{"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/high-speed-tracking-with-multi-kernel","title":"High-speed Tracking with Multi-kernel Correlation Filters","arxiv_id":"1806.06418","date":"2018-06-17","proceeding":"CVPR 2018 6","authors":["Ming Tang","Bin Yu","Fan Zhang","Jinqiao Wang"],"abstract":"Correlation filter (CF) based trackers are currently ranked top in terms of\ntheir performances. Nevertheless, only some of them, such as\nKCF~\\cite{henriques15} and MKCF~\\cite{tangm15}, are able to exploit the\npowerful discriminability of non-linear kernels. Although MKCF achieves more\npowerful discriminability than KCF through introducing multi-kernel learning\n(MKL) into KCF, its improvement over KCF is quite limited and its computational\nburden increases significantly in comparison with KCF. In this paper, we will\nintroduce the MKL into KCF in a different way than MKCF. We reformulate the MKL\nversion of CF objective function with its upper bound, alleviating the negative\nmutual interference of different kernels significantly. Our novel MKCF tracker,\nMKCFup, outperforms KCF and MKCF with large margins and can still work at very\nhigh fps. Extensive experiments on public datasets show that our method is\nsuperior to state-of-the-art algorithms for target objects of small move at\nvery high speed.","url_abs":"http://arxiv.org/abs/1806.06418v1","url_pdf":"http://arxiv.org/pdf/1806.06418v1.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":"video-object-tracking","task_name":"Video Object Tracking"},{"task_slug":"high","task_name":"Vocal Bursts Intensity Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-object-tracking-on-nv-vot211","task":"Video Object Tracking","dataset":"NT-VOT211","model":"MKCFup","rank_in_archive_order":34,"of":43,"metrics":{"AUC":"28.04","Precision":"34.94"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}