{"url":"/task/activity-recognition-in-videos","name":"Activity Recognition In Videos","slug":"activity-recognition-in-videos","description_markdown":null,"categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Time Series","url":"/area/time-series"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":18,"papers_with_code":10,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"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":2,"subtasks":1,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/activity-recognition-in-videos-on-dogcentric","slug":"activity-recognition-in-videos-on-dogcentric","dataset":"DogCentric","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"VTFSA","paper_title":"Learning Latent Sub-events in Activity Videos Using Temporal Attention Filters","paper_url":"/paper/learning-latent-sub-events-in-activity-videos","paper_date":"2016-05-26","arxiv_id":"1605.08140","code_links":[{"title":"piergiaj/latent-subevents","url":"https://github.com/piergiaj/latent-subevents"}],"syntology":null}}],"datasets":[{"url":"/dataset/dahlia-daily-human-life-activity","name":"DAHLIA","full_name":"DAily Human Life Activity","num_papers_in_archive":0},{"url":"/dataset/infiniterep","name":"InfiniteRep","full_name":"InfiniteRep","num_papers_in_archive":0}],"subtasks":[{"url":"/task/activity-prediction","name":"Activity Prediction"}],"parent_tasks":[{"url":"/task/action-recognition","name":"Temporal Action Localization"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":10,"of":10,"tagged_in_all":18,"items":[{"url":"/paper/very-deep-convolutional-networks-for-large","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","date":"2014-09-04","arxiv_id":"1409.1556","repositories_listed":305,"syntology":{"n":122,"n_ran":12,"n_unverified":110,"n_pointer_only":4}},{"url":"/paper/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/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":0,"n_unverified":21,"n_pointer_only":0}},{"url":"/paper/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/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/tormentor-deterministic-dynamic-path-data","title":"TorMentor: Deterministic dynamic-path, data augmentations with fractals","date":"2022-04-07","arxiv_id":"2204.03776","repositories_listed":1,"syntology":null},{"url":"/paper/convolutional-spiking-neural-networks-for","title":"Convolutional Spiking Neural Networks for Spatio-Temporal Feature Extraction","date":"2020-03-27","arxiv_id":"2003.12346","repositories_listed":1,"syntology":null},{"url":"/paper/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":"/paper/action-recognition-with-trajectory-pooled","title":"Action Recognition with Trajectory-Pooled Deep-Convolutional Descriptors","date":"2015-05-19","arxiv_id":"1505.04868","repositories_listed":1,"syntology":null},{"url":"/paper/pooled-motion-features-for-first-person","title":"Pooled Motion Features for First-Person Videos","date":"2014-12-19","arxiv_id":"1412.6505","repositories_listed":1,"syntology":null}],"syntology_records":2,"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"},"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":"2026-09-24T18:15:14+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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"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"}}