{"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/4","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":4,"pages_in_order":4,"rows_per_page":100,"rows":[301,369],"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/papers/3","next":null,"papers":[{"url":null,"slug":"action-localization-through-continual","title":"Action Localization through Continual Predictive Learning","date":"2020-03-26","arxiv_id":"2003.12185","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-novel-online-action-detection-framework","title":"A Novel Online Action Detection Framework from Untrimmed Video Streams","date":"2020-03-17","arxiv_id":"2003.07734","repositories_listed":0,"syntology":null},{"url":null,"slug":"weakly-supervised-multi-person-action","title":"Weakly-Supervised Multi-Person Action Recognition in 360$^{\\circ}$ Videos","date":"2020-02-09","arxiv_id":"2002.03266","repositories_listed":0,"syntology":null},{"url":null,"slug":"action-graphs-weakly-supervised-action","title":"Action Graphs: Weakly-supervised Action Localization with Graph Convolution Networks","date":"2020-02-04","arxiv_id":"2002.01449","repositories_listed":0,"syntology":null},{"url":null,"slug":"191104469","title":"A Proposed Artificial intelligence Model for Real-Time Human Action Localization and Tracking","date":"2019-11-09","arxiv_id":"1911.04469","repositories_listed":0,"syntology":null},{"url":null,"slug":"temporal-action-localization-using-long-short","title":"Temporal Action Localization using Long Short-Term Dependency","date":"2019-11-04","arxiv_id":"1911.01060","repositories_listed":0,"syntology":null},{"url":null,"slug":"lpat-learning-to-predict-adaptive-threshold","title":"Towards Train-Test Consistency for Semi-supervised Temporal Action Localization","date":"2019-10-24","arxiv_id":"1910.11285","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-action-sequence-classification","title":"Human Action Sequence Classification","date":"2019-10-07","arxiv_id":"1910.02602","repositories_listed":0,"syntology":null},{"url":"/paper/hierarchical-self-attention-network-for","slug":"hierarchical-self-attention-network-for","title":"Hierarchical Self-Attention Network for Action Localization in Videos","date":"2019-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/weakly-supervised-temporal-action","slug":"weakly-supervised-temporal-action","title":"Weakly Supervised Temporal Action Localization Through Contrast Based Evaluation Networks","date":"2019-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"weakly-supervised-action-localization-with","title":"Weakly-supervised Action Localization with Background Modeling","date":"2019-08-19","arxiv_id":"1908.06552","repositories_listed":0,"syntology":null},{"url":null,"slug":"three-branches-detecting-actions-with-richer","title":"Three Branches: Detecting Actions With Richer Features","date":"2019-08-13","arxiv_id":"1908.04519","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-seeded-sequence-growing-for","title":"Adversarial Seeded Sequence Growing for Weakly-Supervised Temporal Action Localization","date":"2019-08-07","arxiv_id":"1908.02422","repositories_listed":0,"syntology":null},{"url":null,"slug":"scale-matters-temporal-scale-aggregation","title":"Scale Matters: Temporal Scale Aggregation Network for Precise Action Localization in Untrimmed Videos","date":"2019-08-02","arxiv_id":"1908.00707","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-granularity-fusion-network-for-proposal","title":"Multi-Granularity Fusion Network for Proposal and Activity Localization: Submission to ActivityNet Challenge 2019 Task 1 and Task 2","date":"2019-07-29","arxiv_id":"1907.12223","repositories_listed":0,"syntology":null},{"url":null,"slug":"submission-to-activitynet-challenge-2019-task","title":"Submission to ActivityNet Challenge 2019: Task B Spatio-temporal Action Localization","date":"2019-07-25","arxiv_id":"1907.10837","repositories_listed":0,"syntology":null},{"url":null,"slug":"localizing-unseen-activities-in-video-via","title":"Localizing Unseen Activities in Video via Image Query","date":"2019-06-28","arxiv_id":"1906.12165","repositories_listed":0,"syntology":null},{"url":null,"slug":"vireojd-mm-at-activity-detection-in-extended","title":"vireoJD-MM at Activity Detection in Extended Videos","date":"2019-06-20","arxiv_id":"1906.08547","repositories_listed":0,"syntology":null},{"url":null,"slug":"trimmed-action-recognition-dense-captioning","title":"Trimmed Action Recognition, Dense-Captioning Events in Videos, and Spatio-temporal Action Localization with Focus on ActivityNet Challenge 2019","date":"2019-06-14","arxiv_id":"1906.07016","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-action-localization-by-progressive-1","title":"Improving Action Localization by Progressive Cross-stream Cooperation","date":"2019-05-28","arxiv_id":"1905.11575","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-feature-representation-and-training","title":"Exploring Feature Representation and Training strategies in Temporal Action Localization","date":"2019-05-25","arxiv_id":"1905.10608","repositories_listed":0,"syntology":null},{"url":"/paper/marginalized-average-attentional-network-for-1","slug":"marginalized-average-attentional-network-for-1","title":"Marginalized