{"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":"/task/action-understanding","name":"Action Understanding","slug":"action-understanding","description_markdown":null,"categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":88,"papers_with_code":35,"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":4,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/action-understanding-on-win-fail-action","slug":"action-understanding-on-win-fail-action","dataset":"Win-Fail Action Understanding","dataset_url":"/dataset/win-fail-action-understanding","rows_in_archive":1,"metrics":["2-Class Accuracy"],"first_row_in_archive_order":{"model":"2DCNN+TRN","paper_title":"Win-Fail Action Recognition","paper_url":"/paper/win-fail-action-recognition","paper_date":"2021-02-15","arxiv_id":"2102.07355","code_links":[{"title":"ParitoshParmar/Win-Fail-Action-Recognition","url":"https://github.com/ParitoshParmar/Win-Fail-Action-Recognition"}],"syntology":null}}],"datasets":[{"url":"/dataset/mtl-aqa","name":"MTL-AQA","full_name":"","num_papers_in_archive":33},{"url":"/dataset/fitness-aqa","name":"Fitness-AQA","full_name":"Fitness Action Quality Assessment [ECCV 2022]","num_papers_in_archive":3},{"url":"/dataset/w-oops","name":"W-Oops","full_name":"","num_papers_in_archive":1},{"url":"/dataset/win-fail-action-understanding","name":"Win-Fail Action Understanding","full_name":"Win-Fail Action Understanding","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":88,"of":88,"of_with_code":35,"tagged_in_all":88,"counts":{"archive_papers_tagged":88,"with_a_code_link":35,"where_syntology_ran_a_sample":11,"not_listed_spam_title":0,"listed":88,"listed_where_code_ran":11,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":8,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":8,"listed_every_run_a_failure_of_syntologys_instrument":3,"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 the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/prompted-contrast-with-masked-motion-modeling","slug":"prompted-contrast-with-masked-motion-modeling","title":"Prompted Contrast with Masked Motion Modeling: Towards Versatile 3D Action Representation Learning","date":"2023-08-08","arxiv_id":"2308.03975","repositories_listed":2,"syntology":null},{"url":"/paper/llava-pose-enhancing-human-pose-and-action","slug":"llava-pose-enhancing-human-pose-and-action","title":"LLaVA-Pose: Enhancing Human Pose and Action Understanding via Keypoint-Integrated Instruction Tuning","date":"2025-06-26","arxiv_id":"2506.21317","repositories_listed":1,"syntology":null},{"url":"/paper/f-3-set-towards-analyzing-fast-frequent-and","slug":"f-3-set-towards-analyzing-fast-frequent-and","title":"F$^3$Set: Towards Analyzing Fast, Frequent, and Fine-grained Events from Videos","date":"2025-04-11","arxiv_id":"2504.08222","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":3,"n_honours":3,"n_violates":0,"n_no_contract":4,"n_pointer_only":12,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 3 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/f-3-set-towards-analyzing-fast-frequent-and#ran","syntology_url":"https://syntology.ai/paper/2504.08222","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.08222"}},"official":{"repos":["f3set/f3set"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/llavaction-evaluating-and-training-multi","slug":"llavaction-evaluating-and-training-multi","title":"LLaVAction: evaluating and training multi-modal large language models for action recognition","date":"2025-03-24","arxiv_id":"2503.18712","repositories_listed":1,"syntology":null},{"url":"/paper/sefar-semi-supervised-fine-grained-action","slug":"sefar-semi-supervised-fine-grained-action","title":"SeFAR: Semi-supervised Fine-grained Action Recognition with Temporal Perturbation and Learning Stabilization","date":"2025-01-02","arxiv_id":"2501.01245","repositories_listed":1,"syntology":null},{"url":"/paper/language-assisted-skeleton-action","slug":"language-assisted-skeleton-action","title":"Language-Assisted Skeleton Action Understanding for Skeleton-Based Temporal Action