{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:12:57Z","timestamp":1778080377280,"version":"3.51.4"},"reference-count":84,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176020"],"award-info":[{"award-number":["62176020"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Joint Foundation of the Ministry of Education for Innovation Team","award":["8091B042235"],"award-info":[{"award-number":["8091B042235"]}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["L211016"],"award-info":[{"award-number":["L211016"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2019JBZ110"],"award-info":[{"award-number":["2019JBZ110"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"State Key Laboratory of Rail Traffic Control and Safety of Beijing Jiaotong University","award":["RCS2023K006"],"award-info":[{"award-number":["RCS2023K006"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tpami.2024.3409078","type":"journal-article","created":{"date-parts":[[2024,6,4]],"date-time":"2024-06-04T20:33:49Z","timestamp":1717533229000},"page":"8600-8618","source":"Crossref","is-referenced-by-count":11,"title":["Divert More Attention to Vision-Language Object Tracking"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6399-9753","authenticated-orcid":false,"given":"Mingzhe","family":"Guo","sequence":"first","affiliation":[{"name":"Beijing Key Lab of Traffic Data Analysis and Mining, Beijing Jiaotong University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0479-332X","authenticated-orcid":false,"given":"Zhipeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"KargoBot, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7578-3407","authenticated-orcid":false,"given":"Liping","family":"Jing","sequence":"additional","affiliation":[{"name":"Beijing Key Lab of Traffic Data Analysis and Mining, Beijing Jiaotong University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4094-8413","authenticated-orcid":false,"given":"Haibin","family":"Ling","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Stony Brook University, Stony Brook, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7033-3690","authenticated-orcid":false,"given":"Heng","family":"Fan","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University of North Texas, Denton, TX, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00630"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_20"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2024.3409078","article-title":"Divert more attention to vision-language tracking","volume-title":"Proc. 36th Int. Conf. Neural Inf. Process. Syst.","author":"Guo"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00514"},{"key":"ref6","first-page":"35549","article-title":"Towards video text visual question answering: Benchmark and baseline","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhao"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01628"},{"key":"ref8","first-page":"6634","article-title":"Multi-modal dependency tree for video captioning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhao"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2022.103514"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3059968"},{"key":"ref11","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref13","article-title":"VisionLLM: Large language model is also an open-ended decoder for vision-centric tasks","author":"Wang","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00579"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.777"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093425"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02217"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2388226"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00552"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2957464"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01355"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2112686118"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01387-y"},{"key":"ref25","article-title":"Dynamic channel pruning: Feature boosting and suppression","author":"Gao","year":"2018"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.18"},{"key":"ref27","first-page":"1","article-title":"Neural architecture search with reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zoph"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014780"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539960"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2345390"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.733"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00479"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00721"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.158"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00935"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00472"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00441"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00814"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_46"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00162"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01400"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01792"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01399"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d16-1044"},{"key":"ref50","first-page":"1571","article-title":"Bilinear attention networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kim"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref52","article-title":"CoCa: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022"},{"key":"ref53","article-title":"ClipCap: CLIP prefix for image captioning","author":"Mokady","year":"2021"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00512"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01086"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"ref59","first-page":"1","article-title":"DARTS: Differentiable architecture search","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_32"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01493"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01309"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.789"},{"key":"ref64","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref65","first-page":"3530","article-title":"Efficient attention: Attention with linear complexities","volume-title":"Proc. IEEE Winter Conf. Appl. Comput. Vis.","author":"Shen"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref68","first-page":"10944","article-title":"What makes multi-modal learning better than single (provably)","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Huang"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3399990"},{"key":"ref70","first-page":"28","article-title":"Learning from multiple partially observed views-an application to multilingual text categorization","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Amini"},{"key":"ref71","first-page":"7852","article-title":"On the theory of transfer learning: The importance of task diversity","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Tripuraneni"},{"key":"ref72","first-page":"463","article-title":"Rademacher and Gaussian complexities: Risk bounds and structural results","volume":"3","author":"Bartlett","year":"2002","journal-title":"J. Mach. Learn. Res."},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_13"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00661"},{"key":"ref75","first-page":"16743","article-title":"SwinTrack: A simple and strong baseline for transformer tracking","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lin"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref78","first-page":"1002","article-title":"Active bias: Training more accurate neural networks by emphasizing high variance samples","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chang"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00922"},{"key":"ref80","article-title":"A survey on bias and fairness in machine learning","volume":"54","author":"Mehrabi","year":"2021","journal-title":"ACM Comput. Surv."},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref82","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01068"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10746266\/10547435.pdf?arnumber=10547435","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T14:16:07Z","timestamp":1732716967000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10547435\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":84,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3409078","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}