{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T22:41:07Z","timestamp":1770331267129,"version":"3.49.0"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":["62172111"],"award-info":[{"award-number":["62172111"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Joint Fund Key Project","award":["U21A20478"],"award-info":[{"award-number":["U21A20478"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2024.3405654","type":"journal-article","created":{"date-parts":[[2024,5,27]],"date-time":"2024-05-27T17:22:23Z","timestamp":1716830543000},"page":"10055-10068","source":"Crossref","is-referenced-by-count":2,"title":["Visual Object Tracking With Mutual Affinity Aligned to Human Intuition"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3435-7580","authenticated-orcid":false,"given":"Guotian","family":"Zeng","sequence":"first","affiliation":[{"name":"School of Computers, Guangdong University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8596-8333","authenticated-orcid":false,"given":"Bi","family":"Zeng","sequence":"additional","affiliation":[{"name":"School of Computers, Guangdong University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9982-3119","authenticated-orcid":false,"given":"Qingmao","family":"Wei","sequence":"additional","affiliation":[{"name":"School of Computers, Guangdong University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9896-2923","authenticated-orcid":false,"given":"Huiting","family":"Hu","sequence":"additional","affiliation":[{"name":"Faculty of Information Science and Technology, Zhongkai University of Agriculture and Engineering, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1677-6132","authenticated-orcid":false,"given":"Hong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Electronic and Electrical Engineering, Southern University of Science and Technology, Shenzhen, China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. ICLR","author":"Dosovitskiy","year":"2021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10610022"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094971"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_20"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_22"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01792"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00667"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_9"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_48"},{"key":"ref15","article-title":"Efficient training for visual tracking with deformable transformer","author":"Wei","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2957464"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00661"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00935"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01400"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3321497"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3321476"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3238277"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-020-02572-0"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2022.108485"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref26","article-title":"RTrack: Accelerating convergence for visual object tracking via pseudo-boxes exploration","author":"Zeng","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3223213"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3203607"},{"key":"ref29","article-title":"DeepViT: Towards deeper vision transformer","author":"Zhou","year":"2021"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3323134"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-022-07684-6"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-15429-3"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2022.107730"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_46"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2005.11.033"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1080\/713826335"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1037\/0033-295X.113.2.201"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00181"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.visres.2016.09.010"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00621"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref48","article-title":"SaiT: Sparse vision transformers through adaptive token pruning","author":"Li","year":"2022"},{"key":"ref49","first-page":"13937","article-title":"DynamicViT: Efficient vision transformers with dynamic token sparsification","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Rao","year":"2021"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00552"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_19"},{"key":"ref53","article-title":"Decoupled weight decay regularization","volume-title":"Proc. ICLR","author":"Loshchilov","year":"2019"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2388226"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00928"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3264851"},{"key":"ref57","article-title":"MixFormerV2: Efficient fully transformer tracking","volume-title":"Proc. NeurIPS","author":"Cui","year":"2023"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00859"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_27"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00441"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00479"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00628"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00853"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.128"},{"key":"ref65","first-page":"186","article-title":"The data model concept in statistical mapping","volume":"7","author":"Jenks","year":"1967","journal-title":"Int. Yearbook Cartography"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01060"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3328478"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10539277.pdf?arnumber=10539277","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T17:43:20Z","timestamp":1729187000000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10539277\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3405654","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}