Segmentation","date":"2024-10-31","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/egoexo-fitness-towards-egocentric-and","slug":"egoexo-fitness-towards-egocentric-and","title":"EgoExo-Fitness: Towards Egocentric and Exocentric Full-Body Action Understanding","date":"2024-06-13","arxiv_id":"2406.08877","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":3,"n_instrument":6,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/egoexo-fitness-towards-egocentric-and#ran","syntology_url":"https://syntology.ai/paper/2406.08877","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.08877"}},"official":{"repos":["isee-laboratory/egoexo-fitness"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/ophnet-a-large-scale-video-benchmark-for","slug":"ophnet-a-large-scale-video-benchmark-for","title":"OphNet: A Large-Scale Video Benchmark for Ophthalmic Surgical Workflow Understanding","date":"2024-06-11","arxiv_id":"2406.07471","repositories_listed":1,"syntology":{"n":16,"n_ran":11,"n_constructed":0,"n_ran_checked":7,"n_instrument":4,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":2,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/ophnet-a-large-scale-video-benchmark-for#ran","syntology_url":"https://syntology.ai/paper/2406.07471","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.07471"}},"official":{"repos":["minghu0830/ophnet-benchmark"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/self-supervised-skeleton-action","slug":"self-supervised-skeleton-action","title":"Self-Supervised Skeleton-Based Action Representation Learning: A Benchmark and Beyond","date":"2024-06-05","arxiv_id":"2406.02978","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":3,"n_ran_checked":3,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"phrase":"4 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","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"}},"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"]}}},{"url":"/paper/sports-qa-a-large-scale-video-question","slug":"sports-qa-a-large-scale-video-question","title":"Sports-QA: A Large-Scale Video Question Answering Benchmark for Complex and Professional Sports","date":"2024-01-03","arxiv_id":"2401.01505","repositories_listed":1,"syntology":null},{"url":"/paper/finesports-a-multi-person-hierarchical-sports","slug":"finesports-a-multi-person-hierarchical-sports","title":"FineSports: A Multi-person Hierarchical Sports Video Dataset for Fine-grained Action Understanding","date":"2024-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/open-vocabulary-video-relation-extraction","slug":"open-vocabulary-video-relation-extraction","title":"Open-Vocabulary Video Relation Extraction","date":"2023-12-25","arxiv_id":"2312.15670","repositories_listed":1,"syntology":null},{"url":"/paper/unified-multi-modal-unsupervised","slug":"unified-multi-modal-unsupervised","title":"Unified Multi-modal Unsupervised Representation Learning for Skeleton-based Action Understanding","date":"2023-11-06","arxiv_id":"2311.03106","repositories_listed":1,"syntology":null},{"url":"/paper/memory-and-anticipation-transformer-for","slug":"memory-and-anticipation-transformer-for","title":"Memory-and-Anticipation Transformer for Online Action Understanding","date":"2023-08-15","arxiv_id":"2308.07893","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/memory-and-anticipation-transformer-for#ran","syntology_url":"https://syntology.ai/paper/2308.07893","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.07893"}},"official":{"repos":["echo0125/memory-and-anticipation-transformer"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/paxion-patching-action-knowledge-in-video-1","slug":"paxion-patching-action-knowledge-in-video-1","title":"Paxion: Patching Action Knowledge in Video-Language Foundation Models","date":"2023-05-18","arxiv_id":"2305.10683","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/paxion-patching-action-knowledge-in-video-1#ran","syntology_url":"https://syntology.ai/paper/2305.10683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.10683"}},"official":{"repos":["mikewangwzhl/paxion"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/act-thor-a-controlled-benchmark-for-embodied","slug":"act-thor-a-controlled-benchmark-for-embodied","title":"ACT-Thor: