{"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/part-based-visual-tracking-via-structural","title":"Part-based Visual Tracking via Structural Support Correlation Filter","arxiv_id":"1805.09971","date":"2018-05-25","proceeding":null,"authors":["Zhangjian Ji","Kai Feng","Yuhua Qian"],"abstract":"Recently, part-based and support vector machines (SVM) based trackers have\nshown favorable performance. Nonetheless, the time-consuming online training\nand updating process limit their real-time applications. In order to better\ndeal with the partial occlusion issue and improve their efficiency, we propose\na novel part-based structural support correlation filter tracking method, which\nabsorbs the strong discriminative ability from SVM and the excellent property\nof part-based tracking methods which is less sensitive to partial occlusion.\nThen, our proposed model can learn the support correlation filter of each part\njointly by a star structure model, which preserves the spatial layout structure\namong parts and tolerates outliers of parts. In addition, to mitigate the issue\nof drift away from object further, we introduce inter-frame consistencies of\nlocal parts into our model. Finally, in our model, we accurately estimate the\nscale changes of object by the relative distance change among reliable parts.\nThe extensive empirical evaluations on three benchmark datasets: OTB2015,\nTempleColor128 and VOT2015 demonstrate that the proposed method performs\nsuperiorly against several state-of-the-art trackers in terms of tracking\naccuracy, speed and robustness.","url_abs":"http://arxiv.org/abs/1805.09971v1","url_pdf":"http://arxiv.org/pdf/1805.09971v1.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":"part-based-visual-tracking-via-structural","repo_url":"https://github.com/jzhang2008/L1CFT_ACLKS","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"visual-tracking","task_name":"Visual Tracking"}],"methods":[{"method_slug":"speed","method_name":"SPEED"},{"method_slug":"svm","method_name":"SVM"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}