{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T09:05:20Z","timestamp":1771923920211,"version":"3.50.1"},"reference-count":39,"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\/iccvw69036.2025.00133","type":"proceedings-article","created":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T20:44:02Z","timestamp":1771879442000},"page":"1245-1254","source":"Crossref","is-referenced-by-count":0,"title":["Knowledge-Driven Query Network with Adaptive Cross-View Attention for Structured Radiology Report Generation"],"prefix":"10.1109","author":[{"given":"Xuege","family":"Hou","sequence":"first","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yali","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengjin","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"65","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments","volume-title":"Proceedings of the acl workshop on in-trinsic and extrinsic evaluation measures for machine translation and\/or summarization","author":"Banerjee"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01346"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.112"},{"key":"ref4","article-title":"Cross-modal memory networks for radiology report generation","author":"Chen","year":"2022","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocv080"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref8","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.138"},{"key":"ref10","article-title":"Clinicalbert: Modeling clinical notes and predicting hospital read-mission","author":"Huang","year":"2019","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01897"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"ref13","article-title":"Rad-graph: Extracting clinical entities and relations from radiol-ogy reports","author":"Jain","year":"2021","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p18-1240"},{"key":"ref15","article-title":"Mimic-cxr-jpg, a large publicly available database of labeled chest radiographs","author":"Johnson","year":"2019","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btz682"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016666"},{"key":"ref18","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"},{"key":"ref19","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00325"},{"key":"ref21","article-title":"Hy-brid retrieval-generation reinforced agent for medical image report generation","volume":"31","author":"Li","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref22","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Chin-Yew","year":"2004","journal-title":"Text summarization branches out"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29826"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01354"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.23"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.345"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.38"},{"key":"ref29","first-page":"7008","article-title":"Self-critical sequence training for image captioning","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Steven"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3026098"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01112"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01954"},{"key":"ref35","article-title":"Vicuna: Visual and contextual unified network for accurate medical report generation","volume-title":"Proceedings of the [Conference Name]","author":"Xu"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20204"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102510"},{"key":"ref38","article-title":"Opt: Open pre-trained transformer language models","author":"Zhang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00483"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,20]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11373940\/11374285\/11375664.pdf?arnumber=11375664","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T08:07:01Z","timestamp":1771920421000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11375664\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/iccvw69036.2025.00133","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}