{"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-localization/papers/2","list_of":"/task/action-localization","task":"Action Localization","archive":{"snapshot":"2025-07-28"},"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)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":2,"pages_in_order":4,"rows_per_page":100,"rows":[101,200],"of":369,"counts":{"archive_papers_tagged":369,"with_a_code_link":169,"where_syntology_ran_a_sample":23,"not_listed_spam_title":0,"listed":369,"listed_where_code_ran":23,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":17,"every_run_a_failure_of_syntologys_instrument":6,"listed_with_a_run_with_no_instrument_failure":17,"listed_every_run_a_failure_of_syntologys_instrument":6,"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"},"first_page":"/task/action-localization","prev":"/task/action-localization","next":"/task/action-localization/papers/3","papers":[{"url":"/paper/tvnet-temporal-voting-network-for-action","slug":"tvnet-temporal-voting-network-for-action","title":"TVNet: Temporal Voting Network for Action Localization","date":"2022-01-02","arxiv_id":"2201.00434","repositories_listed":1,"syntology":null},{"url":"/paper/everything-at-once-multi-modal-fusion-1","slug":"everything-at-once-multi-modal-fusion-1","title":"Everything at Once - Multi-Modal Fusion Transformer for Video Retrieval","date":"2022-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/set-supervised-action-learning-in-procedural","slug":"set-supervised-action-learning-in-procedural","title":"Set-Supervised Action Learning in Procedural Task Videos via Pairwise Order Consistency","date":"2022-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/temporal-action-proposal-generation-with-1","slug":"temporal-action-proposal-generation-with-1","title":"Temporal Action Proposal Generation with Background Constraint","date":"2021-12-15","arxiv_id":"2112.07984","repositories_listed":1,"syntology":null},{"url":"/paper/everything-at-once-multi-modal-fusion","slug":"everything-at-once-multi-modal-fusion","title":"Everything at Once -- Multi-modal Fusion Transformer for Video Retrieval","date":"2021-12-08","arxiv_id":"2112.04446","repositories_listed":1,"syntology":null},{"url":"/paper/background-click-supervision-for-temporal","slug":"background-click-supervision-for-temporal","title":"Background-Click Supervision for Temporal Action Localization","date":"2021-11-24","arxiv_id":"2111.12449","repositories_listed":1,"syntology":null},{"url":"/paper/towards-active-vision-for-action-localization","slug":"towards-active-vision-for-action-localization","title":"Towards Active Vision for Action Localization with Reactive Control and Predictive Learning","date":"2021-11-09","arxiv_id":"2111.05448","repositories_listed":1,"syntology":null},{"url":"/paper/korsal-key-point-detection-based-online-real","slug":"korsal-key-point-detection-based-online-real","title":"KORSAL: Key-point Detection based Online Real-Time Spatio-Temporal Action Localization","date":"2021-11-05","arxiv_id":"2111.03319","repositories_listed":1,"syntology":null},{"url":"/paper/diagnosing-errors-in-video-relation-detectors","slug":"diagnosing-errors-in-video-relation-detectors","title":"Diagnosing Errors in Video Relation Detectors","date":"2021-10-25","arxiv_id":"2110.13110","repositories_listed":1,"syntology":null},{"url":"/paper/few-shot-temporal-action-localization-with","slug":"few-shot-temporal-action-localization-with","title":"Few-Shot Temporal Action Localization with Query Adaptive Transformer","date":"2021-10-20","arxiv_id":"2110.10552","repositories_listed":1,"syntology":null},{"url":"/paper/foreground-action-consistency-network-for","slug":"foreground-action-consistency-network-for","title":"Foreground-Action Consistency Network for Weakly Supervised Temporal Action Localization","date":"2021-08-14","arxiv_id":"2108.06524","repositories_listed":1,"syntology":null},{"url":"/paper/learning-action-completeness-from-points-for","slug":"learning-action-completeness-from-points-for","title":"Learning Action Completeness