{"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/multithumos","name":"MultiTHUMOS","full_name":null,"description_markdown":"The **MultiTHUMOS** dataset contains dense, multilabel, frame-level action annotations for 30 hours across 400 videos in the THUMOS'14 action detection dataset. It consists of 38,690 annotations of 65 action classes, with an average of 1.5 labels per frame and 10.5 action classes per video.\r\n\r\nSource: [http://ai.stanford.edu/~syyeung/everymoment.html](http://ai.stanford.edu/~syyeung/everymoment.html)\r\nImage Source: [http://ai.stanford.edu/~syyeung/everymoment.html](http://ai.stanford.edu/~syyeung/everymoment.html)","description_withheld":null,"homepage":"http://ai.stanford.edu/~syyeung/everymoment.html","introduced_date":"2018-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/every-moment-counts-dense-detailed-labeling","title":"Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos","first_author":"Serena Yeung","url":null},"license":{"name":"CC BY 4.0","url":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":"Temporal Action Localization","url":"/task/action-recognition","datasets_with_task":"/datasets/task/action-recognition"},{"name":"Action Detection","url":"/task/action-detection","datasets_with_task":"/datasets/task/action-detection"}],"languages":[],"variants":["Multi-THUMOS","MultiTHUMOS"],"data_loaders":[],"num_papers_in_archive":58,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/action-detection-on-multi-thumos","task":"Action Detection","dataset_variant":"Multi-THUMOS","rows":8,"metrics":["mAP"],"first_row_in_archive_order":{"model":"MLAD","paper":"/paper/modeling-multi-label-action-dependencies-for","metrics":{"mAP":"51.5"},"code_links":[{"title":"ptirupat/MLAD","url":"https://github.com/ptirupat/MLAD"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/temporal-action-localization-on-multithumos-1","task":"Temporal Action Localization","dataset_variant":"MultiTHUMOS","rows":8,"metrics":["Average mAP","mAP IOU@0.1","mAP IOU@0.2","mAP IOU@0.3","mAP IOU@0.4","mAP IOU@0.5","mAP IOU@0.6","mAP IOU@0.7","mAP IOU@0.8","mAP IOU@0.9"],"first_row_in_archive_order":{"model":"TriDet (VideoMAEv2)","paper":"/paper/temporal-action-localization-with-enhanced","metrics":{"Average mAP":"37.5","mAP IOU@0.2":"57.7","mAP IOU@0.5":"42.7","mAP IOU@0.7":"24.3"},"code_links":[{"title":"dingfengshi/tridet","url":"https://github.com/dingfengshi/tridet"},{"title":"sssste/tridet","url":"https://github.com/sssste/tridet"},{"title":"dingfengshi/tridetplus","url":"https://github.com/dingfengshi/tridetplus"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/action-detection-on-multithumos-1","task":"Action Detection","dataset_variant":"MultiTHUMOS","rows":1,"metrics":["mAP"],"first_row_in_archive_order":{"model":"PAT","paper":"/paper/pat-position-aware-transformer-for-dense","metrics":{"mAP":"44.6"},"code_links":[]},"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":12,"of":12,"counts":{"papers_with_a_benchmark_row":12,"with_a_code_link":9,"where_syntology_ran_a_sample":3,"not_listed_spam_title":0,"listed":12,"listed_where_code_ran":3,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":2,"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 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/dual-detrs-for-multi-label-temporal-action","slug":"dual-detrs-for-multi-label-temporal-action","title":"Dual DETRs for Multi-Label Temporal Action Detection","date":"2024-03-31","arxiv_id":"2404.00653","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/temporal-action-localization-with-enhanced","slug":"temporal-action-localization-with-enhanced","title":"Temporal Action Localization with Enhanced Instant Discriminability","date":"2023-09-11","arxiv_id":"2309.05590","rows_on_this_dataset":2,"code_links":3,"syntology":null},{"paper":"/paper/pat-position-aware-transformer-for-dense","slug":"pat-position-aware-transformer-for-dense","title":"PAT: Position-Aware Transformer for Dense Multi-Label Action Detection","date":"2023-08-09","arxiv_id":"2308.05051","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/temporalmaxer-maximize-temporal-context-with","slug":"temporalmaxer-maximize-temporal-context-with","title":"TemporalMaxer: Maximize Temporal Context with only Max Pooling for Temporal Action Localization","date":"2023-03-16","arxiv_id":"2303.09055","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/pointtad-multi-label-temporal-action","slug":"pointtad-multi-label-temporal-action","title":"PointTAD: Multi-Label Temporal Action Detection with Learnable Query Points","date":"2022-10-20","arxiv_id":"2210.11035","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":6,"samples_constructed":1,"samples_ran_checked":2,"samples_ran_instrument_failed":4,"samples_unverified":2,"pointer_only_for_licence":3,"official":{"repos":["mcg-nju/pointtad"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/pointtad-multi-label-temporal-action#ran","syntology_url":"https://syntology.ai/paper/2210.11035","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.11035"}}}},{"paper":"/paper/ms-tct-multi-scale-temporal-convtransformer","slug":"ms-tct-multi-scale-temporal-convtransformer","title":"MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection","date":"2021-12-07","arxiv_id":"2112.03902","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/ms-tct-multi-scale-temporal-convtransformer#ran","syntology_url":"https://syntology.ai/paper/2112.03902","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.03902"}}}},{"paper":"/paper/ctrn-class-temporal-relational-network-for","slug":"ctrn-class-temporal-relational-network-for","title":"CTRN: Class-Temporal Relational Network for Action Detection","date":"2021-10-26","arxiv_id":"2110.13473","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/modeling-multi-label-action-dependencies-for","slug":"modeling-multi-label-action-dependencies-for","title":"Modeling Multi-Label Action Dependencies for Temporal Action