{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:22:08Z","timestamp":1778048528532,"version":"3.51.4"},"reference-count":56,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00233","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"2359-2369","source":"Crossref","is-referenced-by-count":0,"title":["Knowledge to Sight: Reasoning over Visual Attributes via Knowledge Decomposition for Abnormality Grounding"],"prefix":"10.1109","author":[{"given":"Jun","family":"Li","sequence":"first","affiliation":[{"name":"Technical University of Munich"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Che","family":"Liu","sequence":"additional","affiliation":[{"name":"Imperial College London"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenjia","family":"Bai","sequence":"additional","affiliation":[{"name":"Imperial College London"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingxuan","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Trento"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rossella","family":"Arcucci","sequence":"additional","affiliation":[{"name":"Imperial College London"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cosmin I.","family":"Bercea","sequence":"additional","affiliation":[{"name":"Technical University of Munich"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Julia A.","family":"Schnabel","sequence":"additional","affiliation":[{"name":"Technical University of Munich"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms5006"},{"key":"ref3","article-title":"Minigpt-med: Large language model as a general interface for radiology diagnosis","author":"Alkhaldi","year":"2024"},{"key":"ref4","article-title":"Healthbench: Evaluating large language models towards improved human health","author":"Arora","year":"2025"},{"key":"ref5","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023"},{"key":"ref6","article-title":"Maira-2: Grounded radiology report generation","author":"Bannur","year":"2024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_1"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101797"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1056\/aidbp2401120"},{"key":"ref10","article-title":"CheXpert Plus: Augmenting a large chest X-ray dataset with text radiology reports, patient demographics and additional image formats","author":"Chambon","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547948"},{"key":"ref12","article-title":"Chexagent: Towards a foundation model for chest X-ray interpretation","author":"Chen","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocv080"},{"key":"ref14","article-title":"RadVLM: A multitask conversational vision-language model for radiology","author":"Deperrois","year":"2025"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27955"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2462070712"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3310002"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-019-0322-0"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3711680"},{"key":"ref21","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1240"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16452-1_56"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tmi.2024.3424978"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-84525-3_10"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2023.102611"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref28","article-title":"DeepSeek-vl: towards real-world vision-language understanding","author":"Lu","year":"2024"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2025.103514"},{"key":"ref30","article-title":"Devide: Faceted medical knowledge for improved medical vision-language pre-training","author":"Luo","year":"2024"},{"key":"ref31","article-title":"Robust detection outcome: A metric for pathology detection in medical images","author":"Meissen","year":"2023","journal-title":"Medical Imaging with Deep Learning"},{"key":"ref32","first-page":"353","article-title":"Med-flamingo: a multimodal medical few-shot learner","volume-title":"Machine Learning for Health (ML4H)","author":"Moor","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_6"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01498-w"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IWSSIP48289.2020.9145130"},{"key":"ref36","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref37","volume-title":"Radiopaedia.org. Radiomics","year":"2023"},{"key":"ref38","article-title":"Medgemma technical report","author":"Sellergren","year":"2025"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.167"},{"key":"ref40","article-title":"Medical vision language pretraining: A survey","author":"Shrestha","year":"2023"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-03423-7"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3148210"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00718"},{"key":"ref44","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023"},{"key":"ref45","article-title":"Gemma 3 technical report","author":"Team","year":"2025"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2430"},{"key":"ref47","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01954"},{"key":"ref49","article-title":"Medkp: Medical dialogue with knowledge enhancement and clinical pathway encoding","author":"Wu","year":"2024"},{"key":"ref50","article-title":"Chest imagenome dataset for clinical reasoning","author":"Wu","year":"2021"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00461"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3630635"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2992"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-40260-7"},{"key":"ref55","article-title":"Pmc-VQA: Visual instruction tuning for medical visual question answering","author":"Zhang","year":"2023"},{"key":"ref56","article-title":"Internvl3: Exploring advanced training and test-time recipes for open-source multimodal models","author":"Zhu","year":"2025"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492298.pdf?arnumber=11492298","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:08:26Z","timestamp":1778047706000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492298\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00233","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}