{"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/mtl-aqa","name":"MTL-AQA","full_name":null,"description_markdown":"A new multitask action quality assessment (AQA) dataset, the largest to date, comprising of more than 1600 diving samples; contains detailed annotations for  fine-grained action recognition, commentary generation, and estimating the AQA score. Videos from multiple angles provided wherever available.\r\n\r\nSource: [What and How Well You Performed? A Multitask Learning Approach to Action Quality Assessment](/paper/what-and-how-well-you-performed-a-multitask)","description_withheld":null,"homepage":"https://github.com/ParitoshParmar/MTL-AQA","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/what-and-how-well-you-performed-a-multitask","title":"What and How Well You Performed? A Multitask Learning Approach to Action Quality Assessment","first_author":"Paritosh Parmar","url":null},"license":null,"modalities":[{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[{"name":"Action Recognition","url":"/task/action-recognition-in-videos","datasets_with_task":"/datasets/task/action-recognition-in-videos"},{"name":"Action Recognition In Videos","url":"/task/action-recognition-in-videos-2","datasets_with_task":"/datasets/task/action-recognition-in-videos-2"},{"name":"Video Understanding","url":"/task/video-understanding","datasets_with_task":"/datasets/task/video-understanding"},{"name":"Video Captioning","url":"/task/video-captioning","datasets_with_task":"/datasets/task/video-captioning"},{"name":"Multi-Task Learning","url":"/task/multi-task-learning","datasets_with_task":"/datasets/task/multi-task-learning"},{"name":"Action Quality Assessment","url":"/task/action-quality-assessment","datasets_with_task":"/datasets/task/action-quality-assessment"},{"name":"Dense Video Captioning","url":"/task/dense-video-captioning","datasets_with_task":"/datasets/task/dense-video-captioning"},{"name":"Fine-Grained Visual Recognition","url":"/task/fine-grained-visual-recognition","datasets_with_task":"/datasets/task/fine-grained-visual-recognition"},{"name":"Action Understanding","url":"/task/action-understanding","datasets_with_task":"/datasets/task/action-understanding"},{"name":"Fine-Grained Visual Categorization","url":"/task/fine-grained-visual-categorization","datasets_with_task":"/datasets/task/fine-grained-visual-categorization"},{"name":"Multiview Learning","url":"/task/multiview-learning","datasets_with_task":"/datasets/task/multiview-learning"},{"name":"Fine-grained Action Recognition","url":"/task/fine-grained-action-recognition","datasets_with_task":"/datasets/task/fine-grained-action-recognition"}],"languages":[],"variants":["MTL-AQA"],"data_loaders":[{"repo":"https://github.com/ParitoshParmar/MTL-AQA","url":"https://github.com/ParitoshParmar/MTL-AQA","frameworks":[]},{"repo":"https://github.com/laurenok24/nsaqa","url":"https://github.com/laurenok24/nsaqa","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":33,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/action-quality-assessment-on-mtl-aqa","task":"Action Quality Assessment","dataset_variant":"MTL-AQA","rows":21,"metrics":["Spearman Correlation","RL2(*100)"],"first_row_in_archive_order":{"model":"RICA^2 (Deterministic)","paper":"/paper/rica-2-rubric-informed-calibrated-assessment","metrics":{"RL2(*100)":"0.228","Spearman Correlation":"96.20"},"code_links":[{"title":"abrarmajeedi/rica2_aqa","url":"https://github.com/abrarmajeedi/rica2_aqa"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/action-recognition-on-mtl-aqa","task":"Action Recognition","dataset_variant":"MTL-AQA","rows":1,"metrics":["Position Accuracy","Armstand Accuracy","Rotation Type Accuracy","No. of Somersaults Accuracy","No. of Twists Accuracy"],"first_row_in_archive_order":{"model":"C3D-AVG","paper":"/paper/what-and-how-well-you-performed-a-multitask","metrics":{"Armstand Accuracy":"99.72 %","No. of Somersaults Accuracy":"96.88 %","No. of Twists Accuracy":"93.20 %","Position Accuracy":"96.32 %","Rotation Type Accuracy":"97.45 %"},"code_links":[{"title":"ParitoshParmar/MTL-AQA","url":"https://github.com/ParitoshParmar/MTL-AQA"},{"title":"nzl-thu/musdl","url":"https://github.com/nzl-thu/musdl"},{"title":"luciferbobo/dae-aqa","url":"https://github.com/luciferbobo/dae-aqa"},{"title":"InfoX-SEU/DAE-AQA","url":"https://github.com/InfoX-SEU/DAE-AQA"},{"title":"InfoX-SEU/DAE_AQA","url":"https://github.com/InfoX-SEU/DAE_AQA"}]},"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":8,"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/rica-2-rubric-informed-calibrated-assessment","slug":"rica-2-rubric-informed-calibrated-assessment","title":"RICA2: Rubric-Informed, Calibrated Assessment of Actions","date":"2024-08-04","arxiv_id":"2408.02138","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/fineparser-a-fine-grained-spatio-temporal","slug":"fineparser-a-fine-grained-spatio-temporal","title":"FineParser: A Fine-grained Spatio-temporal Action Parser for Human-centric Action Quality Assessment","date":"2024-05-11","arxiv_id":"2405.06887","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":4,"samples_constructed":3,"samples_ran_checked":3,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":5,"official":{"repos":["pku-icst-mipl/fineparser_cvpr2024"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/fineparser-a-fine-grained-spatio-temporal#ran","syntology_url":"https://syntology.ai/paper/2405.06887","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.06887"}}}},{"paper":"/paper/hierarchical-neurosymbolic-approach-for","slug":"hierarchical-neurosymbolic-approach-for","title":"Hierarchical