from Points for Weakly-supervised Temporal Action Localization","date":"2021-08-11","arxiv_id":"2108.05029","repositories_listed":1,"syntology":null},{"url":"/paper/temporal-action-localization-using-gated","slug":"temporal-action-localization-using-gated","title":"Temporal Action Localization Using Gated Recurrent Units","date":"2021-08-07","arxiv_id":"2108.03375","repositories_listed":1,"syntology":null},{"url":"/paper/video-contrastive-learning-with-global","slug":"video-contrastive-learning-with-global","title":"Video Contrastive Learning with Global Context","date":"2021-08-05","arxiv_id":"2108.02722","repositories_listed":1,"syntology":{"n":8,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/video-contrastive-learning-with-global#ran","syntology_url":"https://syntology.ai/paper/2108.02722","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.02722"}},"official":{"repos":["amazon-research/video-contrastive-learning"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/cross-modal-consensus-network-forweakly","slug":"cross-modal-consensus-network-forweakly","title":"Cross-modal Consensus Network forWeakly Supervised Temporal Action Localization","date":"2021-07-27","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/enriching-local-and-global-contexts-for","slug":"enriching-local-and-global-contexts-for","title":"Enriching Local and Global Contexts for Temporal Action Localization","date":"2021-07-27","arxiv_id":"2107.12960","repositories_listed":1,"syntology":null},{"url":"/paper/hear-me-out-fusional-approaches-for-audio","slug":"hear-me-out-fusional-approaches-for-audio","title":"Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action Localization","date":"2021-06-27","arxiv_id":"2106.14118","repositories_listed":1,"syntology":null},{"url":"/paper/babel-bodies-action-and-behavior-with-english","slug":"babel-bodies-action-and-behavior-with-english","title":"BABEL: Bodies, Action and Behavior with English Labels","date":"2021-06-17","arxiv_id":"2106.09696","repositories_listed":1,"syntology":null},{"url":"/paper/few-shot-action-localization-without-knowing","slug":"few-shot-action-localization-without-knowing","title":"Few-Shot Action Localization without Knowing Boundaries","date":"2021-06-08","arxiv_id":"2106.04150","repositories_listed":1,"syntology":null},{"url":"/paper/fineaction-a-fined-video-dataset-for-temporal","slug":"fineaction-a-fined-video-dataset-for-temporal","title":"FineAction: A Fine-Grained Video Dataset for Temporal Action Localization","date":"2021-05-24","arxiv_id":"2105.11107","repositories_listed":1,"syntology":null},{"url":"/paper/multisports-a-multi-person-video-dataset-of","slug":"multisports-a-multi-person-video-dataset-of","title":"MultiSports: A Multi-Person Video Dataset of Spatio-Temporally Localized Sports Actions","date":"2021-05-16","arxiv_id":"2105.07404","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-clustering-networks-for-self","slug":"multimodal-clustering-networks-for-self","title":"Multimodal Clustering Networks for Self-supervised Learning from Unlabeled Videos","date":"2021-04-26","arxiv_id":"2104.12671","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"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) · 0 unverified","sample_list":"/paper/multimodal-clustering-networks-for-self#ran","syntology_url":"https://syntology.ai/paper/2104.12671","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.12671"}},"official":{"repos":["brian7685/Multimodal-Clustering-Network"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/object-priors-for-classifying-and-localizing","slug":"object-priors-for-classifying-and-localizing","title":"Object Priors for Classifying and Localizing Unseen Actions","date":"2021-04-10","arxiv_id":"2104.04715","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/cola-weakly-supervised-temporal-action","slug":"cola-weakly-supervised-temporal-action","title":"CoLA: Weakly-Supervised Temporal Action Localization with Snippet Contrastive