A Controlled Benchmark for Embodied Action Understanding in Simulated Environments","date":"2022-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/weakly-supervised-temporal-action-detection","slug":"weakly-supervised-temporal-action-detection","title":"Weakly-Supervised Temporal Action Detection for Fine-Grained Videos with Hierarchical Atomic Actions","date":"2022-07-24","arxiv_id":"2207.11805","repositories_listed":1,"syntology":null},{"url":"/paper/action-quality-assessment-with-temporal","slug":"action-quality-assessment-with-temporal","title":"Action Quality Assessment with Temporal Parsing Transformer","date":"2022-07-19","arxiv_id":"2207.09270","repositories_listed":1,"syntology":null},{"url":"/paper/tragedy-plus-time-capturing-unintended-human","slug":"tragedy-plus-time-capturing-unintended-human","title":"Tragedy Plus Time: Capturing Unintended Human Activities from Weakly-labeled Videos","date":"2022-04-28","arxiv_id":"2204.13548","repositories_listed":1,"syntology":null},{"url":"/paper/bridge-prompt-towards-ordinal-action","slug":"bridge-prompt-towards-ordinal-action","title":"Bridge-Prompt: Towards Ordinal Action Understanding in Instructional Videos","date":"2022-03-26","arxiv_id":"2203.14104","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/bridge-prompt-towards-ordinal-action#ran","syntology_url":"https://syntology.ai/paper/2203.14104","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.14104"}},"official":{"repos":["ttlmh/bridge-prompt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/domain-knowledge-informed-self-supervised","slug":"domain-knowledge-informed-self-supervised","title":"Domain Knowledge-Informed Self-Supervised Representations for Workout Form Assessment","date":"2022-02-28","arxiv_id":"2202.14019","repositories_listed":1,"syntology":null},{"url":"/paper/towards-tokenized-human-dynamics","slug":"towards-tokenized-human-dynamics","title":"Towards Tokenized Human Dynamics Representation","date":"2021-11-22","arxiv_id":"2111.11433","repositories_listed":1,"syntology":null},{"url":"/paper/video-pose-distillation-for-few-shot-fine","slug":"video-pose-distillation-for-few-shot-fine","title":"Video Pose Distillation for Few-Shot, Fine-Grained Sports Action Recognition","date":"2021-09-03","arxiv_id":"2109.01305","repositories_listed":1,"syntology":null},{"url":"/paper/few-shot-fine-grained-action-recognition-via","slug":"few-shot-fine-grained-action-recognition-via","title":"Few-Shot Fine-Grained Action Recognition via Bidirectional Attention and Contrastive Meta-Learning","date":"2021-08-15","arxiv_id":"2108.06647","repositories_listed":1,"syntology":null},{"url":"/paper/piano-a-parametric-hand-bone-model-from","slug":"piano-a-parametric-hand-bone-model-from","title":"PIANO: A Parametric Hand Bone Model from Magnetic Resonance Imaging","date":"2021-06-21","arxiv_id":"2106.10893","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":7,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/piano-a-parametric-hand-bone-model-from#ran","syntology_url":"https://syntology.ai/paper/2106.10893","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.10893"}},"official":{"repos":["reyuwei/PIANO_model"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/home-action-genome-cooperative-compositional","slug":"home-action-genome-cooperative-compositional","title":"Home Action Genome: Cooperative Compositional Action Understanding","date":"2021-05-11","arxiv_id":"2105.05226","repositories_listed":1,"syntology":{"n":16,"n_ran":13,"n_constructed":0,"n_ran_checked":11,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/home-action-genome-cooperative-compositional#ran","syntology_url":"https://syntology.ai/paper/2105.05226","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.05226"}},"official":{"repos":["nishantrai18/homage"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/win-fail-action-recognition","slug":"win-fail-action-recognition","title":"Win-Fail