{"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/robust-visual-tracking-using-multi-frame","title":"Robust Visual Tracking using Multi-Frame Multi-Feature Joint Modeling","arxiv_id":"1811.07498","date":"2018-11-19","proceeding":null,"authors":["Peng Zhang","Shujian Yu","Jiamiao Xu","Xinge You","Xiubao Jiang","Xiao-Yuan Jing","DaCheng Tao"],"abstract":"It remains a huge challenge to design effective and efficient trackers under\ncomplex scenarios, including occlusions, illumination changes and pose\nvariations. To cope with this problem, a promising solution is to integrate the\ntemporal consistency across consecutive frames and multiple feature cues in a\nunified model. Motivated by this idea, we propose a novel correlation\nfilter-based tracker in this work, in which the temporal relatedness is\nreconciled under a multi-task learning framework and the multiple feature cues\nare modeled using a multi-view learning approach. We demonstrate the resulting\nregression model can be efficiently learned by exploiting the structure of\nblockwise diagonal matrix. A fast blockwise diagonal matrix inversion algorithm\nis developed thereafter for efficient online tracking. Meanwhile, we\nincorporate an adaptive scale estimation mechanism to strengthen the stability\nof scale variation tracking. We implement our tracker using two types of\nfeatures and test it on two benchmark datasets. Experimental results\ndemonstrate the superiority of our proposed approach when compared with other\nstate-of-the-art trackers. project homepage\nhttp://bmal.hust.edu.cn/project/KMF2JMTtracking.html","url_abs":"http://arxiv.org/abs/1811.07498v1","url_pdf":"http://arxiv.org/pdf/1811.07498v1.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":"robust-visual-tracking-using-multi-frame","repo_url":"https://github.com/dscv-lab/KMF2JMTtracking","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"multi-view-learning","task_name":"MULTI-VIEW LEARNING"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"object-tracking","task_name":"Object Tracking"},{"task_slug":"visual-object-tracking","task_name":"Visual Object Tracking"},{"task_slug":"visual-tracking","task_name":"Visual Tracking"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}