{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T20:46:18Z","timestamp":1770756378040,"version":"3.50.0"},"reference-count":79,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000266","name":"EPSRC","doi-asserted-by":"publisher","award":["VisualAI EP \/T028572\/1"],"award-info":[{"award-number":["VisualAI EP \/T028572\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,22]]},"DOI":"10.1109\/cbmi66578.2025.11339290","type":"proceedings-article","created":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T20:38:56Z","timestamp":1768941536000},"page":"1-8","source":"Crossref","is-referenced-by-count":1,"title":["ELIP: Enhanced Visual-Language Foundation Models for Image Retrieval"],"prefix":"10.1109","author":[{"given":"Guanqi","family":"Zhan","sequence":"first","affiliation":[{"name":"University of Oxford,VGG"}]},{"given":"Yuanpei","family":"Liu","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}]},{"given":"Kai","family":"Han","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}]},{"given":"Weidi","family":"Xie","sequence":"additional","affiliation":[{"name":"University of Oxford,VGG"}]},{"given":"Andrew","family":"Zisserman","sequence":"additional","affiliation":[{"name":"University of Oxford,VGG"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Radford"},{"key":"ref2","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Jia"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.29007\/1mjd"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref5","article-title":"Siglip 2: Multilingual vision-language encoders with improved semantic understanding, localization, and dense features","author":"Tschannen","year":"2025","journal-title":"ar Xiv preprint"},{"key":"ref6","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Li"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02053"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref12","article-title":"Elip: Enhanced visual-language foundation models for image retrieval","author":"Zhan","year":"2025","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01267"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01521"},{"key":"ref16","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proceedings of the Advances in Neural Information Processing Systems (NeurIPS)","author":"Li"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01838"},{"key":"ref19","article-title":"Coca: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"Transactions on Machine Learning Research (TMLR)"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01553"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01060"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00831"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00419"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00750"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.767"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00585"},{"key":"ref29","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","volume-title":"Proceedings of the Ad-vances in Neural Information Processing Systems (NeurIPS)","author":"Karpathy"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02243"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350869"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01093"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00208"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_19"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_2"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2797921"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00586"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00277"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01302"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01095"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00800"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3512527.3531358"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20235"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00359"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019291"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4018"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01377"},{"key":"ref50","article-title":"Openclip","author":"Ilharco","year":"2021","journal-title":"if you use this software, please cite it as below."},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72986-7_26"},{"key":"ref52","article-title":"Zero-shot composed text-image retrieval","volume-title":"British Machine Vision Conference (BMVC)","author":"Liu"},{"key":"ref53","article-title":"Compodiff: Versatile composed image retrieval with latent diffusion","author":"Gu","year":"2023","journal-title":"ar Xiv preprint"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01407"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28334"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73021-4_23"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00380"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88682-2_24"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383172"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995601"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4408891"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2014.04.007"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248018"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_43"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01392"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01189"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00480"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2952676"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591712"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657741"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00970"},{"key":"ref72","article-title":"Im2text: Describing images using 1 million captioned photographs","volume-title":"Proceedings of the Advances in Neural Information Processing Systems (NeurIPS)","author":"Ordonez"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref74","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","volume-title":"Proceedings of the Advances in Neural Information Processing Systems (Ne u rIPS)","author":"Schuhmann"},{"key":"ref75","article-title":"Datacomp: In search of the next generation of multimodal datasets","volume-title":"Proceedings of the Advances in Neural Information Processing Systems (NeurIPS)","author":"Gadre"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01511"},{"key":"ref77","article-title":"A tri-layer plug in to improve occluded detection","volume-title":"Proceedings of the British Machine Vision Conference (BMVC)","author":"Zhan"},{"key":"ref78","article-title":"Visual instruction tuning","volume-title":"Proceedings of the Advances in Neural Information Processing Systems (Ne u rIPS)","author":"Liu"},{"key":"ref79","article-title":"Flamingo: a visual language model for few-shot learning","volume-title":"Proceedings of the Advances in Neural Information Processing Systems (NeurIPS)","author":"Alayrac"}],"event":{"name":"2025 International Conference on Content-Based Multimedia Indexing (CBMI)","location":"Dublin, Ireland","start":{"date-parts":[[2025,10,22]]},"end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 International Conference on Content-Based Multimedia Indexing (CBMI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11339229\/11339242\/11339290.pdf?arnumber=11339290","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T07:11:29Z","timestamp":1768979489000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11339290\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":79,"URL":"https:\/\/doi.org\/10.1109\/cbmi66578.2025.11339290","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}