Average Attentional Network for Weakly-Supervised Learning","date":"2019-05-21","arxiv_id":"1905.08586","repositories_listed":0,"syntology":null},{"url":"/paper/neural-message-passing-on-hybrid-spatio","slug":"neural-message-passing-on-hybrid-spatio","title":"Representation Learning on Visual-Symbolic Graphs for Video Understanding","date":"2019-05-17","arxiv_id":"1905.07385","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatio-temporal-action-localization-in-a","title":"Spatio-Temporal Action Localization in a Weakly Supervised Setting","date":"2019-05-06","arxiv_id":"1905.02171","repositories_listed":0,"syntology":null},{"url":null,"slug":"weakly-supervised-gaussian-networks-for","title":"Weakly Supervised Gaussian Networks for Action Detection","date":"2019-04-16","arxiv_id":"1904.07774","repositories_listed":0,"syntology":null},{"url":null,"slug":"progress-regression-rnn-for-online-spatial","title":"Progress Regression RNN for Online Spatial-Temporal Action Localization in Unconstrained Videos","date":"2019-03-01","arxiv_id":"1903.00304","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-frame-segmentation-networks-for","title":"Exploring Frame Segmentation Networks for Temporal Action Localization","date":"2019-02-14","arxiv_id":"1902.05488","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatio-temporal-action-recognition-a-survey","title":"Spatio-temporal Action Recognition: A Survey","date":"2019-01-27","arxiv_id":"1901.09403","repositories_listed":0,"syntology":null},{"url":null,"slug":"cricket-stroke-extraction-towards-creation-of","title":"Cricket stroke extraction: Towards creation of a large-scale cricket actions dataset","date":"2019-01-10","arxiv_id":"1901.03107","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-discriminative-motion-features","title":"Learning Discriminative Motion Features Through Detection","date":"2018-12-11","arxiv_id":"1812.04172","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-modal-capsule-routing-for-actor-and","title":"Multi-modal Capsule Routing for Actor and Action Video Segmentation Conditioned on Natural Language Queries","date":"2018-12-02","arxiv_id":"1812.00303","repositories_listed":0,"syntology":null},{"url":null,"slug":"blp-boundary-likelihood-pinpointing-networks","title":"BLP -- Boundary Likelihood Pinpointing Networks for Accurate Temporal Action Localization","date":"2018-11-06","arxiv_id":"1811.02189","repositories_listed":0,"syntology":null},{"url":null,"slug":"cascaded-pyramid-mining-network-for-weakly","title":"Cascaded Pyramid Mining Network for Weakly Supervised Temporal Action Localization","date":"2018-10-28","arxiv_id":"1810.11794","repositories_listed":0,"syntology":null},{"url":"/paper/autoloc-weakly-supervised-temporal-action-1","slug":"autoloc-weakly-supervised-temporal-action-1","title":"AutoLoc: Weakly-supervised Temporal Action Localization in Untrimmed Videos","date":"2018-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"what-do-i-annotate-next-an-empirical-study-of","title":"What do I Annotate Next? An Empirical Study of Active Learning for Action Localization","date":"2018-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/a-better-baseline-for-ava","slug":"a-better-baseline-for-ava","title":"A Better Baseline for AVA","date":"2018-07-26","arxiv_id":"1807.10066","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatio-temporal-instance-learning-action","title":"Spatio-Temporal Instance Learning: Action Tubes from Class Supervision","date":"2018-07-08","arxiv_id":"1807.02800","repositories_listed":0,"syntology":null},{"url":null,"slug":"yh-technologies-at-activitynet-challenge-2018","title":"YH Technologies at ActivityNet Challenge 2018","date":"2018-06-29","arxiv_id":"1807.00686","repositories_listed":0,"syntology":null},{"url":null,"slug":"modeling-spatio-temporal-human-track","title":"Modeling Spatio-Temporal Human Track Structure for Action Localization","date":"2018-06-28","arxiv_id":"1806.11008","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-shot-action-localization-by-learning","title":"One-Shot Action Localization by Learning Sequence Matching Network","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"pointly-supervised-action-localization","title":"Pointly-Supervised Action Localization","date":"2018-05-29","arxiv_id":"1805.11333","repositories_listed":0,"syntology":null},{"url":null,"slug":"videocapsulenet-a-simplified-network-for","title":"VideoCapsuleNet: A Simplified Network for Action Detection","date":"2018-05-21","arxiv_id":"1805.08162","repositories_listed":0,"syntology":null},{"url":"/paper/rethinking-the-faster-r-cnn-architecture-for","slug":"rethinking-the-faster-r-cnn-architecture-for","title":"Rethinking the Faster R-CNN Architecture for Temporal Action Localization","date":"2018-04-20","arxiv_id":"1804.07667","repositories_listed":0,"syntology":null},{"url":null,"slug":"precise-temporal-action-localization-by","title":"Precise Temporal Action Localization by Evolving Temporal Proposals","date":"2018-04-13","arxiv_id":"1804.04803","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-action-discovery-and","title":"Unsupervised