{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:58:16Z","timestamp":1777888696328,"version":"3.51.4"},"reference-count":47,"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\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["62225605"],"award-info":[{"award-number":["62225605"]}],"id":[{"id":"10.13039\/100000001","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\/iccv51701.2025.02139","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"23041-23050","source":"Crossref","is-referenced-by-count":0,"title":["Boosting Vision Semantic Density with Anatomy Normality Modeling for Medical Vision-Language Pre-Training"],"prefix":"10.1109","author":[{"given":"Weiwei","family":"Cao","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianpeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongyi","family":"Shui","sequence":"additional","affiliation":[{"name":"DAMO Academy, Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sinuo","family":"Wang","sequence":"additional","affiliation":[{"name":"DAMO Academy, Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zeli","family":"Chen","sequence":"additional","affiliation":[{"name":"DAMO Academy, Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xi","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Le","family":"Lu","sequence":"additional","affiliation":[{"name":"DAMO Academy, Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xianghua","family":"Ye","sequence":"additional","affiliation":[{"name":"Zhejiang University,The First Affiliated Hospital of College of Medicine"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tingbo","family":"Liang","sequence":"additional","affiliation":[{"name":"Zhejiang University,The First Affiliated Hospital of College of Medicine"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhejiang University,The First Affiliated Hospital of College of Medicine"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ling","family":"Zhang","sequence":"additional","affiliation":[{"name":"DAMO Academy, Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3435571"},{"key":"ref2","article-title":"Qwen technical report","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Merlin: A vision language foundation model for 3d computed tomography","author":"Blankemeier","year":"2024","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21037\/atm.2020.02.44"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01068"},{"key":"ref6","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"International conference on machine learning","author":"Chen","year":"2020"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547948"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00201"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01953"},{"key":"ref11","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101857"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01186"},{"key":"ref14","article-title":"A foundation model utilizing chest ct volumes and radiology reports for supervisedlevel zero-shot detection of abnormalities","author":"Hamamci","year":"2024","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-020-01008-z"},{"key":"ref20","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume":"34","author":"Li","year":"2021","journal-title":"NeurIPS"},{"key":"ref21","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International conference on machine learning","author":"Li","year":"2022"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00325"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72120-5_8"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2024.3421599"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02240"},{"key":"ref27","article-title":"Ct-glip: 3d grounded languageimage pretraining with ct scans and radiology reports for full-body scenarios","author":"Lin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref28","article-title":"Imitate: Clinical prior guided hierarchical vision-language pre-training","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29826"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_39"},{"key":"ref31","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.21"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3439950"},{"key":"ref34","first-page":"8748","volume-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"ref35","article-title":"Large-scale and fine-grained vision-language pre-training for enhanced ct image understanding","author":"Shui","year":"2025","journal-title":"ICLR"},{"issue":"12","key":"ref36","first-page":"1399","article-title":"Ng, and Pranav Rajpurkar","volume":"6","author":"Tiu","year":"2022","journal-title":"Expert-level detection of pathologies from unannotated chest x-ray images via self-supervised learning. Nature Biomedical Engineering"},{"key":"ref37","article-title":"Neural discrete representation learning","volume":"30","author":"Van Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref38","article-title":"Neural discrete representation learning","volume":"30","author":"Van Den Oord","year":"2017","journal-title":"NeurIPS"},{"key":"ref39","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref40","first-page":"33536","article-title":"Multi-granularity cross-modal alignment for generalized medical visual representation learning","volume":"35","author":"Wang","year":"2022","journal-title":"NeurIPS"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.230024.podcast"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01954"},{"key":"ref43","article-title":"Multimodal chatgpt for medical applications: an experimental study of gpt-4v","author":"Yan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-40260-7"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6989"},{"key":"ref46","article-title":"Advancing radiograph representation learning with masked record modeling","author":"Zhou","year":"2023","journal-title":"arXiv preprint"},{"key":"ref47","article-title":"Large model driven radiology report generation with clinical quality reinforcement learning","author":"Zhou","year":"2024","journal-title":"arXiv preprint"}],"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\/11444916.pdf?arnumber=11444916","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:55:01Z","timestamp":1777611301000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444916\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02139","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}