{"url":"/task/egocentric-activity-recognition","name":"Egocentric Activity Recognition","slug":"egocentric-activity-recognition","description_markdown":null,"categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Robots","url":"/area/robots"},{"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":26,"papers_with_code":14,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"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":4,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/egocentric-activity-recognition-on-epic-1","slug":"egocentric-activity-recognition-on-epic-1","dataset":"EPIC-KITCHENS-55","dataset_url":"/dataset/epic-kitchens","rows_in_archive":7,"metrics":["Actions Top-1 (S1)","Actions Top-1 (S2)"],"first_row_in_archive_order":{"model":"DEEP-HAL with ODF+SDF (AssembleNet++)","paper_title":"Self-supervising Action Recognition by Statistical Moment and Subspace Descriptors","paper_url":"/paper/hallucinating-statistical-moment-and-subspace","paper_date":"2020-01-14","arxiv_id":"2001.04627","code_links":[],"syntology":null}},{"leaderboard":"/sota/egocentric-activity-recognition-on-egtea-1","slug":"egocentric-activity-recognition-on-egtea-1","dataset":"EGTEA","dataset_url":"/dataset/egtea","rows_in_archive":6,"metrics":["Average Accuracy","Mean class accuracy"],"first_row_in_archive_order":{"model":"LaViLa (Finetuned, TimeSformer-L)","paper_title":"Learning Video Representations from Large Language Models","paper_url":"/paper/learning-video-representations-from-large","paper_date":"2022-12-08","arxiv_id":"2212.04501","code_links":[{"title":"facebookresearch/lavila","url":"https://github.com/facebookresearch/lavila"},{"title":"Ziyang412/VideoTree","url":"https://github.com/Ziyang412/VideoTree"},{"title":"ceezh/llovi","url":"https://github.com/ceezh/llovi"}],"syntology":{"n":20,"n_ran":6,"n_unverified":14,"n_pointer_only":20}}}],"datasets":[{"url":"/dataset/egtea","name":"EGTEA","full_name":"EGTEA Gaze+","num_papers_in_archive":100},{"url":"/dataset/epic-kitchens","name":"EPIC-KITCHENS-55","full_name":"","num_papers_in_archive":42},{"url":"/dataset/decade","name":"DECADE","full_name":"","num_papers_in_archive":3},{"url":"/dataset/egok360","name":"EGOK360","full_name":"","num_papers_in_archive":2}],"subtasks":[],"parent_tasks":[{"url":"/task/activity-recognition","name":"Activity Recognition"}],"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":14,"of":14,"tagged_in_all":26,"items":[{"url":"/paper/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":0,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/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":6,"n_unverified":14,"n_pointer_only":20}},{"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/what-would-you-expect-anticipating-egocentric","title":"What Would You Expect? Anticipating Egocentric Actions with Rolling-Unrolling LSTMs and Modality Attention","date":"2019-05-22","arxiv_id":"1905.09035","repositories_listed":2,"syntology":null},{"url":"/paper/wear-a-multimodal-dataset-for-wearable-and","title":"WEAR: An Outdoor Sports Dataset for Wearable and Egocentric Activity Recognition","date":"2023-04-11","arxiv_id":"2304.05088","repositories_listed":1,"syntology":null},{"url":"/paper/towards-continual-egocentric-activity","title":"Towards Continual Egocentric Activity Recognition: A Multi-modal Egocentric Activity Dataset for Continual Learning","date":"2023-01-26","arxiv_id":"2301.10931","repositories_listed":1,"syntology":null},{"url":"/paper/group-contextualization-for-video-recognition","title":"Group Contextualization for Video Recognition","date":"2022-03-18","arxiv_id":"2203.09694","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/ego-exo-transferring-visual-representations","title":"Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos","date":"2021-04-16","arxiv_id":"2104.07905","repositories_listed":1,"syntology":null},{"url":"/paper/integrating-human-gaze-into-attention-for","title":"Integrating Human Gaze into Attention for Egocentric Activity Recognition","date":"2020-11-08","arxiv_id":"2011.03920","repositories_listed":1,"syntology":null},{"url":"/paper/epic-fusion-audio-visual-temporal-binding-for","title":"EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition","date":"2019-08-22","arxiv_id":"1908.08498","repositories_listed":1,"syntology":null},{"url":"/paper/lsta-long-short-term-attention-for-egocentric","title":"LSTA: Long Short-Term Attention for Egocentric Action Recognition","date":"2018-11-26","arxiv_id":"1811.10698","repositories_listed":1,"syntology":null},{"url":"/paper/attention-is-all-we-need-nailing-down-object","title":"Attention is All We Need: Nailing Down Object-centric Attention for Egocentric Activity Recognition","date":"2018-07-31","arxiv_id":"1807.11794","repositories_listed":1,"syntology":null},{"url":"/paper/a-correlation-based-feature-representation","title":"A Correlation Based Feature Representation for First-Person Activity Recognition","date":"2017-11-15","arxiv_id":"1711.05523","repositories_listed":1,"syntology":null},{"url":"/paper/first-person-hand-action-benchmark-with-rgb-d","title":"First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations","date":"2017-04-08","arxiv_id":"1704.02463","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}}],"syntology_records":5,"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"}}