Learning","date":"2021-03-30","arxiv_id":"2103.16392","repositories_listed":1,"syntology":null},{"url":"/paper/learning-salient-boundary-feature-for-anchor","slug":"learning-salient-boundary-feature-for-anchor","title":"Learning Salient Boundary Feature for Anchor-free Temporal Action Localization","date":"2021-03-24","arxiv_id":"2103.13137","repositories_listed":1,"syntology":null},{"url":"/paper/temporal-context-aggregation-network-for","slug":"temporal-context-aggregation-network-for","title":"Temporal Context Aggregation Network for Temporal Action Proposal Refinement","date":"2021-03-24","arxiv_id":"2103.13141","repositories_listed":1,"syntology":null},{"url":"/paper/the-blessings-of-unlabeled-background-in","slug":"the-blessings-of-unlabeled-background-in","title":"The Blessings of Unlabeled Background in Untrimmed Videos","date":"2021-03-24","arxiv_id":"2103.13183","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":3,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"5 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","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"}},"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"]}}},{"url":"/paper/single-run-action-detector-over-video-stream","slug":"single-run-action-detector-over-video-stream","title":"Single Run Action Detector over Video Stream -- A Privacy Preserving Approach","date":"2021-02-05","arxiv_id":"2102.03391","repositories_listed":1,"syntology":null},{"url":"/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,"repositories_listed":1,"syntology":null},{"url":"/paper/a-hybrid-attention-mechanism-for-weakly","slug":"a-hybrid-attention-mechanism-for-weakly","title":"A Hybrid Attention Mechanism for Weakly-Supervised Temporal Action Localization","date":"2021-01-03","arxiv_id":"2101.00545","repositories_listed":1,"syntology":null},{"url":"/paper/multi-shot-temporal-event-localization-a","slug":"multi-shot-temporal-event-localization-a","title":"Multi-shot Temporal Event Localization: a Benchmark","date":"2020-12-17","arxiv_id":"2012.09434","repositories_listed":1,"syntology":null},{"url":"/paper/towards-improving-spatiotemporal-action","slug":"towards-improving-spatiotemporal-action","title":"Towards Improving Spatiotemporal Action Recognition in Videos","date":"2020-12-15","arxiv_id":"2012.08097","repositories_listed":1,"syntology":null},{"url":"/paper/d2-net-weakly-supervised-action-localization","slug":"d2-net-weakly-supervised-action-localization","title":"D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations","date":"2020-12-11","arxiv_id":"2012.06440","repositories_listed":1,"syntology":null},{"url":"/paper/video-self-stitching-graph-network-for","slug":"video-self-stitching-graph-network-for","title":"Video Self-Stitching Graph Network for Temporal Action Localization","date":"2020-11-30","arxiv_id":"2011.14598","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"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) · 0 unverified","sample_list":"/paper/video-self-stitching-graph-network-for#ran","syntology_url":"https://syntology.ai/paper/2011.14598","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.14598"}},"official":{"repos":["coolbay/VSGN"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/tsp-temporally-sensitive-pretraining-of-video","slug":"tsp-temporally-sensitive-pretraining-of-video","title":"TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks","date":"2020-11-23","arxiv_id":"2011.11479","repositories_listed":1,"syntology":null},{"url":"/paper/bsn-complementary-boundary-regressor-with","slug":"bsn-complementary-boundary-regressor-with","title":"BSN++: Complementary Boundary Regressor with Scale-Balanced Relation Modeling for Temporal Action Proposal Generation","date":"2020-09-15","arxiv_id":"2009.07641","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/bsn-complementary-boundary-regressor-with#ran","syntology_url":"https://syntology.ai/paper/2009.07641","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.07641"}},"official":null}},{"url":"/paper/learning-to-localize-actions-from-moments","slug":"learning-to-localize-actions-from-moments","title":"Learning