"url":"/paper/videomae-v2-scaling-video-masked-autoencoders","slug":"videomae-v2-scaling-video-masked-autoencoders","title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking","date":"2023-03-29","arxiv_id":"2303.16727","repositories_listed":1,"syntology":{"n":6,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"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) · 4 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/videomae-v2-scaling-video-masked-autoencoders#ran","syntology_url":"https://syntology.ai/paper/2303.16727","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.16727"}},"official":{"repos":["OpenGVLab/VideoMAEv2"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/dual-path-adaptation-from-image-to-video","slug":"dual-path-adaptation-from-image-to-video","title":"Dual-path Adaptation from Image to Video Transformers","date":"2023-03-17","arxiv_id":"2303.09857","repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-video-vits-sparse-video-tubes-for","slug":"rethinking-video-vits-sparse-video-tubes-for","title":"Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning","date":"2022-12-06","arxiv_id":"2212.03229","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"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) · 0 unverified","sample_list":"/paper/rethinking-video-vits-sparse-video-tubes-for#ran","syntology_url":"https://syntology.ai/paper/2212.03229","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.03229"}},"official":null}},{"url":"/paper/exploring-modulated-detection-transformer-as","slug":"exploring-modulated-detection-transformer-as","title":"Exploring Modulated Detection Transformer as a Tool for Action Recognition in Videos","date":"2022-09-21","arxiv_id":"2209.10126","repositories_listed":1,"syntology":null},{"url":"/paper/mmnet-a-model-based-multimodal-network-for","slug":"mmnet-a-model-based-multimodal-network-for","title":"MMNet: A Model-Based Multimodal Network for Human Action Recognition in RGB-D Videos","date":"2022-05-26","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/direcformer-a-directed-attention-in","slug":"direcformer-a-directed-attention-in","title":"DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition","date":"2022-03-19","arxiv_id":"2203.10233","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":8,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/direcformer-a-directed-attention-in#ran","syntology_url":"https://syntology.ai/paper/2203.10233","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.10233"}},"official":{"repos":["uark-cviu/direcformer"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/a-new-face-swap-method-for-image-and-video","slug":"a-new-face-swap-method-for-image-and-video","title":"A new face swap method for image and video domains: a technical report","date":"2022-02-07","arxiv_id":"2202.03046","repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-video-transformer","slug":"self-supervised-video-transformer","title":"Self-supervised Video Transformer","date":"2021-12-02","arxiv_id":"2112.01514","repositories_listed":1,"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/self-supervised-video-transformer#ran","syntology_url":"https://syntology.ai/paper/2112.01514","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.01514"}},"official":{"repos":["kahnchana/svt"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/logsig-rnn-a-novel-network-for-robust-and","slug":"logsig-rnn-a-novel-network-for-robust-and","title":"Logsig-RNN: a novel network for robust and efficient skeleton-based action recognition","date":"2021-10-25","arxiv_id":"2110.13008","repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-video-representation-learning-7","slug":"self-supervised-video-representation-learning-7","title":"Self-supervised Video Representation Learning with Cross-Stream Prototypical Contrasting","date":"2021-06-18","arxiv_id":"2106.10137","repositories_listed":1,"syntology":null},{"url":"/paper/space-time-mixing-attention-for-video","slug":"space-time-mixing-attention-for-video","title":"Space-time Mixing Attention for Video Transformer","date":"2021-06-10","arxiv_id":"2106.05968","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/space-time-mixing-attention-for-video#ran","syntology_url":"https://syntology.ai/paper/2106.05968","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.05968"}},"official":{"repos":["1adrianb/video-transformers"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/multimodal-fusion-via-teacher-student-network","slug":"multimodal-fusion-via-teacher-student-network","title":"Multimodal Fusion via Teacher-Student Network for Indoor Action Recognition","date":"2021-05-18","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/learning-implicit-temporal-alignment-for-few","slug":"learning-implicit-temporal-alignment-for-few","title":"Learning Implicit Temporal Alignment for Few-shot Video