{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T06:48:11Z","timestamp":1784616491732,"version":"3.55.0"},"reference-count":83,"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\/501100014219","name":"National Science Fund for Distinguished Young Scholars","doi-asserted-by":"publisher","award":["62025108"],"award-info":[{"award-number":["62025108"]}],"id":[{"id":"10.13039\/501100014219","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001348","name":"Agency for Science, Technology and Research (A*STAR) under its IAF-ICP Programme","doi-asserted-by":"publisher","award":["I2501E0041"],"award-info":[{"award-number":["I2501E0041"]}],"id":[{"id":"10.13039\/501100001348","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001475","name":"Nanyang Technological University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001475","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\/iccv51701.2025.00737","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"7872-7872","source":"Crossref","is-referenced-by-count":2,"title":["M-SpecGene: Generalized Foundation Model for RGBT Multispectral Vision"],"prefix":"10.1109","author":[{"given":"Kailai","family":"Zhou","sequence":"first","affiliation":[{"name":"Nanjing University,Nanjing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fuqiang","family":"Yang","sequence":"additional","affiliation":[{"name":"Nanjing University,Nanjing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shixian","family":"Wang","sequence":"additional","affiliation":[{"name":"Nanjing University,Nanjing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bihan","family":"Wen","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chongde","family":"Zi","sequence":"additional","affiliation":[{"name":"Nanjing University,Nanjing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linsen","family":"Chen","sequence":"additional","affiliation":[{"name":"Nanjing University,Nanjing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiu","family":"Shen","sequence":"additional","affiliation":[{"name":"Nanjing University,Nanjing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xun","family":"Cao","sequence":"additional","affiliation":[{"name":"Nanjing University,Nanjing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3229571"},{"key":"ref2","article-title":"Foundational models defining a new era in vision: A survey and outlook","author":"Awais","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00046"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_9"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636084"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3231135"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/iros58592.2024.10801872"},{"key":"ref10","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3073689"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2018.11.017"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206396"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612651"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3362475"},{"key":"ref17","article-title":"Milan: Masked image pretraining on language assisted representation","author":"Hou","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102027"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3069812"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298706"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298706"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611738"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00112"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00389"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_18"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2024.02.012"},{"key":"ref27","article-title":"Multispectral Pedestrian Detection via Simultaneous Detection and Segmentation","author":"Li","year":"2018","journal-title":"arXiv e-prints, art. arXiv"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3130533"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1039"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2959244"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3160589"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3531988"},{"key":"ref33","first-page":"21002","article-title":"Generalized focal loss: Learning qualified and distributed bounding boxes for dense object detection","volume":"33","author":"Li","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01616"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72649-1_24"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.73"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00745"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01377"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636192"},{"key":"ref41","article-title":"Crossmodality fusion transformer for multispectral object detection","author":"Qingyun","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109913"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196831"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3233131"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00881"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2904733"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2924578"},{"key":"ref48","article-title":"Multi-interactive encoder-decoder network for rgbt salient object detection","author":"Tu","year":"2020","journal-title":"arXiv e-prints, pages arXiv-2005"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3087412"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3171688"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3557581"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-13-1702-6_36"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01000"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3099120"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3281419"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613849"},{"key":"ref58","article-title":"Object-wise masked autoencoders for fast pre-training","author":"Wu","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref60","first-page":"30392","article-title":"Early convolutions help transformers see better","volume":"34","author":"Xiao","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2105.15203"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101835"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-025-02032-z"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3376819"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_30"},{"key":"ref66","article-title":"Unirgb-ir: A unified framework for visible-infrared downstream tasks via adapter tuning","author":"Yuan","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102246"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_11"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.3390\/math10213966"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2024.3418965"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9191080"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00012"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02547"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2018.09.015"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00523"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2959253"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00266"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3233089"},{"key":"ref79","article-title":"Removal and selection: Improving rgbinfrared object detection via coarse-to-fine fusion","author":"Zhao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_46"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3086618"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20269"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3242775"}],"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\/11446318.pdf?arnumber=11446318","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:44:54Z","timestamp":1777531494000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446318\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":83,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00737","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}