{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:39:29Z","timestamp":1787013569190,"version":"build-2736575974"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006754","name":"Army Research Laboratory","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006754","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00546","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"5633-5642","source":"Crossref","is-referenced-by-count":1,"title":["F-ViTA: Foundation Model Guided Visible-to-Infrared Translation"],"prefix":"10.1109","author":[{"given":"Jay Nitin","family":"Paranjape","sequence":"first","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Celso M","family":"de Melo","sequence":"additional","affiliation":[{"name":"DEVCOM Army Research Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vishal M.","family":"Patel","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01764"},{"key":"ref2","first-page":"177","article-title":"Multispectral SIFT for scene category recognition","volume-title":"Computer Vision and Pattern Recognition (CVPR11)","author":"Brown","year":"2011"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3390\/s16081253"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN60899.2024.10650029"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-020-01882-2"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2006.06.010"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.23919\/FUSION49465.2021.9626853"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3390\/app10082924"},{"key":"ref9","volume-title":"Flir adas dataset","year":"2025"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298706"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref12","author":"Jocher","year":"2023","journal-title":"Ultralytics yolov8"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11024-6_46"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.32728\/ric.2016.24\/5"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.5220\/0006723704870495"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161210"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3184840"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111816"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00319"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ITEC.2019.8790493"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3185402"},{"key":"ref24","author":"Radford","year":"2021","journal-title":"Learning transferable visual models from natural language supervision"},{"key":"ref25","author":"Ravi","year":"2024","journal-title":"Sam 2: Segment anything in images and videos"},{"key":"ref26","author":"Ren","year":"2024","journal-title":"Grounded sam: Assembling open-world models for diverse visual tasks"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2020.2993143"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3126686.3126727"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1117\/12.548359"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00176"},{"key":"ref32","volume-title":"Segformer: simple and efficient design for semantic segmentation with transformers","author":"Xie","year":"2021"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw63382.2024.00179"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3077058"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2022.01.026"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492552.pdf?arnumber=11492552","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:33:29Z","timestamp":1778049209000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492552\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00546","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}