Classification","date":"2021-05-11","arxiv_id":"2105.04823","repositories_listed":1,"syntology":null},{"url":"/paper/video-transformer-network","slug":"video-transformer-network","title":"Video Transformer Network","date":"2021-02-01","arxiv_id":"2102.00719","repositories_listed":1,"syntology":null},{"url":"/paper/tensor-representations-for-action-recognition","slug":"tensor-representations-for-action-recognition","title":"Tensor Representations for Action Recognition","date":"2020-12-28","arxiv_id":"2012.14371","repositories_listed":1,"syntology":null},{"url":"/paper/tdn-temporal-difference-networks-for","slug":"tdn-temporal-difference-networks-for","title":"TDN: Temporal Difference Networks for Efficient Action Recognition","date":"2020-12-18","arxiv_id":"2012.10071","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/tdn-temporal-difference-networks-for#ran","syntology_url":"https://syntology.ai/paper/2012.10071","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.10071"}},"official":{"repos":["MCG-NJU/TDN"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-improving-spatiotemporal-action","slug":"towards-improving-spatiotemporal-action","title":"Towards Improving Spatiotemporal Action Recognition in Videos","date":"2020-12-15","arxiv_id":"2012.08097","repositories_listed":1,"syntology":null},{"url":"/paper/right-on-time-multi-temporal-convolutions-for","slug":"right-on-time-multi-temporal-convolutions-for","title":"Multi-Temporal Convolutions for Human Action Recognition in Videos","date":"2020-11-08","arxiv_id":"2011.03949","repositories_listed":1,"syntology":null},{"url":"/paper/pose-and-joint-aware-action-recognition","slug":"pose-and-joint-aware-action-recognition","title":"Pose And Joint-Aware Action Recognition","date":"2020-10-16","arxiv_id":"2010.08164","repositories_listed":1,"syntology":null},{"url":"/paper/spatial-temporal-transformer-network-for","slug":"spatial-temporal-transformer-network-for","title":"Skeleton-based Action Recognition via Spatial and Temporal Transformer Networks","date":"2020-08-17","arxiv_id":"2008.07404","repositories_listed":1,"syntology":null},{"url":"/paper/region-based-non-local-operation-for-video","slug":"region-based-non-local-operation-for-video","title":"Region-based Non-local Operation for Video Classification","date":"2020-07-17","arxiv_id":"2007.09033","repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-multimodal-versatile-networks","slug":"self-supervised-multimodal-versatile-networks","title":"Self-Supervised MultiModal Versatile Networks","date":"2020-06-29","arxiv_id":"2006.16228","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-learning-of-video-1","slug":"unsupervised-learning-of-video-1","title":"Unsupervised Learning of Video Representations via Dense Trajectory Clustering","date":"2020-06-28","arxiv_id":"2006.15731","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/unsupervised-learning-of-video-1#ran","syntology_url":"https://syntology.ai/paper/2006.15731","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.15731"}},"official":{"repos":["pvtokmakov/video_cluster"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learn-to-cycle-time-consistent-feature","slug":"learn-to-cycle-time-consistent-feature","title":"Learn to cycle: Time-consistent feature discovery for action recognition","date":"2020-06-15","arxiv_id":"2006.08247","repositories_listed":1,"syntology":null},{"url":"/paper/tea-temporal-excitation-and-aggregation-for","slug":"tea-temporal-excitation-and-aggregation-for","title":"TEA: Temporal Excitation and Aggregation for Action Recognition","date":"2020-04-03","arxiv_id":"2004.01398","repositories_listed":1,"syntology":null},{"url":"/paper/mmtm-multimodal-transfer-module-for-cnn","slug":"mmtm-multimodal-transfer-module-for-cnn","title":"MMTM: Multimodal Transfer Module for CNN Fusion","date":"2019-11-20","arxiv_id":"1911.08670","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/mmtm-multimodal-transfer-module-for-cnn#ran","syntology_url":"https://syntology.ai/paper/1911.08670","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.08670"}},"official":null}},{"url":"/paper/collaborative-spatiotemporal-feature-learning","slug":"collaborative-spatiotemporal-feature-learning","title":"Collaborative Spatiotemporal Feature Learning for Video Action Recognition","date":"2019-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/out-of-distribution-detection-for-generalized","slug":"out-of-distribution-detection-for-generalized","title":"Out-of-Distribution Detection for Generalized Zero-Shot Action Recognition","date":"2019-04-18","arxiv_id":"1904.08703","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"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) · 0 unverified","sample_list":"/paper/out-of-distribution-detection-for-generalized#ran","syntology_url":"https://syntology.ai/paper/1904.08703","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.08703"}},"official":{"repos":["naraysa/gzsl-od"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/robust-real-time-violence-detection-in-video","slug":"robust-real-time-violence-detection-in-video","title":"Robust