{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T18:26:35Z","timestamp":1790274395974,"version":"4.1.0"},"reference-count":88,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NSFC Regional Innovation and Development Joint Fund","award":["U25A20537"],"award-info":[{"award-number":["U25A20537"]}]},{"name":"National Key Research and Development Program of China","award":["2024YFC3015600"],"award-info":[{"award-number":["2024YFC3015600"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1109\/tpami.2026.3697145","type":"journal-article","created":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T19:42:01Z","timestamp":1779824521000},"page":"12348-12365","source":"Crossref","is-referenced-by-count":3,"title":["Leveraging Text-to-Image Diffusion Models for Unsupervised Visual Object Tracking"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8956-0095","authenticated-orcid":false,"given":"Zhengbo","family":"Zhang","sequence":"first","affiliation":[{"name":"Singapore University of Technology and Design"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5003-2260","authenticated-orcid":false,"given":"Zhigang","family":"Tu","sequence":"additional","affiliation":[{"name":"Wuhan University","place":["Wuhan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7324-7034","authenticated-orcid":false,"given":"Junsong","family":"Yuan","sequence":"additional","affiliation":[{"name":"University at Buffalo","place":["Buffalo, NY, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6490-6467","authenticated-orcid":false,"given":"De Wen","family":"Soh","sequence":"additional","affiliation":[{"name":"Singapore University of Technology and Design"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0059-8458","authenticated-orcid":false,"given":"Bo","family":"Du","sequence":"additional","affiliation":[{"name":"Wuhan University","place":["Wuhan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3529926"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/09544070211006520"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2930337"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3266669"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/70.210792"},{"issue":"3","key":"ref6","first-page":"289","article-title":"Design of object tracking for military robot using PID controller and computer vision","volume":"14","author":"Budiharto","year":"2020","journal-title":"ICIC Exp. Lett."},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2025.01.039"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00676"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00721"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01251"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01329"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00140"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00793"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01357-4"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413611"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3382753"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72624-8_20"},{"key":"ref20","article-title":"Uni-CoT: Towards unified chain-of-thought reasoning across text and vision","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Qin","year":"2026"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0068"},{"key":"ref22","article-title":"SLiMe: Segment like me","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Khani","year":"2024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1973"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2479460"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296749"},{"key":"ref26","first-page":"1","article-title":"On the connections between saliency and tracking","volume-title":"Proc. Adv. Neural Inf Process. Syst.","volume":"25","author":"Mahadevan","year":"2012"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3389\/frsip.2024.1356793"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01349"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1142\/S0218001409007624"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.424"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA240524"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2388226"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00552"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73390-1_19"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68238-5_39"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3127492"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2417577"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01600"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.733"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00479"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00628"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00441"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3172932"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01630"},{"key":"ref46","first-page":"4095","article-title":"Efficient neural architecture search via parameters sharing","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pham","year":"2018"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01493"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3212594"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2829180"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00301"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00267"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00440"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01013"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref55","article-title":"PixArt-$\\alpha$\u03b1: Fast training of diffusion transformer for photorealistic text-to-image synthesis","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Chen","year":"2024"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01737"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-026-04522-x"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00729"},{"key":"ref60","first-page":"1","article-title":"Prompt-to-prompt image editing with cross-attention control","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hertz","year":"2023"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.310"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00652"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-20145-3"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_19"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.230"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11009-3_1"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_7"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2345390"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.112109"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2957464"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_36"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref78","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kingma","year":"2015"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_33"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_20"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00935"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.5244\/C.28.65"},{"key":"ref83","first-page":"1","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_22"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3758243"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72949-2_22"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74936-3_22"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72667-5_3"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11674301\/11535413.pdf?arnumber=11535413","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T16:06:43Z","timestamp":1790266003000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11535413\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":88,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3697145","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":[[2026,10]]}}}