{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:39Z","timestamp":1777865379990,"version":"3.51.4"},"reference-count":69,"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\/iccv51701.2025.02266","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"24445-24455","source":"Crossref","is-referenced-by-count":0,"title":["Seeing the Trees for the Forest: Rethinking Weakly-Supervised Medical Visual Grounding"],"prefix":"10.1109","author":[{"given":"Ta Duc","family":"Huy","sequence":"first","affiliation":[{"name":"Australian Institute for Machine Learning, University of Adelaide"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Duy Anh","family":"Huynh","sequence":"additional","affiliation":[{"name":"Australian Institute for Machine Learning, University of Adelaide"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yutong","family":"Xie","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuankai","family":"Qi","sequence":"additional","affiliation":[{"name":"Macquarie University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Chen","sequence":"additional","affiliation":[{"name":"Australian Institute for Machine Learning, University of Adelaide"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Phi","family":"Le Nguyen","sequence":"additional","affiliation":[{"name":"Hanoi University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sen Kim","family":"Tran","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Son Lam","family":"Phung","sequence":"additional","affiliation":[{"name":"University of Wollongong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anton","family":"van den Hengel","sequence":"additional","affiliation":[{"name":"Australian Institute for Machine Learning, University of Adelaide"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhibin","family":"Liao","sequence":"additional","affiliation":[{"name":"Australian Institute for Machine Learning, University of Adelaide"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minh-Son","family":"To","sequence":"additional","affiliation":[{"name":"Flinders University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Johan W.","family":"Verjans","sequence":"additional","affiliation":[{"name":"Australian Institute for Machine Learning, University of Adelaide"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vu Minh Hieu","family":"Phan","sequence":"additional","affiliation":[{"name":"Australian Institute for Machine Learning, University of Adelaide"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00182"},{"key":"ref3","article-title":"Exploring visual prompts for adapting large-scale models","author":"Bahng","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01442"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87196-3_53"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_1"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00132"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00045"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00425"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681058"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43990-2_35"},{"key":"ref12","article-title":"Chexagent: Towards a foundation model for chest x-ray interpretation","author":"Chen","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00269"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-020-00741-6"},{"key":"ref17","article-title":"Adam: A method for stochastic optimization","author":"Diederik","year":"2014","journal-title":"(No Title)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00430"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01369"},{"key":"ref20","volume-title":"Medrax: Medical reasoning agent for chest x-ray","author":"Fallahpour","year":"2025"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_44"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/isbi60581.2025.10981029"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01244"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1349"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02868"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43904-9_59"},{"key":"ref27","article-title":"Radgraph: Extracting clinical entities and relations from radiology reports","author":"Jain","year":"2021","journal-title":"NeurIPS"},{"key":"ref28","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"International Conference on Machine Learning","author":"Jia"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01507"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00263"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-019-0322-0"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref35","article-title":"Covlm: Composing visual entities and relationships in large language models via communicative decoding","author":"Li","year":"2024","journal-title":"ICLR"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445738"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00270"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351074"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00556"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00265"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.89"},{"key":"ref42","article-title":"Localizing before answering: A hallucination evaluation benchmark for grounded medical multimodal 11 ms","author":"Nguyen","year":"2025","journal-title":"arXiv e-prints"},{"key":"ref43","volume-title":"Gpt-4 technical report","year":"2023"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01092"},{"key":"ref45","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_49"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00669"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2046"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2019180041"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.028"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01101"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3058684"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-022-00936-9"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICARSC52212.2021.9429801"},{"key":"ref55","first-page":"8465","article-title":"Found a reason for me? weakly-supervised grounded visual question answering using capsules","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Urooj"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3387702"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00476"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01387"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00782"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01954"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103304"},{"issue":"2","key":"ref63","article-title":"A simple baseline for zeroshot semantic segmentation with pre-trained vision-language model","volume":"3","author":"Xu","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref64","article-title":"Florence: A new foundation model for computer vision","author":"Yuan","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref65","article-title":"Biomedclip: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs","author":"Zhang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73242-3_9"},{"key":"ref69","first-page":"1136","article-title":"Read before grounding: Scene knowledge visual grounding via multi-step parsing","volume-title":"Proceedings of the 31st International Conference on Computational Linguistics","author":"Zhu"}],"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\/11446174.pdf?arnumber=11446174","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:22:43Z","timestamp":1777530163000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446174\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02266","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}