Real-Time Violence Detection in Video Using CNN And LSTM","date":"2019-03-27","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/collaborative-spatio-temporal-feature","slug":"collaborative-spatio-temporal-feature","title":"Collaborative Spatio-temporal Feature Learning for Video Action Recognition","date":"2019-03-04","arxiv_id":"1903.01197","repositories_listed":1,"syntology":null},{"url":"/paper/optical-flow-guided-feature-a-fast-and-robust","slug":"optical-flow-guided-feature-a-fast-and-robust","title":"Optical Flow Guided Feature: A Fast and Robust Motion Representation for Video Action Recognition","date":"2017-11-29","arxiv_id":"1711.11152","repositories_listed":1,"syntology":null},{"url":"/paper/rpan-an-end-to-end-recurrent-pose-attention-1","slug":"rpan-an-end-to-end-recurrent-pose-attention-1","title":"RPAN: An End-to-End Recurrent Pose-Attention Network for Action Recognition in Videos","date":"2017-10-22","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/two-stream-flow-guided-convolutional","slug":"two-stream-flow-guided-convolutional","title":"Two-stream Flow-guided Convolutional Attention Networks for Action Recognition","date":"2017-08-30","arxiv_id":"1708.09268","repositories_listed":1,"syntology":null},{"url":"/paper/spatiotemporal-residual-networks-for-video","slug":"spatiotemporal-residual-networks-for-video","title":"Spatiotemporal Residual Networks for Video Action Recognition","date":"2016-11-07","arxiv_id":"1611.02155","repositories_listed":1,"syntology":null},{"url":"/paper/learning-latent-sub-events-in-activity-videos","slug":"learning-latent-sub-events-in-activity-videos","title":"Learning Latent Sub-events in Activity Videos Using Temporal Attention Filters","date":"2016-05-26","arxiv_id":"1605.08140","repositories_listed":1,"syntology":null},{"url":null,"slug":"the-impact-of-compositionality-in-zero-shot","title":"The impact of Compositionality in Zero-shot Multi-label action recognition for Object-based tasks","date":"2024-05-14","arxiv_id":"2405.08695","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-approaches-for-human-action","title":"Deep Learning Approaches for Human Action Recognition in Video Data","date":"2024-03-11","arxiv_id":"2403.06810","repositories_listed":0,"syntology":null},{"url":null,"slug":"action-class-relation-detection-and","title":"Action Class Relation Detection and Classification Across Multiple Video Datasets","date":"2023-08-15","arxiv_id":"2308.07558","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-prompting-for-few-shot-action","title":"Knowledge Prompting for Few-shot Action Recognition","date":"2022-11-22","arxiv_id":"2211.12030","repositories_listed":0,"syntology":null},{"url":"/paper/could-giant-pretrained-image-models-extract","slug":"could-giant-pretrained-image-models-extract","title":"Could Giant Pretrained Image Models Extract Universal Representations?","date":"2022-11-03","arxiv_id":"2211.02043","repositories_listed":0,"syntology":null},{"url":"/paper/class-incremental-learning-for-action-1","slug":"class-incremental-learning-for-action-1","title":"Class-Incremental Learning for Action Recognition in Videos","date":"2022-03-25","arxiv_id":"2203.13611","repositories_listed":0,"syntology":{"n":11,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":5,"n_honours":1,"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; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/class-incremental-learning-for-action-1#ran","syntology_url":"https://syntology.ai/paper/2203.13611","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.13611"}},"official":null}},{"url":"/paper/co-training-transformer-with-videos-and","slug":"co-training-transformer-with-videos-and","title":"Co-training Transformer with Videos and Images Improves Action Recognition","date":"2021-12-14","arxiv_id":"2112.07175","repositories_listed":0,"syntology":null},{"url":null,"slug":"technical-report-disentangled-action-parsing","title":"Technical Report: Disentangled Action Parsing Networks for Accurate Part-level Action Parsing","date":"2021-11-05","arxiv_id":"2111.03225","repositories_listed":0,"syntology":null},{"url":null,"slug":"class-incremental-learning-for-video-action","title":"Class incremental learning for video action classification","date":"2021-09-19","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"nas-tc-neural-architecture-search-on-temporal","title":"NAS-TC: Neural Architecture Search on Temporal Convolutions for Complex Action Recognition","date":"2021-03-17","arxiv_id":"2104.01110","repositories_listed":0,"syntology":null},{"url":null,"slug":"temporal-difference-networks-for-action","title":"Temporal Difference Networks for Action Recognition","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"developing-motion-code-embedding-for-action","title":"Developing Motion Code Embedding for Action Recognition in