{"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/discriminative-correlation-filter-with","title":"Discriminative Correlation Filter with Channel and Spatial Reliability","arxiv_id":"1611.08461","date":"2016-11-25","proceeding":"CVPR 2017 7","authors":["Alan Lukežič","Tomáš Vojíř","Luka Čehovin","Jiří Matas","Matej Kristan"],"abstract":"Short-term tracking is an open and challenging problem for which\ndiscriminative correlation filters (DCF) have shown excellent performance. We\nintroduce the channel and spatial reliability concepts to DCF tracking and\nprovide a novel learning algorithm for its efficient and seamless integration\nin the filter update and the tracking process. The spatial reliability map\nadjusts the filter support to the part of the object suitable for tracking.\nThis both allows to enlarge the search region and improves tracking of\nnon-rectangular objects. Reliability scores reflect channel-wise quality of the\nlearned filters and are used as feature weighting coefficients in localization.\nExperimentally, with only two simple standard features, HoGs and Colornames,\nthe novel CSR-DCF method -- DCF with Channel and Spatial Reliability --\nachieves state-of-the-art results on VOT 2016, VOT 2015 and OTB100. The CSR-DCF\nruns in real-time on a CPU.","url_abs":"http://arxiv.org/abs/1611.08461v3","url_pdf":"http://arxiv.org/pdf/1611.08461v3.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":[{"paper_slug":"discriminative-correlation-filter-with","repo_url":"https://github.com/alanlukezic/csr-dcf","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"discriminative-correlation-filter-with","repo_url":"https://github.com/Eladamar/Dual-Tracker","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"discriminative-correlation-filter-with","repo_url":"https://github.com/Eladamar/tracking","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"discriminative-correlation-filter-with","repo_url":"https://github.com/fengyang95/pyCFTrackers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":null,"task_name":"CPU"},{"task_slug":"visual-object-tracking","task_name":"Visual Object Tracking"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-object-tracking-on-vot201718","task":"Visual Object Tracking","dataset":"VOT2017/18","model":"CSRDCF","rank_in_archive_order":14,"of":15,"metrics":{"Expected Average Overlap (EAO)":"0.263"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1611.08461","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}