Action Discovery and Localization in Videos","date":"2017-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-temporal-preservation-networks-for","title":"Exploring Temporal Preservation Networks for Precise Temporal Action Localization","date":"2017-08-10","arxiv_id":"1708.03280","repositories_listed":0,"syntology":null},{"url":null,"slug":"localizing-actions-from-video-labels-and","title":"Localizing Actions from Video Labels and Pseudo-Annotations","date":"2017-07-28","arxiv_id":"1707.09143","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatial-aware-object-embeddings-for-zero-shot","title":"Spatial-Aware Object Embeddings for Zero-Shot Localization and Classification of Actions","date":"2017-07-28","arxiv_id":"1707.09145","repositories_listed":0,"syntology":null},{"url":"/paper/temporal-convolution-based-action-proposal","slug":"temporal-convolution-based-action-proposal","title":"Temporal Convolution Based Action Proposal: Submission to ActivityNet 2017","date":"2017-07-21","arxiv_id":"1707.06750","repositories_listed":0,"syntology":null},{"url":null,"slug":"detecting-parts-for-action-localization","title":"Detecting Parts for Action Localization","date":"2017-07-19","arxiv_id":"1707.06005","repositories_listed":0,"syntology":null},{"url":null,"slug":"generic-tubelet-proposals-for-action","title":"Generic Tubelet Proposals for Action Localization","date":"2017-05-30","arxiv_id":"1705.10861","repositories_listed":0,"syntology":null},{"url":null,"slug":"temporal-action-localization-by-structured","title":"Temporal Action Localization by Structured Maximal Sums","date":"2017-04-15","arxiv_id":"1704.04671","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-action-detection-in-untrimmed","title":"Efficient Action Detection in Untrimmed Videos via Multi-Task Learning","date":"2016-12-22","arxiv_id":"1612.07403","repositories_listed":0,"syntology":null},{"url":"/paper/social-scene-understanding-end-to-end-multi","slug":"social-scene-understanding-end-to-end-multi","title":"Social Scene Understanding: End-to-End Multi-Person Action Localization and Collective Activity Recognition","date":"2016-11-28","arxiv_id":"1611.09078","repositories_listed":0,"syntology":null},{"url":null,"slug":"distributed-adaptive-learning-of-graph","title":"Distributed Adaptive Learning of Graph Signals","date":"2016-09-20","arxiv_id":"1609.06100","repositories_listed":0,"syntology":null},{"url":null,"slug":"tubelets-unsupervised-action-proposals-from","title":"Tubelets: Unsupervised action proposals from spatiotemporal super-voxels","date":"2016-07-07","arxiv_id":"1607.02003","repositories_listed":0,"syntology":null},{"url":null,"slug":"predicting-the-where-and-what-of-actors-and","title":"Predicting the Where and What of Actors and Actions Through Online Action Localization","date":"2016-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"temporal-action-localization-with-pyramid-of","title":"Temporal Action Localization With Pyramid of Score Distribution Features","date":"2016-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"what-if-we-do-not-have-multiple-videos-of-the","title":"What If We Do Not Have Multiple Videos of the Same Action? -- Video Action Localization Using Web Images","date":"2016-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-caption-to-narrative-video-captioning","title":"Beyond Caption To Narrative: Video Captioning With Multiple Sentences","date":"2016-05-18","arxiv_id":"1605.05440","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-action-localization-with-sparse-spatial","title":"Human Action Localization with Sparse Spatial Supervision","date":"2016-05-17","arxiv_id":"1605.05197","repositories_listed":0,"syntology":null},{"url":null,"slug":"spot-on-action-localization-from-pointly","title":"Spot On: Action Localization from Pointly-Supervised Proposals","date":"2016-04-26","arxiv_id":"1604.07602","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":null,"slug":"action-localization-in-videos-through-context","title":"Action Localization in Videos Through Context Walk","date":"2015-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-track-for-spatio-temporal-action","title":"Learning to track for spatio-temporal action localization","date":"2015-06-05","arxiv_id":"1506.01929","repositories_listed":0,"syntology":null},{"url":null,"slug":"action-localization-with-tubelets-from-motion","title":"Action Localization with Tubelets from Motion","date":"2014-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-action-localization-with","title":"Efficient Action Localization with Approximately Normalized Fisher Vectors","date":"2014-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"action-is-in-the-eye-of-the-beholder-eye-gaze","title":"Action is in the Eye of the Beholder: Eye-gaze Driven Model for Spatio-Temporal Action Localization","date":"2013-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"max-margin-structured-output-regression-for","title":"Max-Margin Structured Output Regression for Spatio-Temporal Action Localization","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"272151a39497d3e57b29668a3add17475e6f0c941531ae7f225ff7132047198d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}