Action Recognition","date":"2021-02-15","arxiv_id":"2102.07355","repositories_listed":1,"syntology":null},{"url":"/paper/temporal-relational-modeling-with-self","slug":"temporal-relational-modeling-with-self","title":"Temporal Relational Modeling with Self-Supervision for Action Segmentation","date":"2020-12-14","arxiv_id":"2012.07508","repositories_listed":1,"syntology":null},{"url":"/paper/video-action-understanding-a-tutorial","slug":"video-action-understanding-a-tutorial","title":"Video Action Understanding","date":"2020-10-13","arxiv_id":"2010.06647","repositories_listed":1,"syntology":null},{"url":"/paper/online-spatiotemporal-action-detection-and","slug":"online-spatiotemporal-action-detection-and","title":"Online Spatiotemporal Action Detection and Prediction via Causal Representations","date":"2020-08-31","arxiv_id":"2008.13759","repositories_listed":1,"syntology":null},{"url":"/paper/lemma-a-multi-view-dataset-for-learning-multi","slug":"lemma-a-multi-view-dataset-for-learning-multi","title":"LEMMA: A Multi-view Dataset for Learning Multi-agent Multi-task Activities","date":"2020-07-31","arxiv_id":"2007.15781","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/lemma-a-multi-view-dataset-for-learning-multi#ran","syntology_url":"https://syntology.ai/paper/2007.15781","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.15781"}},"official":{"repos":["Buzz-Beater/LEMMA"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/detailed-2d-3d-joint-representation-for-human","slug":"detailed-2d-3d-joint-representation-for-human","title":"Detailed 2D-3D Joint Representation for Human-Object Interaction","date":"2020-04-17","arxiv_id":"2004.08154","repositories_listed":1,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/detailed-2d-3d-joint-representation-for-human#ran","syntology_url":"https://syntology.ai/paper/2004.08154","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.08154"}},"official":{"repos":["DirtyHarryLYL/DJ-RN"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/youmakeup-vqa-challenge-towards-fine-grained","slug":"youmakeup-vqa-challenge-towards-fine-grained","title":"YouMakeup VQA Challenge: Towards Fine-grained Action Understanding in Domain-Specific Videos","date":"2020-04-12","arxiv_id":"2004.05573","repositories_listed":1,"syntology":null},{"url":"/paper/action-recognition-with-trajectory-pooled","slug":"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":null,"slug":"the-role-of-video-generation-in-enhancing","title":"The Role of Video Generation in Enhancing Data-Limited Action Understanding","date":"2025-05-26","arxiv_id":"2505.19495","repositories_listed":0,"syntology":null},{"url":null,"slug":"pcbear-pose-concept-bottleneck-for","title":"PCBEAR: Pose Concept Bottleneck for Explainable Action Recognition","date":"2025-04-17","arxiv_id":"2504.13140","repositories_listed":0,"syntology":null},{"url":null,"slug":"roboact-clip-video-driven-pre-training-of","title":"RoboAct-CLIP: Video-Driven Pre-training of Atomic Action Understanding for Robotics","date":"2025-04-02","arxiv_id":"2504.02069","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-deepseek-v3-reason-like-a-surgeon-an","title":"Can DeepSeek Reason Like a Surgeon? An Empirical Evaluation for Vision-Language Understanding in Robotic-Assisted Surgery","date":"2025-03-29","arxiv_id":"2503.23130","repositories_listed":0,"syntology":null},{"url":null,"slug":"screenllm-stateful-screen-schema-for","title":"ScreenLLM: Stateful Screen Schema for Efficient Action Understanding and Prediction","date":"2025-03-26","arxiv_id":"2503.20978","repositories_listed":0,"syntology":null},{"url":null,"slug":"haic-improving-human-action-understanding-and","title":"HAIC: Improving Human Action Understanding and Generation with Better Captions for Multi-modal Large Language Models","date":"2025-02-28","arxiv_id":"2502.20811","repositories_listed":0,"syntology":null},{"url":null,"slug":"humanomni-a-large-vision-speech-language","title":"HumanOmni: A Large Vision-Speech Language Model for Human-Centric Video