{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/point-level-temporal-action-localization","title":"Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses","arxiv_id":"2012.08236","date":"2020-12-15","proceeding":null,"authors":["Chen Ju","Peisen Zhao","Ya zhang","Yanfeng Wang","Qi Tian"],"abstract":"Point-Level temporal action localization (PTAL) aims to localize actions in untrimmed videos with only one timestamp annotation for each action instance. Existing methods adopt the frame-level prediction paradigm to learn from the sparse single-frame labels. However, such a framework inevitably suffers from a large solution space. This paper attempts to explore the proposal-based prediction paradigm for point-level annotations, which has the advantage of more constrained solution space and consistent predictions among neighboring frames. The point-level annotations are first used as the keypoint supervision to train a keypoint detector. At the location prediction stage, a simple but effective mapper module, which enables back-propagation of training errors, is then introduced to bridge the fully-supervised framework with weak supervision. To our best of knowledge, this is the first work to leverage the fully-supervised paradigm for the point-level setting. Experiments on THUMOS14, BEOID, and GTEA verify the effectiveness of our proposed method both quantitatively and qualitatively, and demonstrate that our method outperforms state-of-the-art methods.","url_abs":"https://arxiv.org/abs/2012.08236v1","url_pdf":"https://arxiv.org/pdf/2012.08236v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"action-localization","task_name":"Action Localization"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"},{"task_slug":"weakly-supervised-action-localization","task_name":"Weakly Supervised Action Localization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/weakly-supervised-action-localization-on-6","task":"Weakly Supervised Action Localization","dataset":"BEOID","model":"Ju et al.","rank_in_archive_order":3,"of":5,"metrics":{"mAP@0.1:0.7":"34.9","mAP@0.5":"20.9"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-action-localization-on-gtea","task":"Weakly Supervised Action Localization","dataset":"GTEA","model":"Ju et al.","rank_in_archive_order":5,"of":6,"metrics":{"mAP@0.1:0.7":"33.7","mAP@0.5":"21.9"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-action-localization-on","task":"Weakly Supervised Action Localization","dataset":"THUMOS 2014","model":"Ju et al.","rank_in_archive_order":11,"of":30,"metrics":{"mAP@0.1:0.5":"55.6","mAP@0.1:0.7":"44.8","mAP@0.5":"35.9"},"uses_additional_data":true},{"leaderboard":"/sota/weakly-supervised-action-localization-on-5","task":"Weakly Supervised Action Localization","dataset":"THUMOS14","model":"Ju et al.","rank_in_archive_order":4,"of":12,"metrics":{"avg-mAP (0.1-0.5)":"55.6","avg-mAP (0.1:0.7)":"44.8","avg-mAP (0.3-0.7)":"35.4"},"uses_additional_data":true},{"leaderboard":"/sota/weakly-supervised-action-localization-on-4","task":"Weakly Supervised Action Localization","dataset":"THUMOS’14","model":"Ju et al.","rank_in_archive_order":5,"of":13,"metrics":{"mAP@0.5":"35.9"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2012.08236","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}