Localization","date":"2021-03-04","arxiv_id":"2103.03027","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":5,"samples_constructed":3,"samples_ran_checked":4,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":5,"official":{"repos":["ptirupat/MLAD"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/modeling-multi-label-action-dependencies-for#ran","syntology_url":"https://syntology.ai/paper/2103.03027","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.03027"}}}},{"paper":"/paper/pdan-pyramid-dilated-attention-network-for","slug":"pdan-pyramid-dilated-attention-network-for","title":"PDAN: Pyramid Dilated Attention Network for Action Detection","date":"2021-01-05","arxiv_id":null,"rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/temporal-gaussian-mixture-layer-for-videos","slug":"temporal-gaussian-mixture-layer-for-videos","title":"Temporal Gaussian Mixture Layer for Videos","date":"2018-03-16","arxiv_id":"1803.06316","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-latent-super-events-to-detect","slug":"learning-latent-super-events-to-detect","title":"Learning Latent Super-Events to Detect Multiple Activities in Videos","date":"2017-12-05","arxiv_id":"1712.01938","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/every-moment-counts-dense-detailed-labeling","slug":"every-moment-counts-dense-detailed-labeling","title":"Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos","date":"2015-07-21","arxiv_id":"1507.05738","rows_on_this_dataset":2,"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/dual-detrs-for-multi-label-temporal-action","slug":"dual-detrs-for-multi-label-temporal-action","title":"Dual DETRs for Multi-Label Temporal Action Detection","date":"2024-03-31","arxiv_id":"2404.00653","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/temporal-action-localization-with-enhanced","slug":"temporal-action-localization-with-enhanced","title":"Temporal Action Localization with Enhanced Instant Discriminability","date":"2023-09-11","arxiv_id":"2309.05590","rows_on_this_dataset":2,"code_links":3,"syntology":null},{"paper":"/paper/pat-position-aware-transformer-for-dense","slug":"pat-position-aware-transformer-for-dense","title":"PAT: Position-Aware Transformer for Dense Multi-Label Action Detection","date":"2023-08-09","arxiv_id":"2308.05051","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/temporalmaxer-maximize-temporal-context-with","slug":"temporalmaxer-maximize-temporal-context-with","title":"TemporalMaxer: Maximize Temporal Context with only Max Pooling for Temporal Action Localization","date":"2023-03-16","arxiv_id":"2303.09055","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/pointtad-multi-label-temporal-action","slug":"pointtad-multi-label-temporal-action","title":"PointTAD: Multi-Label Temporal Action Detection with Learnable Query Points","date":"2022-10-20","arxiv_id":"2210.11035","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":6,"samples_constructed":1,"samples_ran_checked":2,"samples_ran_instrument_failed":4,"samples_unverified":2,"pointer_only_for_licence":3,"official":{"repos":["mcg-nju/pointtad"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/pointtad-multi-label-temporal-action#ran","syntology_url":"https://syntology.ai/paper/2210.11035","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.11035"}}}},{"paper":"/paper/ms-tct-multi-scale-temporal-convtransformer","slug":"ms-tct-multi-scale-temporal-convtransformer","title":"MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection","date":"2021-12-07","arxiv_id":"2112.03902","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/ms-tct-multi-scale-temporal-convtransformer#ran","syntology_url":"https://syntology.ai/paper/2112.03902","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.03902"}}}},{"paper":"/paper/ctrn-class-temporal-relational-network-for","slug":"ctrn-class-temporal-relational-network-for","title":"CTRN: Class-Temporal Relational Network for Action Detection","date":"2021-10-26","arxiv_id":"2110.13473","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/modeling-multi-label-action-dependencies-for","slug":"modeling-multi-label-action-dependencies-for","title":"Modeling Multi-Label Action Dependencies for Temporal Action Localization","date":"2021-03-04","arxiv_id":"2103.03027","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":5,"samples_constructed":3,"samples_ran_checked":4,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":5,"official":{"repos":["ptirupat/MLAD"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/modeling-multi-label-action-dependencies-for#ran","syntology_url":"https://syntology.ai/paper/2103.03027","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.03027"}}}},{"paper":"/paper/pdan-pyramid-dilated-attention-network-for","slug":"pdan-pyramid-dilated-attention-network-for","title":"PDAN: Pyramid Dilated Attention Network for Action Detection","date":"2021-01-05","arxiv_id":null,"rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/temporal-gaussian-mixture-layer-for-videos","slug":"temporal-gaussian-mixture-layer-for-videos","title":"Temporal Gaussian Mixture Layer for Videos","date":"2018-03-16","arxiv_id":"1803.06316","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-latent-super-events-to-detect","slug":"learning-latent-super-events-to-detect","title":"Learning Latent Super-Events to Detect Multiple Activities in Videos","date":"2017-12-05","arxiv_id":"1712.01938","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/every-moment-counts-dense-detailed-labeling","slug":"every-moment-counts-dense-detailed-labeling","title":"Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos","date":"2015-07-21","arxiv_id":"1507.05738","rows_on_this_dataset":2,"code_links":1,"syntology":null}],"papers_where_code_ran":3,"papers_where_code_ran_first_page":"/dataset/multithumos/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/multithumos/papers/ran/1","json":"/dataset/multithumos/papers/ran/1.json","rows":3}],"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":3,"samples_harvested":14,"samples_ran":12,"samples_constructed":4,"samples_ran_checked":6,"samples_ran_instrument_failed":6,"samples_unverified":2,"pointer_only_for_licence":9,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":3,"papers_with_a_run_with_no_instrument_failure":2,"papers_where_every_run_was_an_instrument_failure":1,"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":"41485d3f06e22bfe695092c9661054b6f6a854baad162a2ceb9b2a01833f6595","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}