{"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/towards-unified-token-learning-for-vision","title":"Towards Unified Token Learning for Vision-Language Tracking","arxiv_id":"2308.14103","date":"2023-08-27","proceeding":null,"authors":["Yaozong Zheng","Bineng Zhong","Qihua Liang","Guorong Li","Rongrong Ji","Xianxian Li"],"abstract":"In this paper, we present a simple, flexible and effective vision-language (VL) tracking pipeline, termed \\textbf{MMTrack}, which casts VL tracking as a token generation task. Traditional paradigms address VL tracking task indirectly with sophisticated prior designs, making them over-specialize on the features of specific architectures or mechanisms. In contrast, our proposed framework serializes language description and bounding box into a sequence of discrete tokens. In this new design paradigm, all token queries are required to perceive the desired target and directly predict spatial coordinates of the target in an auto-regressive manner. The design without other prior modules avoids multiple sub-tasks learning and hand-designed loss functions, significantly reducing the complexity of VL tracking modeling and allowing our tracker to use a simple cross-entropy loss as unified optimization objective for VL tracking task. Extensive experiments on TNL2K, LaSOT, LaSOT$_{\\rm{ext}}$ and OTB99-Lang benchmarks show that our approach achieves promising results, compared to other state-of-the-arts.","url_abs":"https://arxiv.org/abs/2308.14103v1","url_pdf":"https://arxiv.org/pdf/2308.14103v1.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":"towards-unified-token-learning-for-vision","repo_url":"https://github.com/azong-hqu/mmtrack","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2308.14103","atlas_url":"https://app.syntology.ai/?focus=2308.14103","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}