{"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":"/dataset/epic-kitchens","name":"EPIC-KITCHENS-55","full_name":null,"description_markdown":"The EPIC-KITCHENS-55 dataset comprises a set of 432 egocentric videos recorded by 32 participants in their kitchens at 60fps with a head mounted camera. There is no guiding script for the participants who freely perform activities in kitchens related to cooking, food preparation or washing up among others. Each video is split into short action segments (mean duration is 3.7s) with specific start and end times and a verb and noun annotation describing the action (e.g. ‘open fridge‘). The verb classes are 125 and the noun classes 331. The dataset is divided into one train and two test splits.\r\n\r\nSource: [Egocentric Hand Track and Object-based Human Action Recognition](https://arxiv.org/abs/1905.00742)\r\nImage Source: [https://epic-kitchens.github.io/2020-100](https://epic-kitchens.github.io/2020-100)","description_withheld":null,"homepage":"https://epic-kitchens.github.io/2019","introduced_date":"2018-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/scaling-egocentric-vision-the-epic-kitchens","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","first_author":"Dima Damen","url":null},"license":null,"modalities":[{"name":"Videos","url":"/datasets/modality/videos"}],"tasks":[{"name":"Action Recognition","url":"/task/action-recognition-in-videos","datasets_with_task":"/datasets/task/action-recognition-in-videos"},{"name":"Video Understanding","url":"/task/video-understanding","datasets_with_task":"/datasets/task/video-understanding"},{"name":"Video Object Detection","url":"/task/video-object-detection","datasets_with_task":"/datasets/task/video-object-detection"},{"name":"Egocentric Activity Recognition","url":"/task/egocentric-activity-recognition","datasets_with_task":"/datasets/task/egocentric-activity-recognition"}],"languages":[],"variants":["EPIC-KITCHENS-55"],"data_loaders":[],"num_papers_in_archive":42,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/egocentric-activity-recognition-on-epic-1","task":"Egocentric Activity Recognition","dataset_variant":"EPIC-KITCHENS-55","rows":7,"metrics":["Actions Top-1 (S1)","Actions Top-1 (S2)"],"first_row_in_archive_order":{"model":"DEEP-HAL with ODF+SDF (AssembleNet++)","paper":"/paper/hallucinating-statistical-moment-and-subspace","metrics":{"Actions Top-1 (S1)":"35.8","Actions Top-1 (S2)":"27.3"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/action-recognition-in-videos-on-epic-kitchens","task":"Action Recognition","dataset_variant":"EPIC-KITCHENS-55","rows":1,"metrics":["Top-1 Accuracy"],"first_row_in_archive_order":{"model":"TSM+W3 - full res","paper":"/paper/knowing-what-where-and-when-to-look-efficient","metrics":{"Top-1 Accuracy":"34.2"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/video-object-detection-on-epic-kitchens-55","task":"Video Object Detection","dataset_variant":"EPIC-KITCHENS-55","rows":1,"metrics":["mAP@.5"],"first_row_in_archive_order":{"model":"Ours (Faster RCNN)","paper":"/paper/objects-do-not-disappear-video-object","metrics":{"mAP@.5":"41.7"},"code_links":[{"title":"l-kid/video-object-detection-by-location-anticipation","url":"https://github.com/l-kid/video-object-detection-by-location-anticipation"},{"title":"Elstuhn/Video-object-detection-by-location-anticipation","url":"https://github.com/Elstuhn/Video-object-detection-by-location-anticipation"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":8,"of":8,"counts":{"papers_with_a_benchmark_row":8,"with_a_code_link":6,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":8,"listed_where_code_ran":2,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":2,"listed_every_run_a_failure_of_syntologys_instrument":0,"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 with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/objects-do-not-disappear-video-object","slug":"objects-do-not-disappear-video-object","title":"Objects do not disappear: Video object detection by single-frame object location anticipation","date":"2023-08-09","arxiv_id":"2308.04770","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/knowing-what-where-and-when-to-look-efficient","slug":"knowing-what-where-and-when-to-look-efficient","title":"Knowing What, Where and When to Look: Efficient Video Action Modeling with Attention","date":"2020-04-02","arxiv_id":"2004.01278","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/hallucinating-statistical-moment-and-subspace","slug":"hallucinating-statistical-moment-and-subspace","title":"Self-supervising Action Recognition by Statistical Moment and Subspace Descriptors","date":"2020-01-14","arxiv_id":"2001.04627","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/epic-fusion-audio-visual-temporal-binding-for","slug":"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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/what-would-you-expect-anticipating-egocentric","slug":"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","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":21,"samples_ran":12,"samples_constructed":0,"samples_ran_checked":12,"samples_ran_instrument_failed":0,"samples_unverified":9,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/lsta-long-short-term-attention-for-egocentric","slug":"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","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/objects-do-not-disappear-video-object","slug":"objects-do-not-disappear-video-object","title":"Objects do not disappear: Video object detection by single-frame object location anticipation","date":"2023-08-09","arxiv_id":"2308.04770","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/knowing-what-where-and-when-to-look-efficient","slug":"knowing-what-where-and-when-to-look-efficient","title":"Knowing What, Where and When to Look: Efficient Video Action Modeling with Attention","date":"2020-04-02","arxiv_id":"2004.01278","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/hallucinating-statistical-moment-and-subspace","slug":"hallucinating-statistical-moment-and-subspace","title":"Self-supervising Action Recognition by Statistical Moment and Subspace Descriptors","date":"2020-01-14","arxiv_id":"2001.04627","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/epic-fusion-audio-visual-temporal-binding-for","slug":"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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/what-would-you-expect-anticipating-egocentric","slug":"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","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":21,"samples_ran":12,"samples_constructed":0,"samples_ran_checked":12,"samples_ran_instrument_failed":0,"samples_unverified":9,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/lsta-long-short-term-attention-for-egocentric","slug":"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","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"papers_where_code_ran":2,"papers_where_code_ran_first_page":"/dataset/epic-kitchens/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/epic-kitchens/papers/ran/1","json":"/dataset/epic-kitchens/papers/ran/1.json","rows":2}],"row_route":"each paper's syntology object 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","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":2,"samples_harvested":29,"samples_ran":20,"samples_constructed":0,"samples_ran_checked":20,"samples_ran_instrument_failed":0,"samples_unverified":9,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":2,"papers_with_a_run_with_no_instrument_failure":2,"papers_where_every_run_was_an_instrument_failure":0,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_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'","samples_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":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"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":[]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"ef6d0dd20356c916bf8e3f179c2e036d2fcf9695c34bbc3f532851ee673d17cf","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}