{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T08:50:21Z","timestamp":1771923021393,"version":"3.50.1"},"reference-count":57,"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\/iccvw69036.2025.00294","type":"proceedings-article","created":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T20:44:02Z","timestamp":1771879442000},"page":"2818-2828","source":"Crossref","is-referenced-by-count":0,"title":["ViewDelta: Scaling Scene Change Detection Through Text-Conditioning"],"prefix":"10.1109","author":[{"given":"Subin","family":"Varghese","sequence":"first","affiliation":[{"name":"University of Houston,Houston,TX,4226"}]},{"given":"Joshua","family":"Gao","sequence":"additional","affiliation":[{"name":"University of Houston,Houston,TX,4226"}]},{"given":"Vedhus","family":"Hoskere","sequence":"additional","affiliation":[{"name":"University of Houston,Houston,TX,4226"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-018-9734-5"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3390\/rs15071860"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1080\/10095020.2022.2085633"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS46834.2022.9883686"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/rs12101662"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3095166"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3417253"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IV48863.2021.9575362"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2783902"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3390\/rs16132355"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2004.833105"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/icip.2018.8451652"},{"key":"ref14","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume":"abs\/2010.11929","author":"Dosovitskiy","year":"2020","journal-title":"CoRR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2922095"},{"key":"ref16","article-title":"Dat-acomp: In search of the next generation of multimodal datasets","volume":"36","author":"Gadre","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.2022.0182"},{"key":"ref18","article-title":"xbd: A dataset for assessing building damage from satellite imagery","volume":"abs\/1911.09296","author":"Gupta","year":"2019","journal-title":"Ar Xiv"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3240097"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclepro.2016.09.177"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2003.1211414"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3390\/rs14071552"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73414-4_3"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02278"},{"key":"ref25","article-title":"Adam: A method for stochastic opti-mization","author":"Kingma","year":"2014","journal-title":"arXiv preprint arXiv"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2022.3169479"},{"key":"ref28","article-title":"Robust scene change detection using visual foundation models and cross-attention mechanisms","volume":"abs\/2409.16850","author":"Lin","year":"2024","journal-title":"ArXiv"},{"key":"ref29","volume-title":"Llava-next: Improved reasoning, ocr, and world knowledge","author":"Liu","year":"2024"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1038\/nature14324"},{"key":"ref32","volume-title":"Dinov2: Learning robust visual features with-out supervision","author":"Oquab","year":"2024"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/igarss.2019.8900330"},{"key":"ref34","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00024"},{"key":"ref36","volume-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024"},{"key":"ref37","volume-title":"Grounding dino 1.5: Ad-vance the \u201cedge\u201d of open-set object detection","author":"Ren","year":"2024"},{"key":"ref38","volume-title":"Grounded sam: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00398"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00220"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1193\/1.1650865"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/icra40945.2020.9196985"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3085870"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3390\/rs12101688"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1080\/01431168908903939"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.3390\/rs11091123"},{"key":"ref47","article-title":"Eva-clip: Improved training techniques for clip at scale","author":"Sun","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/wacv51458.2022.00323"},{"key":"ref49","article-title":"How to reduce change detection to semantic segmentation","volume":"abs\/2206.07557","author":"Wang","year":"2022","journal-title":"Ar Xiv"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.3390\/rs13050905"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01308"},{"key":"ref52","volume-title":"Semantic change detection with asymmetric siamese networks","author":"Yang","year":"2021"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2016.2590322"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3160007"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3475824"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1080\/10095020.2022.2128902"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,20]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11373940\/11374285\/11374365.pdf?arnumber=11374365","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T07:44:40Z","timestamp":1771919080000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11374365\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/iccvw69036.2025.00294","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}