{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T16:29:02Z","timestamp":1793377742913,"version":"4.5.0"},"reference-count":70,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00330","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"3455-3465","source":"Crossref","is-referenced-by-count":9,"title":["What You Have is What You Track: Adaptive and Robust Multimodal Tracking"],"prefix":"10.1109","author":[{"given":"Yuedong","family":"Tan","sequence":"first","affiliation":[{"name":"China Telecom,TeleAI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiawei","family":"Shao","sequence":"additional","affiliation":[{"name":"China Telecom,TeleAI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eduard","family":"Zamfir","sequence":"additional","affiliation":[{"name":"University of Wurzburg,Computer Vision Lab, CAIDAS &#x0026; IFI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruanjun","family":"Li","sequence":"additional","affiliation":[{"name":"ShanghaiTech University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaochong","family":"An","sequence":"additional","affiliation":[{"name":"University of Copenhagen"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Ma","sequence":"additional","affiliation":[{"name":"AI Institute, Shanghai Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Danda","family":"Paudel","sequence":"additional","affiliation":[{"name":"Sofia University,INSAIT"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luc","family":"Van Gool","sequence":"additional","affiliation":[{"name":"Sofia University,INSAIT"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Radu","family":"Timofte","sequence":"additional","affiliation":[{"name":"University of Wurzburg,Computer Vision Lab, CAIDAS &#x0026; IFI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zongwei","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Wurzburg,Computer Vision Lab, CAIDAS &#x0026; IFI"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00628"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00879"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01400"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i2.32223"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3195759"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261988"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.70"},{"key":"ref10","article-title":"High-performance longterm tracking with meta-updater, in","author":"Dai","year":"2020","journal-title":"Proc. CVPR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00479"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00721"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00552"},{"issue":"120","key":"ref14","first-page":"1","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"JMLR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/127"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_9"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00630"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2167"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01805"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02507"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32372"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2957464"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43999-5_38"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32440"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00276"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68238-5_39"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25085-9_25"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.106977"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_14"},{"key":"ref31","first-page":"392","article-title":"Lasher: A large-scale highdiversity benchmark for rgbt tracking","volume":"31","author":"Li","year":"2021","journal-title":"TIP"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3285802"},{"key":"ref33","first-page":"16743","article-title":"Swintrack: A simple and strong baseline for transformer tracking","volume":"35","author":"Lin","year":"2022","journal-title":"NeurIPS"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2018.2863604"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02311-4"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16330"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01764"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01319"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_19"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.465"},{"key":"ref42","article-title":"Dal: A deep depthaware long-term tracker, in","author":"Qian","year":"2021","journal-title":"Proc. ICPR"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00937"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3429508"},{"key":"ref45","first-page":"10078","article-title":"Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training","volume":"35","author":"Tong","year":"2022","journal-title":"NeurIPS"},{"key":"ref46","article-title":"Siam R-CNN: Visual tracking by redetection, in","author":"Voigtlaender","year":"2020","journal-title":"Proc. CVPR"},{"key":"ref47","article-title":"Cross-modal patternpropagation for rgb-t tracking, in","author":"Wang","year":"2020","journal-title":"Proc. CVPR"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43901-8_21"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00142"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2023.3318601"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/tcyb.2023.3318601"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01821"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00935"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25378"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01399"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01812"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20187"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00855"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01055"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547851"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_20"},{"key":"ref63","article-title":"Flex-moe: Modeling arbitrary modality combination via the flexible mixture-of-experts, in","author":"Yun","journal-title":"Proc. NeurIPS"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.3390\/s20020393"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3060862"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.203"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00918"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.890"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25500"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2020.2980735"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11443458.pdf?arnumber=11443458","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:14:23Z","timestamp":1777612463000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443458\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00330","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}