NeuroSymbolic Approach for Comprehensive and Explainable Action Quality Assessment","date":"2024-03-20","arxiv_id":"2403.13798","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/auto-encoding-score-distribution-regression","slug":"auto-encoding-score-distribution-regression","title":"Auto-Encoding Score Distribution Regression for Action Quality Assessment","date":"2021-11-22","arxiv_id":"2111.11029","rows_on_this_dataset":3,"code_links":3,"syntology":null},{"paper":"/paper/group-aware-contrastive-regression-for-action","slug":"group-aware-contrastive-regression-for-action","title":"Group-aware Contrastive Regression for Action Quality Assessment","date":"2021-08-17","arxiv_id":"2108.07797","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/group-aware-contrastive-regression-for-action#ran","syntology_url":"https://syntology.ai/paper/2108.07797","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.07797"}}}},{"paper":"/paper/improving-action-quality-assessment-using","slug":"improving-action-quality-assessment-using","title":"Improving Action Quality Assessment using Weighted Aggregation","date":"2021-02-21","arxiv_id":"2102.10555","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/uncertainty-aware-score-distribution-learning-1","slug":"uncertainty-aware-score-distribution-learning-1","title":"Uncertainty-aware Score Distribution Learning for Action Quality Assessment","date":"2020-06-13","arxiv_id":"2006.07665","rows_on_this_dataset":5,"code_links":1,"syntology":null},{"paper":"/paper/what-and-how-well-you-performed-a-multitask","slug":"what-and-how-well-you-performed-a-multitask","title":"What and How Well You Performed? A Multitask Learning Approach to Action Quality Assessment","date":"2019-04-08","arxiv_id":"1904.04346","rows_on_this_dataset":5,"code_links":5,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/rica-2-rubric-informed-calibrated-assessment","slug":"rica-2-rubric-informed-calibrated-assessment","title":"RICA2: Rubric-Informed, Calibrated Assessment of Actions","date":"2024-08-04","arxiv_id":"2408.02138","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/fineparser-a-fine-grained-spatio-temporal","slug":"fineparser-a-fine-grained-spatio-temporal","title":"FineParser: A Fine-grained Spatio-temporal Action Parser for Human-centric Action Quality Assessment","date":"2024-05-11","arxiv_id":"2405.06887","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":4,"samples_constructed":3,"samples_ran_checked":3,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":5,"official":{"repos":["pku-icst-mipl/fineparser_cvpr2024"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/fineparser-a-fine-grained-spatio-temporal#ran","syntology_url":"https://syntology.ai/paper/2405.06887","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.06887"}}}},{"paper":"/paper/hierarchical-neurosymbolic-approach-for","slug":"hierarchical-neurosymbolic-approach-for","title":"Hierarchical NeuroSymbolic Approach for Comprehensive and Explainable Action Quality Assessment","date":"2024-03-20","arxiv_id":"2403.13798","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/auto-encoding-score-distribution-regression","slug":"auto-encoding-score-distribution-regression","title":"Auto-Encoding Score Distribution Regression for Action Quality Assessment","date":"2021-11-22","arxiv_id":"2111.11029","rows_on_this_dataset":3,"code_links":3,"syntology":null},{"paper":"/paper/group-aware-contrastive-regression-for-action","slug":"group-aware-contrastive-regression-for-action","title":"Group-aware Contrastive Regression for Action Quality Assessment","date":"2021-08-17","arxiv_id":"2108.07797","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/group-aware-contrastive-regression-for-action#ran","syntology_url":"https://syntology.ai/paper/2108.07797","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.07797"}}}},{"paper":"/paper/improving-action-quality-assessment-using","slug":"improving-action-quality-assessment-using","title":"Improving Action Quality Assessment using Weighted Aggregation","date":"2021-02-21","arxiv_id":"2102.10555","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/uncertainty-aware-score-distribution-learning-1","slug":"uncertainty-aware-score-distribution-learning-1","title":"Uncertainty-aware Score Distribution Learning for Action Quality Assessment","date":"2020-06-13","arxiv_id":"2006.07665","rows_on_this_dataset":5,"code_links":1,"syntology":null},{"paper":"/paper/what-and-how-well-you-performed-a-multitask","slug":"what-and-how-well-you-performed-a-multitask","title":"What and How Well You Performed? A Multitask Learning Approach to Action Quality Assessment","date":"2019-04-08","arxiv_id":"1904.04346","rows_on_this_dataset":5,"code_links":5,"syntology":null}],"papers_where_code_ran":2,"papers_where_code_ran_first_page":"/dataset/mtl-aqa/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/mtl-aqa/papers/ran/1","json":"/dataset/mtl-aqa/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":6,"samples_ran":5,"samples_constructed":4,"samples_ran_checked":4,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":6,"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":"3c2a78b1817e9aec22767f145fc20913c6bfbe97934e86ded5ffbd1aaa3a6d58","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}