Understanding","date":"2025-01-25","arxiv_id":"2501.15111","repositories_listed":0,"syntology":null},{"url":null,"slug":"heterogeneous-skeleton-based-action","title":"Heterogeneous Skeleton-Based Action Representation Learning","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"stpro-spatial-and-temporal-progressive","title":"STPro: Spatial and Temporal Progressive Learning for Weakly Supervised Spatio-Temporal Grounding","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"about-time-advances-challenges-and-outlooks","title":"About Time: Advances, Challenges, and Outlooks of Action Understanding","date":"2024-11-22","arxiv_id":"2411.15106","repositories_listed":0,"syntology":null},{"url":"/paper/macdiff-unified-skeleton-modeling-with-masked","slug":"macdiff-unified-skeleton-modeling-with-masked","title":"MacDiff: Unified Skeleton Modeling with Masked Conditional Diffusion","date":"2024-09-16","arxiv_id":"2409.10473","repositories_listed":0,"syntology":{"n":12,"n_ran":8,"n_constructed":6,"n_ran_checked":7,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":12,"phrase":"8 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/macdiff-unified-skeleton-modeling-with-masked#ran","syntology_url":"https://syntology.ai/paper/2409.10473","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.10473"}},"official":null}},{"url":null,"slug":"cathaction-a-benchmark-for-endovascular","title":"CathAction: A Benchmark for Endovascular Intervention Understanding","date":"2024-08-23","arxiv_id":"2408.13126","repositories_listed":0,"syntology":null},{"url":null,"slug":"probing-fine-grained-action-understanding-and","title":"Probing Fine-Grained Action Understanding and Cross-View Generalization of Foundation Models","date":"2024-07-22","arxiv_id":"2407.15605","repositories_listed":0,"syntology":null},{"url":null,"slug":"region-aware-image-based-human-action","title":"Region-aware Image-based Human Action Retrieval with Transformers","date":"2024-07-13","arxiv_id":"2407.09924","repositories_listed":0,"syntology":null},{"url":null,"slug":"velociti-can-video-language-models-bind","title":"VELOCITI: Benchmarking Video-Language Compositional Reasoning with Strict Entailment","date":"2024-06-16","arxiv_id":"2406.10889","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-skatingverse-workshop-challenge-methods","title":"The SkatingVerse Workshop & Challenge: Methods and Results","date":"2024-05-27","arxiv_id":"2405.17188","repositories_listed":0,"syntology":null},{"url":null,"slug":"social-mae-social-masked-autoencoder-for","title":"Social-MAE: Social Masked Autoencoder for Multi-person Motion Representation Learning","date":"2024-04-08","arxiv_id":"2404.05578","repositories_listed":0,"syntology":null},{"url":"/paper/enhancing-video-transformers-for-action","slug":"enhancing-video-transformers-for-action","title":"Enhancing Video Transformers for Action Understanding with VLM-aided Training","date":"2024-03-24","arxiv_id":"2403.16128","repositories_listed":0,"syntology":null},{"url":null,"slug":"impact-of-large-language-model-assistance-on","title":"Impact of Large Language Model Assistance on Patients Reading Clinical Notes: A Mixed-Methods Study","date":"2024-01-17","arxiv_id":"2401.09637","repositories_listed":0,"syntology":null},{"url":null,"slug":"multitask-learning-in-minimally-invasive","title":"Multitask Learning in Minimally Invasive Surgical Vision: A Review","date":"2024-01-16","arxiv_id":"2401.08256","repositories_listed":0,"syntology":null},{"url":"/paper/adafocus-towards-end-to-end-weakly-supervised","slug":"adafocus-towards-end-to-end-weakly-supervised","title":"Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition","date":"2023-11-28","arxiv_id":"2311.17118","repositories_listed":0,"syntology":null},{"url":null,"slug":"kantian-deontology-meets-ai-alignment-towards","title":"Kantian Deontology Meets AI Alignment: Towards Morally Grounded Fairness Metrics","date":"2023-11-09","arxiv_id":"2311.05227","repositories_listed":0,"syntology":null},{"url":null,"slug":"comparing-machines-and-children-using","title":"Comparing Machines and Children: Using