to Localize Actions from Moments","date":"2020-08-31","arxiv_id":"2008.13705","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"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) · 2 unverified","sample_list":"/paper/learning-to-localize-actions-from-moments#ran","syntology_url":"https://syntology.ai/paper/2008.13705","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.13705"}},"official":{"repos":["FuchenUSTC/AherNet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/revisiting-anchor-mechanisms-for-temporal","slug":"revisiting-anchor-mechanisms-for-temporal","title":"Revisiting Anchor Mechanisms for Temporal Action Localization","date":"2020-08-22","arxiv_id":"2008.09837","repositories_listed":1,"syntology":null},{"url":"/paper/localizing-the-common-action-among-a-few","slug":"localizing-the-common-action-among-a-few","title":"Localizing the Common Action Among a Few Videos","date":"2020-08-13","arxiv_id":"2008.05826","repositories_listed":1,"syntology":null},{"url":"/paper/cbr-net-cascade-boundary-refinement-network","slug":"cbr-net-cascade-boundary-refinement-network","title":"CBR-Net: Cascade Boundary Refinement Network for Action Detection: Submission to ActivityNet Challenge 2020 (Task 1)","date":"2020-06-13","arxiv_id":"2006.07526","repositories_listed":1,"syntology":null},{"url":"/paper/learning-temporal-co-attention-models-for","slug":"learning-temporal-co-attention-models-for","title":"Learning Temporal Co-Attention Models for Unsupervised Video Action Localization","date":"2020-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/weakly-supervised-action-localization-with-2","slug":"weakly-supervised-action-localization-with-2","title":"Weakly-Supervised Action Localization with Expectation-Maximization Multi-Instance Learning","date":"2020-03-31","arxiv_id":"2004.00163","repositories_listed":1,"syntology":null},{"url":"/paper/weakly-supervised-action-localization-by-2","slug":"weakly-supervised-action-localization-by-2","title":"Weakly-Supervised Action Localization by Generative Attention Modeling","date":"2020-03-27","arxiv_id":"2003.12424","repositories_listed":1,"syntology":null},{"url":"/paper/sf-net-single-frame-supervision-for-temporal","slug":"sf-net-single-frame-supervision-for-temporal","title":"SF-Net: Single-Frame Supervision for Temporal Action Localization","date":"2020-03-15","arxiv_id":"2003.06845","repositories_listed":1,"syntology":null},{"url":"/paper/constraining-temporal-relationship-for-action","slug":"constraining-temporal-relationship-for-action","title":"Bottom-Up Temporal Action Localization with Mutual Regularization","date":"2020-02-18","arxiv_id":"2002.07358","repositories_listed":1,"syntology":null},{"url":"/paper/weakly-supervised-temporal-action-1","slug":"weakly-supervised-temporal-action-1","title":"Weakly Supervised Temporal Action Localization Using Deep Metric Learning","date":"2020-01-21","arxiv_id":"2001.07793","repositories_listed":1,"syntology":null},{"url":"/paper/comprehensive-soccer-video-understanding","slug":"comprehensive-soccer-video-understanding","title":"SoccerDB: A Large-Scale Database for Comprehensive Video Understanding","date":"2019-12-10","arxiv_id":"1912.04465","repositories_listed":1,"syntology":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/gaussian-temporal-awareness-networks-for-1","slug":"gaussian-temporal-awareness-networks-for-1","title":"Gaussian Temporal Awareness Networks for Action Localization","date":"2019-09-09","arxiv_id":"1909.03877","repositories_listed":1,"syntology":null},{"url":"/paper/graph-convolutional-networks-for-temporal","slug":"graph-convolutional-networks-for-temporal","title":"Graph Convolutional Networks for Temporal Action Localization","date":"2019-09-07","arxiv_id":"1909.03252","repositories_listed":1,"syntology":null},{"url":"/paper/3c-net-category-count-and-center-loss-for","slug":"3c-net-category-count-and-center-loss-for","title":"3C-Net: Category Count and Center Loss for Weakly-Supervised Action