{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:01Z","timestamp":1777865341214,"version":"3.51.4"},"reference-count":48,"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\/iccv51701.2025.00174","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1783-1792","source":"Crossref","is-referenced-by-count":0,"title":["Towards Cross-Modal Backward-Compatible Representation Learning for Vision-Language Models"],"prefix":"10.1109","author":[{"given":"Young Kyun","family":"Jang","sequence":"first","affiliation":[{"name":"Google DeepMind"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ser-nam","family":"Lim","sequence":"additional","affiliation":[{"name":"University of Central Florida"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00904"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.753"},{"key":"ref3","author":"Ba","year":"2016","journal-title":"Layer normalization"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00020"},{"key":"ref5","article-title":"Efficient lifelong learning with a-gem","author":"Chaudhry","year":"2019","journal-title":"ICLR"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1369-5"},{"key":"ref7","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2021.3057446","article-title":"A continual learning survey: Defying forgetting in classification tasks","author":"De Lange","year":"2021","journal-title":"TPAMI"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01256"},{"key":"ref9","author":"Hendrycks","year":"2016","journal-title":"Gaussian error linear units (gelus)"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref11","article-title":"One loss for all: Deep hashing with a single cosine similarity based learning objective","author":"Hoe","year":"2021","journal-title":"NeurIPS"},{"key":"ref12","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"ICLR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539194"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/1460096.1460104"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00348"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_21"},{"key":"ref17","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","author":"Jia","year":"2021","journal-title":"ICML"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref19","volume-title":"How to adapt your large-scale vision-and-language model","author":"Kim","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref21","article-title":"Blip: Bootstrapping language-image pre-training for unified visionlanguage understanding and generation","author":"Li","year":"2022","journal-title":"ICML"},{"key":"ref22","article-title":"Supervision exists everywhere: A data efficient contrastive languageimage pre-training paradigm","author":"Li","year":"2022","journal-title":"ICLR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref24","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"ICLR"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2015.01.010"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00979"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.299"},{"key":"ref28","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01878"},{"key":"ref30","article-title":"Content based image retrieval: survey","author":"Rehman","year":"2012","journal-title":"World Applied Sciences Journal"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref32","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","author":"Schuhmann","year":"2022","journal-title":"NeurIPS"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00640"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"ref36","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654948"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.5244\/C.34.55"},{"key":"ref39","article-title":"Learning robust global representations by penalizing local predictive power","volume":"32","author":"Wang","year":"2019","journal-title":"NeurIPS"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00402"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01407"},{"key":"ref43","article-title":"Hot-refresh model upgrades with regression-alleviating compatible training in image retrieval","author":"Zhang","year":"2022","journal-title":"ICLR"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/225"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2020.3029181"},{"key":"ref46","author":"Zhou","year":"2017","journal-title":"Recent advance in content-based image retrieval: A literature survey"},{"key":"ref47","author":"Zhou","year":"2022","journal-title":"bt2: Backward-compatible training with basis transformation"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3004555"}],"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\/11445027.pdf?arnumber=11445027","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:18:31Z","timestamp":1777529911000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445027\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00174","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}