{"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/artrackv2-prompting-autoregressive-tracker","title":"ARTrackV2: Prompting Autoregressive Tracker Where to Look and How to Describe","arxiv_id":"2312.17133","date":"2023-12-28","proceeding":"CVPR 2024 1","authors":["Yifan Bai","Zeyang Zhao","Yihong Gong","Xing Wei"],"abstract":"We present ARTrackV2, which integrates two pivotal aspects of tracking: determining where to look (localization) and how to describe (appearance analysis) the target object across video frames. Building on the foundation of its predecessor, ARTrackV2 extends the concept by introducing a unified generative framework to \"read out\" object's trajectory and \"retell\" its appearance in an autoregressive manner. This approach fosters a time-continuous methodology that models the joint evolution of motion and visual features, guided by previous estimates. Furthermore, ARTrackV2 stands out for its efficiency and simplicity, obviating the less efficient intra-frame autoregression and hand-tuned parameters for appearance updates. Despite its simplicity, ARTrackV2 achieves state-of-the-art performance on prevailing benchmark datasets while demonstrating remarkable efficiency improvement. In particular, ARTrackV2 achieves AO score of 79.5\\% on GOT-10k, and AUC of 86.1\\% on TrackingNet while being $3.6 \\times$ faster than ARTrack. The code will be released.","url_abs":"https://arxiv.org/abs/2312.17133v3","url_pdf":"https://arxiv.org/pdf/2312.17133v3.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":"artrackv2-prompting-autoregressive-tracker","repo_url":"https://github.com/miv-xjtu/artrack","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-tracking","task_name":"Object Tracking"},{"task_slug":"template-matching","task_name":"Template Matching"},{"task_slug":"video-object-tracking","task_name":"Video Object Tracking"},{"task_slug":"visual-object-tracking","task_name":"Visual Object Tracking"}],"methods":[{"method_slug":"ao","method_name":"AO"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-object-tracking-on-got-10k","task":"Visual Object Tracking","dataset":"GOT-10k","model":"ARTrackV2-L","rank_in_archive_order":7,"of":42,"metrics":{"Average Overlap":"79.5","Success Rate 0.5":"87.8","Success Rate 0.75":"79.6"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-lasot","task":"Visual Object Tracking","dataset":"LaSOT","model":"ARTrackV2-L","rank_in_archive_order":12,"of":46,"metrics":{"AUC":"73.6","Normalized Precision":"82.8","Precision":"81.1"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-lasot-ext","task":"Visual Object Tracking","dataset":"LaSOT-ext","model":"ARTrackV2-L","rank_in_archive_order":10,"of":18,"metrics":{"AUC":"53.4","Normalized Precision":"63.7","Precision":"60.2"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-needforspeed","task":"Visual Object Tracking","dataset":"NeedForSpeed","model":"ARTrackV2-L","rank_in_archive_order":2,"of":10,"metrics":{"AUC":"0.684"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-tnl2k","task":"Visual Object Tracking","dataset":"TNL2K","model":"ARTrackV2-L","rank_in_archive_order":9,"of":16,"metrics":{"AUC":"61.6"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-trackingnet","task":"Visual Object Tracking","dataset":"TrackingNet","model":"ARTrackV2-L","rank_in_archive_order":5,"of":40,"metrics":{"Accuracy":"86.1","Normalized Precision":"90.4","Precision":"86.2"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-uav123","task":"Visual Object Tracking","dataset":"UAV123","model":"ARTrackV2-L","rank_in_archive_order":4,"of":16,"metrics":{"AUC":"0.717"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2312.17133","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}