Localization","date":"2019-08-22","arxiv_id":"1908.08216","repositories_listed":1,"syntology":null},{"url":"/paper/completeness-modeling-and-context-separation","slug":"completeness-modeling-and-context-separation","title":"Completeness Modeling and Context Separation for Weakly Supervised Temporal Action Localization","date":"2019-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/190411953","slug":"190411953","title":"Temporal Unet: Sample Level Human Action Recognition using WiFi","date":"2019-04-19","arxiv_id":"1904.11953","repositories_listed":1,"syntology":null},{"url":"/paper/refineloc-iterative-refinement-for-weakly","slug":"refineloc-iterative-refinement-for-weakly","title":"RefineLoc: Iterative Refinement for Weakly-Supervised Action Localization","date":"2019-03-30","arxiv_id":"1904.00227","repositories_listed":1,"syntology":null},{"url":"/paper/a-perceptual-prediction-framework-for-self","slug":"a-perceptual-prediction-framework-for-self","title":"A Perceptual Prediction Framework for Self Supervised Event Segmentation","date":"2018-11-12","arxiv_id":"1811.04869","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/a-perceptual-prediction-framework-for-self#ran","syntology_url":"https://syntology.ai/paper/1811.04869","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.04869"}},"official":{"repos":["CVPRUSFTampa/EventSegmentation"],"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/actor-centric-relation-network","slug":"actor-centric-relation-network","title":"Actor-Centric Relation Network","date":"2018-07-28","arxiv_id":"1807.10982","repositories_listed":1,"syntology":null},{"url":"/paper/diagnosing-error-in-temporal-action-detectors","slug":"diagnosing-error-in-temporal-action-detectors","title":"Diagnosing Error in Temporal Action Detectors","date":"2018-07-27","arxiv_id":"1807.10706","repositories_listed":1,"syntology":null},{"url":"/paper/autoloc-weakly-supervised-temporal-action","slug":"autoloc-weakly-supervised-temporal-action","title":"AutoLoc: Weakly-supervised Temporal Action Localization","date":"2018-07-22","arxiv_id":"1807.08333","repositories_listed":1,"syntology":null},{"url":"/paper/a-flexible-model-for-training-action","slug":"a-flexible-model-for-training-action","title":"A flexible model for training action localization with varying levels of supervision","date":"2018-06-29","arxiv_id":"1806.11328","repositories_listed":1,"syntology":null},{"url":"/paper/action-search-spotting-actions-in-videos-and","slug":"action-search-spotting-actions-in-videos-and","title":"Action Search: Spotting Actions in Videos and Its Application to Temporal Action Localization","date":"2017-06-13","arxiv_id":"1706.04269","repositories_listed":1,"syntology":null},{"url":"/paper/chained-multi-stream-networks-exploiting-pose","slug":"chained-multi-stream-networks-exploiting-pose","title":"Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection","date":"2017-04-03","arxiv_id":"1704.00616","repositories_listed":1,"syntology":null},{"url":"/paper/turn-tap-temporal-unit-regression-network-for","slug":"turn-tap-temporal-unit-regression-network-for","title":"TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals","date":"2017-03-17","arxiv_id":"1703.06189","repositories_listed":1,"syntology":null},{"url":"/paper/cdc-convolutional-de-convolutional-networks","slug":"cdc-convolutional-de-convolutional-networks","title":"CDC: Convolutional-De-Convolutional Networks for Precise Temporal Action Localization in Untrimmed Videos","date":"2017-03-04","arxiv_id":"1703.01515","repositories_listed":1,"syntology":null},{"url":"/paper/videolstm-convolves-attends-and-flows-for","slug":"videolstm-convolves-attends-and-flows-for","title":"VideoLSTM Convolves, Attends and Flows for Action Recognition","date":"2016-07-06","arxiv_id":"1607.01794","repositories_listed":1,"syntology":null},{"url":"/paper/temporal-action-localization-in-untrimmed","slug":"temporal-action-localization-in-untrimmed","title":"Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs","date":"2016-01-09","arxiv_id":"1601.02129","repositories_listed":1,"syntology":null},{"url":"/paper/temporal-localization-of-fine-grained-actions","slug":"temporal-localization-of-fine-grained-actions","title":"Temporal