{"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/video-action-detection","name":"Video Action Detection","slug":"video-action-detection","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":32,"papers_with_code":19,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":1,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/bah","name":"BAH","full_name":"Behavioural Ambivalence/Hesitancy","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":32,"of":32,"of_with_code":19,"tagged_in_all":32,"counts":{"archive_papers_tagged":32,"with_a_code_link":19,"where_syntology_ran_a_sample":8,"not_listed_spam_title":0,"listed":32,"listed_where_code_ran":8,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":6,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":6,"listed_every_run_a_failure_of_syntologys_instrument":2,"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/context-aware-rcnn-a-baseline-for-action","slug":"context-aware-rcnn-a-baseline-for-action","title":"Context-Aware RCNN: A Baseline for Action Detection in Videos","date":"2020-07-20","arxiv_id":"2007.09861","repositories_listed":3,"syntology":null},{"url":"/paper/stable-mean-teacher-for-semi-supervised-video","slug":"stable-mean-teacher-for-semi-supervised-video","title":"Stable Mean Teacher for Semi-supervised Video Action Detection","date":"2024-12-10","arxiv_id":"2412.07072","repositories_listed":2,"syntology":{"n":6,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"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) · 4 unverified","sample_list":"/paper/stable-mean-teacher-for-semi-supervised-video#ran","syntology_url":"https://syntology.ai/paper/2412.07072","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.07072"}},"official":{"repos":["AKASH2907/stable-mean-teacher","akash2907/stable_mean_teacher"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/efficient-video-action-detection-with-token","slug":"efficient-video-action-detection-with-token","title":"Efficient Video Action Detection with Token Dropout and Context Refinement","date":"2023-04-17","arxiv_id":"2304.08451","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/efficient-video-action-detection-with-token#ran","syntology_url":"https://syntology.ai/paper/2304.08451","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.08451"}},"official":{"repos":["mcg-nju/evad"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/spotting-temporally-precise-fine-grained","slug":"spotting-temporally-precise-fine-grained","title":"Spotting Temporally Precise, Fine-Grained Events in Video","date":"2022-07-20","arxiv_id":"2207.10213","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":1,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"5 ran (of which 1 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/spotting-temporally-precise-fine-grained#ran","syntology_url":"https://syntology.ai/paper/2207.10213","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.10213"}},"official":{"repos":["soccernet/sn-spotting","jhong93/spot"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/asynchronous-interaction-aggregation-for","slug":"asynchronous-interaction-aggregation-for","title":"Asynchronous Interaction Aggregation for Action Detection","date":"2020-04-16","arxiv_id":"2004.07485","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/asynchronous-interaction-aggregation-for#ran","syntology_url":"https://syntology.ai/paper/2004.07485","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.07485"}},"official":{"repos":["MVIG-SJTU/AlphAction"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/actor-conditioned-attention-maps-for-video","slug":"actor-conditioned-attention-maps-for-video","title":"Actor Conditioned Attention Maps for Video Action Detection","date":"2018-12-30","arxiv_id":"1812.11631","repositories_listed":2,"syntology":null},{"url":"/paper/scaling-open-vocabulary-action-detection","slug":"scaling-open-vocabulary-action-detection","title":"Scaling Open-Vocabulary Action Detection","date":"2025-04-04","arxiv_id":"2504.03096","repositories_listed":1,"syntology":null},{"url":"/paper/jovale-detecting-human-actions-in-video-using","slug":"jovale-detecting-human-actions-in-video-using","title":"JoVALE: Detecting Human Actions in Video Using Audiovisual and Language Contexts","date":"2024-12-18","arxiv_id":"2412.13708","repositories_listed":1,"syntology":null},{"url":"/paper/on-occlusions-in-video-action-detection-1","slug":"on-occlusions-in-video-action-detection-1","title":"On Occlusions in Video Action Detection: Benchmark Datasets And Training Recipes","date":"2024-10-25","arxiv_id":"2410.19553","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/on-occlusions-in-video-action-detection-1#ran","syntology_url":"https://syntology.ai/paper/2410.19553","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.19553"}},"official":{"repos":["rajatmodi62/occludedactionbenchmark"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/benchmarking-deep-learning-models-on-nvidia","slug":"benchmarking-deep-learning-models-on-nvidia","title":"Benchmarking Deep Learning Models on NVIDIA Jetson Nano for Real-Time Systems: An Empirical Investigation","date":"2024-06-25","arxiv_id":"2406.17749","repositories_listed":1,"syntology":null},{"url":"/paper/generative-model-based-feature-knowledge","slug":"generative-model-based-feature-knowledge","title":"Generative Model-based Feature Knowledge Distillation for Action Recognition","date":"2023-12-14","arxiv_id":"2312.08644","repositories_listed":1,"syntology":null},{"url":"/paper/semi-supervised-active-learning-for-video","slug":"semi-supervised-active-learning-for-video","title":"Semi-supervised Active Learning for Video Action Detection","date":"2023-12-12","arxiv_id":"2312.07169","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":2,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/semi-supervised-active-learning-for-video#ran","syntology_url":"https://syntology.ai/paper/2312.07169","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.07169"}},"official":{"repos":["akash2907/semi-sup-active-learning"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/e-2tad-an-energy-efficient-tracking-based","slug":"e-2tad-an-energy-efficient-tracking-based","title":"E^2TAD: