{"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/after-attention-based-fusion-router-for-rgbt","title":"AFter: Attention-based Fusion Router for RGBT Tracking","arxiv_id":"2405.02717","date":"2024-05-04","proceeding":null,"authors":["Andong Lu","Wanyu Wang","Chenglong Li","Jin Tang","Bin Luo"],"abstract":"Multi-modal feature fusion as a core investigative component of RGBT tracking emerges numerous fusion studies in recent years. However, existing RGBT tracking methods widely adopt fixed fusion structures to integrate multi-modal feature, which are hard to handle various challenges in dynamic scenarios. To address this problem, this work presents a novel \\emph{A}ttention-based \\emph{F}usion rou\\emph{ter} called AFter, which optimizes the fusion structure to adapt to the dynamic challenging scenarios, for robust RGBT tracking. In particular, we design a fusion structure space based on the hierarchical attention network, each attention-based fusion unit corresponding to a fusion operation and a combination of these attention units corresponding to a fusion structure. Through optimizing the combination of attention-based fusion units, we can dynamically select the fusion structure to adapt to various challenging scenarios. Unlike complex search of different structures in neural architecture search algorithms, we develop a dynamic routing algorithm, which equips each attention-based fusion unit with a router, to predict the combination weights for efficient optimization of the fusion structure. Extensive experiments on five mainstream RGBT tracking datasets demonstrate the superior performance of the proposed AFter against state-of-the-art RGBT trackers. We release the code in https://github.com/Alexadlu/AFter.","url_abs":"https://arxiv.org/abs/2405.02717v1","url_pdf":"https://arxiv.org/pdf/2405.02717v1.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":"after-attention-based-fusion-router-for-rgbt","repo_url":"https://github.com/alexadlu/after","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"architecture-search","task_name":"Neural Architecture Search"},{"task_slug":"rgb-t-tracking","task_name":"Rgb-T Tracking"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/rgb-t-tracking-on-gtot","task":"Rgb-T Tracking","dataset":"GTOT","model":"AFter","rank_in_archive_order":8,"of":15,"metrics":{"Precision":"91.6","Success":"78.5"},"uses_additional_data":false},{"leaderboard":"/sota/rgb-t-tracking-on-lasher","task":"Rgb-T Tracking","dataset":"LasHeR","model":"AFter","rank_in_archive_order":22,"of":39,"metrics":{"Precision":"70.3","Success":"55.1"},"uses_additional_data":false},{"leaderboard":"/sota/rgb-t-tracking-on-rgbt210","task":"Rgb-T Tracking","dataset":"RGBT210","model":"AFter","rank_in_archive_order":7,"of":19,"metrics":{"Precision":"87.6","Success":"63.5"},"uses_additional_data":false},{"leaderboard":"/sota/rgb-t-tracking-on-rgbt234","task":"Rgb-T Tracking","dataset":"RGBT234","model":"AFter","rank_in_archive_order":8,"of":42,"metrics":{"Precision":"90.1","Success":"66.7"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}