Localization of Fine-Grained Actions in Videos by Domain Transfer from Web Images","date":"2015-04-04","arxiv_id":"1504.00983","repositories_listed":1,"syntology":null},{"url":"/paper/learning-and-transferring-mid-level-image","slug":"learning-and-transferring-mid-level-image","title":"Learning and Transferring Mid-Level Image Representations using Convolutional Neural Networks","date":"2014-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":null,"slug":"llm-powered-query-expansion-for-enhancing","title":"LLM-powered Query Expansion for Enhancing Boundary Prediction in Language-driven Action Localization","date":"2025-05-30","arxiv_id":"2505.24282","repositories_listed":0,"syntology":null},{"url":null,"slug":"clip-ae-clip-assisted-cross-view-audio-visual","title":"CLIP-AE: CLIP-assisted Cross-view Audio-Visual Enhancement for Unsupervised Temporal Action Localization","date":"2025-05-29","arxiv_id":"2505.23524","repositories_listed":0,"syntology":null},{"url":null,"slug":"protal-a-drag-and-link-video-programming","title":"ProTAL: A Drag-and-Link Video Programming Framework for Temporal Action Localization","date":"2025-05-23","arxiv_id":"2505.17555","repositories_listed":0,"syntology":null},{"url":null,"slug":"action-spotting-and-precise-event-detection","title":"Action Spotting and Precise Event Detection in Sports: Datasets, Methods, and Challenges","date":"2025-05-06","arxiv_id":"2505.03991","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridge-the-gap-from-weak-to-full-supervision","title":"Bridge the Gap: From Weak to Full Supervision for Temporal Action Localization with PseudoFormer","date":"2025-04-21","arxiv_id":"2504.14860","repositories_listed":0,"syntology":null},{"url":null,"slug":"chain-of-thought-textual-reasoning-for-few","title":"Chain-of-Thought Textual Reasoning for Few-shot Temporal Action Localization","date":"2025-04-18","arxiv_id":"2504.13460","repositories_listed":0,"syntology":null},{"url":null,"slug":"minimalistic-video-saliency-prediction-via","title":"Minimalistic Video Saliency Prediction via Efficient Decoder & Spatio Temporal Action Cues","date":"2025-02-01","arxiv_id":"2502.00397","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-pseudo-label-guided-learning-for","title":"Rethinking Pseudo-Label Guided Learning for Weakly Supervised Temporal Action Localization from the Perspective of Noise Correction","date":"2025-01-19","arxiv_id":"2501.11124","repositories_listed":0,"syntology":null},{"url":null,"slug":"boosting-point-supervised-temporal-action","title":"Boosting Point-Supervised Temporal Action Localization through Integrating Query Reformation and Optimal Transport","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"weakly-supervised-temporal-action-9","title":"Weakly Supervised Temporal Action Localization via Dual-Prior Collaborative Learning Guided by Multimodal Large Language Models","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dave-diverse-atomic-visual-elements-dataset","title":"DAVE: Diverse Atomic Visual Elements Dataset with High Representation of Vulnerable Road Users in Complex and Unpredictable Environments","date":"2024-12-28","arxiv_id":"2412.20042","repositories_listed":0,"syntology":null},{"url":null,"slug":"stitch-contrast-and-segment-learning-a-human","title":"Stitch Contrast and Segment_Learning a Human Action Segmentation Model Using Trimmed Skeleton Videos","date":"2024-12-19","arxiv_id":"2412.14988","repositories_listed":0,"syntology":null},{"url":null,"slug":"imuvie-pickup-timeline-action-localization","title":"IMUVIE: Pickup Timeline Action Localization via Motion Movies","date":"2024-11-19","arxiv_id":"2411.12689","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-top-probability-from-multi-view","title":"Rethinking Top Probability from Multi-view for Distracted Driver Behaviour Localization","date":"2024-11-19","arxiv_id":"2411.12525","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-mllms-guide-weakly-supervised-temporal","title":"Can