Developmental Psychology Experiments to Assess the Strengths and Weaknesses of LaMDA Responses","date":"2023-05-18","arxiv_id":"2305.11243","repositories_listed":0,"syntology":null},{"url":null,"slug":"attach-dataset-annotated-two-handed-assembly","title":"ATTACH Dataset: Annotated Two-Handed Assembly Actions for Human Action Understanding","date":"2023-04-17","arxiv_id":"2304.08210","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-isolated-islands-to-pangea-unifying","title":"From Isolated Islands to Pangea: Unifying Semantic Space for Human Action Understanding","date":"2023-04-02","arxiv_id":"2304.00553","repositories_listed":0,"syntology":null},{"url":null,"slug":"mri-multi-modal-3d-human-pose-estimation","title":"mRI: Multi-modal 3D Human Pose Estimation Dataset using mmWave, RGB-D, and Inertial Sensors","date":"2022-10-15","arxiv_id":"2210.08394","repositories_listed":0,"syntology":null},{"url":null,"slug":"invisible-to-visible-privacy-aware-human","title":"Invisible-to-Visible: Privacy-Aware Human Instance Segmentation using Airborne Ultrasound via Collaborative Learning Variational Autoencoder","date":"2022-04-15","arxiv_id":"2204.07280","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-discovery-of-human-actons","title":"Self-supervised Discovery of Human Actons from Long Kinematic Videos","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/jrdb-act-a-large-scale-multi-modal-dataset","slug":"jrdb-act-a-large-scale-multi-modal-dataset","title":"JRDB-Act: A Large-scale Dataset for Spatio-temporal Action, Social Group and Activity Detection","date":"2021-06-16","arxiv_id":"2106.08827","repositories_listed":0,"syntology":null},{"url":null,"slug":"event-based-timestamp-image-encoding-network","title":"Event-based Timestamp Image Encoding Network for Human Action Recognition and Anticipation","date":"2021-04-12","arxiv_id":"2104.05145","repositories_listed":0,"syntology":null},{"url":null,"slug":"gta-global-temporal-attention-for-video","title":"GTA: Global Temporal Attention for Video Action Understanding","date":"2020-12-15","arxiv_id":"2012.08510","repositories_listed":0,"syntology":null},{"url":"/paper/actor-and-action-modular-network-for-text","slug":"actor-and-action-modular-network-for-text","title":"Actor and Action Modular Network for Text-based Video Segmentation","date":"2020-11-02","arxiv_id":"2011.00786","repositories_listed":0,"syntology":null},{"url":"/paper/boundary-content-graph-neural-network-for","slug":"boundary-content-graph-neural-network-for","title":"Boundary Content Graph Neural Network for Temporal Action Proposal Generation","date":"2020-08-04","arxiv_id":"2008.01432","repositories_listed":0,"syntology":null},{"url":null,"slug":"explainable-robotic-systems-interpreting","title":"Explainable robotic systems: Understanding goal-driven actions in a reinforcement learning scenario","date":"2020-06-24","arxiv_id":"2006.13615","repositories_listed":0,"syntology":null},{"url":"/paper/intra-and-inter-action-understanding-via","slug":"intra-and-inter-action-understanding-via","title":"Intra- and Inter-Action Understanding via Temporal Action Parsing","date":"2020-05-20","arxiv_id":"2005.10229","repositories_listed":0,"syntology":null},{"url":"/paper/finegym-a-hierarchical-video-dataset-for-fine","slug":"finegym-a-hierarchical-video-dataset-for-fine","title":"FineGym: A Hierarchical Video Dataset for Fine-grained Action Understanding","date":"2020-04-14","arxiv_id":"2004.06704","repositories_listed":0,"syntology":null},{"url":"/paper/mmact-a-large-scale-dataset-for-cross-modal","slug":"mmact-a-large-scale-dataset-for-cross-modal","title":"MMAct: A Large-Scale Dataset for Cross Modal Human Action Understanding","date":"2019-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"cortical-mirror-system-activation-during-real","title":"Cortical Mirror-System Activation During Real-Life Game Playing: An Intracranial Electroencephalography (EEG) Study","date":"2019-03-27","arxiv_id":"1902.09189","repositories_listed":0,"syntology":null},{"url":null,"slug":"scene-understanding-for-autonomous","title":"Scene