{"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/correlation-tracking-via-joint-discrimination","title":"Correlation Tracking via Joint Discrimination and Reliability Learning","arxiv_id":"1804.08965","date":"2018-04-24","proceeding":"CVPR 2018 6","authors":["Chong Sun","Dong Wang","Huchuan Lu","Ming-Hsuan Yang"],"abstract":"For visual tracking, an ideal filter learned by the correlation filter (CF)\nmethod should take both discrimination and reliability information. However,\nexisting attempts usually focus on the former one while pay less attention to\nreliability learning. This may make the learned filter be dominated by the\nunexpected salient regions on the feature map, thereby resulting in model\ndegradation. To address this issue, we propose a novel CF-based optimization\nproblem to jointly model the discrimination and reliability information. First,\nwe treat the filter as the element-wise product of a base filter and a\nreliability term. The base filter is aimed to learn the discrimination\ninformation between the target and backgrounds, and the reliability term\nencourages the final filter to focus on more reliable regions. Second, we\nintroduce a local response consistency regular term to emphasize equal\ncontributions of different regions and avoid the tracker being dominated by\nunreliable regions. The proposed optimization problem can be solved using the\nalternating direction method and speeded up in the Fourier domain. We conduct\nextensive experiments on the OTB-2013, OTB-2015 and VOT-2016 datasets to\nevaluate the proposed tracker. Experimental results show that our tracker\nperforms favorably against other state-of-the-art trackers.","url_abs":"http://arxiv.org/abs/1804.08965v1","url_pdf":"http://arxiv.org/pdf/1804.08965v1.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":"correlation-tracking-via-joint-discrimination","repo_url":"https://github.com/cswaynecool/DRT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"visual-tracking","task_name":"Visual Tracking"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.08965","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}