{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:29:50Z","timestamp":1778052590855,"version":"3.51.4"},"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"}],"funder":[{"DOI":"10.13039\/100005156","name":"Alexander von Humboldt Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100005156","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62376156,62322113"],"award-info":[{"award-number":["62376156,62322113"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00543","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"5734-5744","source":"Crossref","is-referenced-by-count":1,"title":["XTrack: Multimodal Training Boosts RGB-X Video Object Trackers"],"prefix":"10.1109","author":[{"given":"Yuedong","family":"Tan","sequence":"first","affiliation":[{"name":"University of Wurzburg,Computer Vision Lab, CAIDAS & IFI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zongwei","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Wurzburg,Computer Vision Lab, CAIDAS & IFI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuqian","family":"Fu","sequence":"additional","affiliation":[{"name":"Sofia University,INSAIT"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhuyun","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of Wurzburg,Computer Vision Lab, CAIDAS & IFI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guolei","family":"Sun","sequence":"additional","affiliation":[{"name":"CVL, ETH Zurich"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eduard","family":"Zamfir","sequence":"additional","affiliation":[{"name":"University of Wurzburg,Computer Vision Lab, CAIDAS & IFI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Ma","sequence":"additional","affiliation":[{"name":"AI Institute, Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Danda","family":"Paudel","sequence":"additional","affiliation":[{"name":"Sofia University,INSAIT"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luc","family":"Van Gool","sequence":"additional","affiliation":[{"name":"Sofia University,INSAIT"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Radu","family":"Timofte","sequence":"additional","affiliation":[{"name":"University of Wurzburg,Computer Vision Lab, CAIDAS & IFI"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Alternating gradient descent and mixture-of-experts for integrated multimodal perception","volume":"36","author":"Akbari","year":"2024","journal-title":"NeurIPS"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27852"},{"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":"10.1109\/TPAMI.2022.3195759"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.70"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00633"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00479"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00721"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00552"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/127"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00017"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00630"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/iros51168.2021.9636448"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2345390"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01805"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02507"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2957464"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01310"},{"key":"ref22","article-title":"Damex: Dataset-aware mixture-of-experts for visual understanding of mixture-of-datasets","volume":"36","author":"Jain","year":"2024","journal-title":"NeurIPS"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.129"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68238-5_39"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00305"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25085-9_25"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2614135"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.106977"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2021.3130533"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3285802"},{"key":"ref32","article-title":"Polyvit: Co-training vision transformers on images, videos and audio","author":"Likhosherstov","year":"2022","journal-title":"TMLR"},{"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\/WHISPERS61460.2023.10431304"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01319"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_19"},{"key":"ref39","first-page":"9564","article-title":"Multimodal contrastive learning with limoe: the language-image mixture of experts","volume":"35","author":"Mustafa","year":"2022","journal-title":"NeurIPS"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.465"},{"key":"ref41","first-page":"8583","article-title":"Scaling vision with sparse mixture of experts","volume":"34","author":"Riquelme","year":"2021","journal-title":"NeurIPS"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00661"},{"key":"ref43","article-title":"Cross-modal patternpropagation for rgb-t tracking","author":"Wang","year":"2020","journal-title":"CVPR"},{"key":"ref44","article-title":"Visionllm: Large language model is also an openended decoder for vision-centric tasks","volume":"36","author":"Wang","year":"2024","journal-title":"NeurIPS"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/tcyb.2023.3318601"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01821"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00935"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01399"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01812"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20187"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00855"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01055"},{"key":"ref54","article-title":"Rgbd object tracking: An in-depth review","author":"Yang","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547851"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_20"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.3390\/s20020393"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01280"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00860"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00278"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3060862"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00868"},{"key":"ref63","article-title":"Metatransformer: A unified framework for multimodal learning","author":"Zhang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01793"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00141"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00918"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.890"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25500"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25500"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02015"}],"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\/11445097.pdf?arnumber=11445097","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:55:08Z","timestamp":1777611308000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445097\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00543","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}