Videos","date":"2020-12-10","arxiv_id":"2012.05438","repositories_listed":0,"syntology":null},{"url":null,"slug":"toward-accurate-person-level-action","title":"Toward Accurate Person-level Action Recognition in Videos of Crowded Scenes","date":"2020-10-16","arxiv_id":"2010.08365","repositories_listed":0,"syntology":null},{"url":"/paper/towards-efficient-coarse-to-fine-networks-for","slug":"towards-efficient-coarse-to-fine-networks-for","title":"Towards Efficient Coarse-to-Fine Networks for Action and Gesture Recognition","date":"2020-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/dynamic-sampling-networks-for-efficient","slug":"dynamic-sampling-networks-for-efficient","title":"Dynamic Sampling Networks for Efficient Action Recognition in Videos","date":"2020-06-28","arxiv_id":"2006.15560","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatiotemporal-fusion-in-3d-cnns-a","title":"Spatiotemporal Fusion in 3D CNNs: A Probabilistic View","date":"2020-04-10","arxiv_id":"2004.04981","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-inference-a-new-approach-toward","title":"Dynamic Inference: A New Approach Toward Efficient Video Action Recognition","date":"2020-02-09","arxiv_id":"2002.03342","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-information-rich-sampling-technique-over","title":"An Information-rich Sampling Technique over Spatio-Temporal CNN for Classification of Human Actions in Videos","date":"2020-02-06","arxiv_id":"2002.02100","repositories_listed":0,"syntology":null},{"url":null,"slug":"skeleton-based-activity-recognition-by-fusing","title":"Skeleton based Activity Recognition by Fusing Part-wise Spatio-temporal and Attention Driven Residues","date":"2019-12-02","arxiv_id":"1912.00576","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-image-to-video-adaptation-and-fusion","title":"Deep Image-to-Video Adaptation and Fusion Networks for Action Recognition","date":"2019-11-25","arxiv_id":"1911.10751","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-action-recognition-in-videos-a","title":"Zero-Shot Action Recognition in Videos: A Survey","date":"2019-09-13","arxiv_id":"1909.06423","repositories_listed":0,"syntology":null},{"url":null,"slug":"discriminative-video-representation-learning","title":"Discriminative Video Representation Learning Using Support Vector Classifiers","date":"2019-09-05","arxiv_id":"1909.02856","repositories_listed":0,"syntology":null},{"url":"/paper/stm-spatiotemporal-and-motion-encoding-for","slug":"stm-spatiotemporal-and-motion-encoding-for","title":"STM: SpatioTemporal and Motion Encoding for Action Recognition","date":"2019-08-07","arxiv_id":"1908.02486","repositories_listed":0,"syntology":null},{"url":null,"slug":"where-and-when-to-look-spatial-temporal","title":"Where and when to look? Spatial-temporal attention for action recognition in videos","date":"2019-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-transferable-self-attentive","title":"Learning Transferable Self-attentive Representations for Action Recognition in Untrimmed Videos with Weak Supervision","date":"2019-02-20","arxiv_id":"1902.07370","repositories_listed":0,"syntology":null},{"url":"/paper/dmc-net-generating-discriminative-motion-cues","slug":"dmc-net-generating-discriminative-motion-cues","title":"DMC-Net: Generating Discriminative Motion Cues for Fast Compressed Video Action Recognition","date":"2019-01-11","arxiv_id":"1901.03460","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-recognize-3d-human-action-from-a","title":"Learning to Recognize 3D Human Action from A New Skeleton-based Representation Using Deep Convolutional Neural Networks","date":"2018-12-26","arxiv_id":"1812.10550","repositories_listed":0,"syntology":null},{"url":null,"slug":"coupled-recurrent-network-crn","title":"Coupled Recurrent Network (CRN)","date":"2018-12-25","arxiv_id":"1812.10071","repositories_listed":0,"syntology":null},{"url":"/paper/evolving-space-time-neural-architectures-for","slug":"evolving-space-time-neural-architectures-for","title":"Evolving Space-Time Neural Architectures for Videos","date":"2018-11-26","arxiv_id":"1811.10636","repositories_listed":0,"syntology":null}],"syntology_records":25,"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-recognition-in-videos-on-pku-mmd","since_archive":"/sota/action-recognition-in-videos-on-pku-mmd#since-judged","papers_judged":1,"placed":0}]},"papers_where_code_ran":23,"papers_where_code_ran_first_page":"/task/action-recognition-in-videos-2/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":2,"url":"/task/action-recognition-in-videos-2/papers/2","json":"/task/action-recognition-in-videos-2/papers/2.json","rows":24},{"order":"ran","page":1,"of":1,"url":"/task/action-recognition-in-videos-2/papers/ran/1","json":"/task/action-recognition-in-videos-2/papers/ran/1.json","rows":23}],"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":"603348fe5c904527ccfacac8d1f4b99d001b55fd596ad91d59b8861bf1dd56bb","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}