{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:21:10Z","timestamp":1777890070615,"version":"3.51.4"},"reference-count":80,"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\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2022ZD0160101,2022ZD0160102"],"award-info":[{"award-number":["2022ZD0160101,2022ZD0160102"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272450"],"award-info":[{"award-number":["62272450"]}],"id":[{"id":"10.13039\/501100001809","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\/iccv51701.2025.01845","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1-12","source":"Crossref","is-referenced-by-count":0,"title":["OphCLIP: Hierarchical Retrieval-Augmented Learning for Ophthalmic Surgical Video-Language Pretraining"],"prefix":"10.1109","author":[{"given":"Ming","family":"Hu","sequence":"first","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kun","family":"Yuan","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaling","family":"Shen","sequence":"additional","affiliation":[{"name":"Monash University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feilong","family":"Tang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaohao","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Michigan,Ann Arbor"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin","family":"Zhou","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongxing","family":"Xu","sequence":"additional","affiliation":[{"name":"Monash University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zelin","family":"Peng","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siyuan","family":"Yan","sequence":"additional","affiliation":[{"name":"Monash University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vinkle","family":"Srivastav","sequence":"additional","affiliation":[{"name":"University of Strasbourg"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Diping","family":"Song","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianbin","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Danli","family":"Shi","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jin","family":"Ye","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nicolas","family":"Padoy","sequence":"additional","affiliation":[{"name":"University of Strasbourg"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nassir","family":"Navab","sequence":"additional","affiliation":[{"name":"Technische Universitat Munchen"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junjun","family":"He","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zongyuan","family":"Ge","sequence":"additional","affiliation":[{"name":"Monash University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.02209"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2015.02.007"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s41060-023-00433-5"},{"key":"ref5","first-page":"2206","article-title":"Improving language models by retrieving from trillions of tokens","volume-title":"International conference on machine learning","author":"Borgeaud"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102569"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref8","article-title":"Chexagent: Towards a foundation model for chest x-ray interpretation","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1544"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CBMS49503.2020.00112"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412525"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87237-3_8"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-024-03193-4"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102053"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3458754"},{"key":"ref16","article-title":"Vidlpro: A video-language pretraining framework for robotic and laparoscopic surgery","author":"Honarmand","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_27"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02238"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-023-02504-3"},{"key":"ref20","first-page":"36","article-title":"Quilt-1m: One million image-text pairs for histopathology","author":"Ikezogwo","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref21","article-title":"Retrieval-enhanced contrastive vision-text models","author":"Iscen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2021.3049304"},{"key":"ref23","article-title":"Mimic-cxr-jpg, a large publicly available database of labeled chest radiographs","author":"Johnson","year":"2019","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref25","article-title":"A large-scale analysis on self-supervised video representation learning","author":"Kumar","year":"2023","journal-title":"arXiv e-prints"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/wacv57701.2024.00214"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-66185-8_75"},{"key":"ref28","article-title":"Llava-surg: Towards multimodal surgical assistant via structured surgical video learning","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01303"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01826"},{"key":"ref31","article-title":"Supervision exists everywhere: A data efficient contrastive language-image pre-training paradigm","author":"Li","year":"2021","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01927"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00683"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00695"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3390\/gastroent13030027"},{"key":"ref38","first-page":"529","article-title":"Slip: Self-supervision meets language-image pretraining","volume-title":"European conference on computer vision","author":"Mu"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_1"},{"key":"ref40","article-title":"Capabilities of gpt-4 on medical challenge problems","author":"Nori","year":"2023","journal-title":"arXiv preprint"},{"key":"ref41","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32692-0_65"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340816"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3390\/surgeries4010010"},{"key":"ref45","first-page":"241","article-title":"Frame-based classification of operation phases in cataract surgery videos","volume-title":"MultiMedia Modeling - 24th International Conference, MMM 2018","author":"J\u00fcrgen Primus","year":"2018"},{"key":"ref46","article-title":"Medical image understanding with pretrained vision language models: A comprehensive study","author":"Qin","year":"2022","journal-title":"arXiv preprint"},{"key":"ref47","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref48","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00605"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00278"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3549555.3549585"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3577925"},{"key":"ref53","article-title":"Gp-vls: A general-purpose vision language model for surgery","author":"Schmidgall","year":"2024","journal-title":"arXiv preprint"},{"key":"ref54","article-title":"General surgery vision transformer: A video pre-trained foundation model for general surgery","author":"Schmidgall","year":"2024","journal-title":"arXiv preprint"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-017-5252-2"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3204949.3208137"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_9"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43996-4_27"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2018.00100"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-013-0926-3"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-021-00920-z"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-02970-3"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102770"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00795"},{"key":"ref66","article-title":"Clinicalgpt: large language models finetuned with diverse medical data and comprehensive evaluation","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref67","article-title":"Surgical-1vlm: Learning to adapt large vision-language model for grounded visual question answering in robotic surgery","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43996-4_10"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01284"},{"key":"ref70","article-title":"Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2025.103644"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72089-5_29"},{"key":"ref73","article-title":"Procedure-aware surgical video-language pretraining with hierarchical knowledge augmentation","author":"Yuan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00692"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_23"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.725"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1243"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01451"},{"key":"ref80","first-page":"36","article-title":"Segment everything everywhere all at once","author":"Zou","year":"2024","journal-title":"Advances in Neural Information Processing Systems"}],"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\/11444472.pdf?arnumber=11444472","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:29:36Z","timestamp":1777613376000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444472\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":80,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01845","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}