An Energy-Efficient Tracking-based Action Detector","date":"2022-04-09","arxiv_id":"2204.04416","repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-semi-supervised-learning-for-video","slug":"end-to-end-semi-supervised-learning-for-video","title":"End-to-End Semi-Supervised Learning for Video Action Detection","date":"2022-03-08","arxiv_id":"2203.04251","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/end-to-end-semi-supervised-learning-for-video#ran","syntology_url":"https://syntology.ai/paper/2203.04251","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.04251"}},"official":{"repos":["AKASH2907/End-to-End-Semi-Supervised-Learning-for-Video-Action-Detection"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-stronger-baseline-for-ego-centric-action","slug":"a-stronger-baseline-for-ego-centric-action","title":"A Stronger Baseline for Ego-Centric Action Detection","date":"2021-06-13","arxiv_id":"2106.06942","repositories_listed":1,"syntology":null},{"url":"/paper/tuber-tube-transformer-for-action-detection","slug":"tuber-tube-transformer-for-action-detection","title":"TubeR: Tubelet Transformer for Video Action Detection","date":"2021-04-02","arxiv_id":"2104.00969","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":2,"n_honours":3,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/tuber-tube-transformer-for-action-detection#ran","syntology_url":"https://syntology.ai/paper/2104.00969","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.00969"}},"official":null}},{"url":"/paper/stage-spatio-temporal-attention-on-graph","slug":"stage-spatio-temporal-attention-on-graph","title":"Video action detection by learning graph-based spatio-temporal interactions","date":"2019-12-09","arxiv_id":"1912.04316","repositories_listed":1,"syntology":null},{"url":"/paper/step-spatio-temporal-progressive-learning-for","slug":"step-spatio-temporal-progressive-learning-for","title":"STEP: Spatio-Temporal Progressive Learning for Video Action Detection","date":"2019-04-19","arxiv_id":"1904.09288","repositories_listed":1,"syntology":null},{"url":"/paper/tube-convolutional-neural-network-t-cnn-for","slug":"tube-convolutional-neural-network-t-cnn-for","title":"Tube Convolutional Neural Network (T-CNN) for Action Detection in Videos","date":"2017-03-30","arxiv_id":"1703.10664","repositories_listed":1,"syntology":null},{"url":null,"slug":"jarvis-detecting-actions-in-video-using","title":"JARViS: Detecting Actions in Video Using Unified Actor-Scene Context Relation Modeling","date":"2024-08-07","arxiv_id":"2408.03612","repositories_listed":0,"syntology":null},{"url":null,"slug":"classification-matters-improving-video-action","title":"Classification Matters: Improving Video Action Detection with Class-Specific Attention","date":"2024-07-29","arxiv_id":"2407.19698","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-grammatical-compositional-model-for-video","title":"A Grammatical Compositional Model for Video Action Detection","date":"2023-10-04","arxiv_id":"2310.02887","repositories_listed":0,"syntology":null},{"url":null,"slug":"m-3-3d-learning-3d-priors-using-multi-modal","title":"M$^{3}$3D: Learning 3D priors using Multi-Modal Masked Autoencoders for 2D image and video understanding","date":"2023-09-26","arxiv_id":"2309.15313","repositories_listed":0,"syntology":null},{"url":null,"slug":"mrsn-multi-relation-support-network-for-video","title":"MRSN: Multi-Relation Support Network for Video Action Detection","date":"2023-04-24","arxiv_id":"2304.11975","repositories_listed":0,"syntology":null},{"url":null,"slug":"cycleacr-cycle-modeling-of-actor-context","title":"CycleACR: Cycle Modeling of Actor-Context Relations for Video Action Detection","date":"2023-03-28","arxiv_id":"2303.16118","repositories_listed":0,"syntology":null},{"url":null,"slug":"context-understanding-in-computer-vision-a","title":"Context Understanding in Computer Vision: A Survey","date":"2023-02-10","arxiv_id":"2302.05011","repositories_listed":0,"syntology":null},{"url":null,"slug":"hybrid-active-learning-via-deep-clustering","title":"Hybrid Active Learning via Deep Clustering for Video Action Detection","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"video-action-detection-analysing-limitations","title":"Video Action Detection: Analysing Limitations and Challenges","date":"2022-04-17","arxiv_id":"2204.07892","repositories_listed":0,"syntology":null},{"url":null,"slug":"context-lstm-a-robust-classifier-for-video","title":"Context-LSTM: a robust classifier for video detection on UCF101","date":"2022-03-13","arxiv_id":"2203.06610","repositories_listed":0,"syntology":null},{"url":null,"slug":"watch-only-once-an-end-to-end-video-action","title":"Watch Only Once: An End-to-End Video Action Detection Framework","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"long-short-term-relation-networks-for-video","title":"Long Short-Term Relation Networks for Video Action Detection","date":"2020-03-31","arxiv_id":"2003.14065","repositories_listed":0,"syntology":null},{"url":null,"slug":"unconstrained-monocular-3d-human-pose","title":"Unconstrained Monocular 3D Human Pose Estimation by Action Detection and Cross-Modality Regression Forest","date":"2013-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"syntology_records":8,"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":8,"papers_where_code_ran_first_page":"/task/video-action-detection/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/video-action-detection/papers/ran/1","json":"/task/video-action-detection/papers/ran/1.json","rows":8}],"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":"daf5a105a4477ca5243d9d2a58bc934aacea2b31203c1db15075a6a1de9db2f9","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}