Understanding for Autonomous Manipulation with Deep Learning","date":"2019-03-23","arxiv_id":"1903.09761","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-uncertainty-in-conditional-multi","title":"Exploring Uncertainty in Conditional Multi-Modal Retrieval Systems","date":"2019-01-23","arxiv_id":"1901.07702","repositories_listed":0,"syntology":null},{"url":null,"slug":"theory-of-minds-understanding-behavior-in","title":"Theory of Minds: Understanding Behavior in Groups Through Inverse Planning","date":"2019-01-18","arxiv_id":"1901.06085","repositories_listed":0,"syntology":null},{"url":null,"slug":"weakly-supervised-actor-action-segmentation","title":"Weakly Supervised Actor-Action Segmentation via Robust Multi-Task Ranking","date":"2017-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"action-understanding-with-multiple-classes-of","title":"Action Understanding with Multiple Classes of Actors","date":"2017-04-27","arxiv_id":"1704.08723","repositories_listed":0,"syntology":null},{"url":"/paper/pku-mmd-a-large-scale-benchmark-for","slug":"pku-mmd-a-large-scale-benchmark-for","title":"PKU-MMD: A Large Scale Benchmark for Continuous Multi-Modal Human Action Understanding","date":"2017-03-22","arxiv_id":"1703.07475","repositories_listed":0,"syntology":null},{"url":"/paper/who-is-mistaken","slug":"who-is-mistaken","title":"Who is Mistaken?","date":"2016-12-04","arxiv_id":"1612.01175","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-attention-network-for-action","title":"Hierarchical Attention Network for Action Recognition in Videos","date":"2016-07-21","arxiv_id":"1607.06416","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-hierarchical-pose-based-approach-to-complex","title":"A Hierarchical Pose-Based Approach to Complex Action Understanding Using Dictionaries of Actionlets and Motion Poselets","date":"2016-06-15","arxiv_id":"1606.04992","repositories_listed":0,"syntology":null},{"url":null,"slug":"dap3d-net-where-what-and-how-actions-occur-in","title":"DAP3D-Net: Where, What and How Actions Occur in Videos?","date":"2016-02-10","arxiv_id":"1602.03346","repositories_listed":0,"syntology":null},{"url":"/paper/can-humans-fly-action-understanding-with","slug":"can-humans-fly-action-understanding-with","title":"Can Humans Fly? Action Understanding With Multiple Classes of Actors","date":"2015-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"grasp-type-revisited-a-modern-perspective-on","title":"Grasp Type Revisited: A Modern Perspective on a Classical Feature for Vision","date":"2015-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"human-action-segmentation-with-hierarchical","title":"Human Action Segmentation With Hierarchical Supervoxel Consistency","date":"2015-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"an-expressive-deep-model-for-human-action","title":"An Expressive Deep Model for Human Action Parsing from A Single Image","date":"2015-02-02","arxiv_id":"1502.00501","repositories_listed":0,"syntology":null},{"url":null,"slug":"compositional-structure-learning-for-action","title":"Compositional Structure Learning for Action Understanding","date":"2014-10-21","arxiv_id":"1410.5861","repositories_listed":0,"syntology":null}],"syntology_records":12,"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"},"key_notes":{"n_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'","n_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_where_code_ran":11,"papers_where_code_ran_first_page":"/task/action-understanding/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/action-understanding/papers/ran/1","json":"/task/action-understanding/papers/ran/1.json","rows":11}],"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":"2026-10-05T00:36:11+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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper 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"},"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"},"record_sha256":"2a70a981d012203080c13844cdb21a3ee290bb110f93beb1eb14a8b207ffa0ae","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}