{"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/temporal-context-network-for-activity","title":"Temporal Context Network for Activity Localization in Videos","arxiv_id":"1708.02349","date":"2017-08-08","proceeding":"ICCV 2017 10","authors":["Xiyang Dai","Bharat Singh","Guyue Zhang","Larry S. Davis","Yan Qiu Chen"],"abstract":"We present a Temporal Context Network (TCN) for precise temporal localization\nof human activities. Similar to the Faster-RCNN architecture, proposals are\nplaced at equal intervals in a video which span multiple temporal scales. We\npropose a novel representation for ranking these proposals. Since pooling\nfeatures only inside a segment is not sufficient to predict activity\nboundaries, we construct a representation which explicitly captures context\naround a proposal for ranking it. For each temporal segment inside a proposal,\nfeatures are uniformly sampled at a pair of scales and are input to a temporal\nconvolutional neural network for classification. After ranking proposals,\nnon-maximum suppression is applied and classification is performed to obtain\nfinal detections. TCN outperforms state-of-the-art methods on the ActivityNet\ndataset and the THUMOS14 dataset.","url_abs":"http://arxiv.org/abs/1708.02349v1","url_pdf":"http://arxiv.org/pdf/1708.02349v1.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":"classification","task_name":"General Classification"},{"task_slug":"temporal-localization","task_name":"Temporal Localization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-recognition-in-videos-on-thumos14","task":"Action Recognition","dataset":"THUMOS’14","model":"Dai et. al.","rank_in_archive_order":7,"of":10,"metrics":{"mAP@0.4":"33.3","mAP@0.5":"25.6"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1708.02349","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}