MLLMs Guide Weakly-Supervised Temporal Action Localization Tasks?","date":"2024-11-13","arxiv_id":"2411.08466","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-action-localization-via-the","title":"Zero-shot Action Localization via the Confidence of Large Vision-Language Models","date":"2024-10-18","arxiv_id":"2410.14340","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-02957","title":"Online Temporal Action Localization with Memory-Augmented Transformer","date":"2024-08-06","arxiv_id":"2408.02957","repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-supervised-pipe-video-temporal-defect","title":"Semi-Supervised Pipe Video Temporal Defect Interval Localization","date":"2024-07-21","arxiv_id":"2407.15170","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-adaptive-pseudo-label-learning-for","title":"Towards Adaptive Pseudo-label Learning for Semi-Supervised Temporal Action Localization","date":"2024-07-10","arxiv_id":"2407.07673","repositories_listed":0,"syntology":null},{"url":null,"slug":"open-vocabulary-temporal-action-localization","title":"Open-Vocabulary Temporal Action Localization using Multimodal Guidance","date":"2024-06-21","arxiv_id":"2406.15556","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-multi-actor-social-activity","title":"Self-supervised Multi-actor Social Activity Understanding in Streaming Videos","date":"2024-06-20","arxiv_id":"2406.14472","repositories_listed":0,"syntology":null},{"url":null,"slug":"vitals-vision-transformer-for-action","title":"ViTALS: Vision Transformer for Action Localization in Surgical Nephrectomy","date":"2024-05-04","arxiv_id":"2405.02571","repositories_listed":0,"syntology":null},{"url":null,"slug":"stat-towards-generalizable-temporal-action","title":"STAT: Towards Generalizable Temporal Action Localization","date":"2024-04-20","arxiv_id":"2404.13311","repositories_listed":0,"syntology":null},{"url":null,"slug":"deeplocalization-using-change-point-detection","title":"DeepLocalization: Using change point detection for Temporal Action Localization","date":"2024-04-18","arxiv_id":"2404.12258","repositories_listed":0,"syntology":null},{"url":null,"slug":"localizing-moments-of-actions-in-untrimmed","title":"Localizing Moments of Actions in Untrimmed Videos of Infants with Autism Spectrum Disorder","date":"2024-04-08","arxiv_id":"2404.05849","repositories_listed":0,"syntology":null},{"url":null,"slug":"losa-long-short-range-adapter-for-scaling-end","title":"LoSA: Long-Short-range Adapter for Scaling End-to-End Temporal Action Localization","date":"2024-04-01","arxiv_id":"2404.01282","repositories_listed":0,"syntology":null},{"url":null,"slug":"plot-tal-prompt-learning-with-optimal","title":"PLOT-TAL -- Prompt Learning with Optimal Transport for Few-Shot Temporal Action Localization","date":"2024-03-27","arxiv_id":"2403.18915","repositories_listed":0,"syntology":null},{"url":null,"slug":"boosting-semi-supervised-temporal-action","title":"Boosting Semi-Supervised Temporal Action Localization by Learning from Non-Target Classes","date":"2024-03-17","arxiv_id":"2403.11189","repositories_listed":0,"syntology":null},{"url":null,"slug":"bid-boundary-interior-decoding-for","title":"BID: Boundary-Interior Decoding for Unsupervised Temporal Action Localization Pre-Trainin","date":"2024-03-12","arxiv_id":"2403.07354","repositories_listed":0,"syntology":null},{"url":null,"slug":"density-guided-label-smoothing-for-temporal","title":"Density-Guided Label Smoothing for Temporal Localization of Driving Actions","date":"2024-03-11","arxiv_id":"2403.06616","repositories_listed":0,"syntology":null},{"url":null,"slug":"cutup-and-detect-human-fall-detection-on","title":"Cutup and Detect: Human Fall Detection on Cutup Untrimmed Videos Using a Large Foundational Video Understanding Model","date":"2024-01-29","arxiv_id":"2401.16280","repositories_listed":0,"syntology":null}],"record_sha256":"3370d13dc4e2cbf3744df59354a22973b7ca53c62348f562d56d64c69326e301","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}