{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T16:56:38Z","timestamp":1792169798693,"version":"4.4.0"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306037"],"award-info":[{"award-number":["62306037"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62025104"],"award-info":[{"award-number":["62025104"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U22A2052"],"award-info":[{"award-number":["U22A2052"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61771056"],"award-info":[{"award-number":["61771056"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tip.2025.3623915","type":"journal-article","created":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T17:39:39Z","timestamp":1761673179000},"page":"7391-7406","source":"Crossref","is-referenced-by-count":2,"title":["VTAG: Visual-Textual Association Guided Radiology Reports Generation"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-3137-6389","authenticated-orcid":false,"given":"Zhaoli","family":"Su","sequence":"first","affiliation":[{"name":"School of Medical Technology, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9039-0318","authenticated-orcid":false,"given":"Yucong","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Optics and Photonics, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3171-2604","authenticated-orcid":false,"given":"Hong","family":"Song","sequence":"additional","affiliation":[{"name":"Zhengzhou Research Institute, Beijing Institute of Technology, Zhengzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6437-0387","authenticated-orcid":false,"given":"Ruoyi","family":"Jian","sequence":"additional","affiliation":[{"name":"McCormick School of Engineering, Northwestern University, Evanston, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bowen","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Medical Technology, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1250-6319","authenticated-orcid":false,"given":"Jian","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Optics and Photonics, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.chest.2022.12.003"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.2214\/ajr.24.30920"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.2991\/jaims.d.210428.002"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2020.101878"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3522747"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16258"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref10","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref11","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"arXiv:1706.03762"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/2273\/1\/012029"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2020.09.003"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3390\/s23052385"},{"key":"ref15","article-title":"How do vision transformers work?","author":"Park","year":"2022","journal-title":"arXiv:2202.06709"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3390\/rs15102696"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25111"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pdig.0000198"},{"key":"ref19","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref20","author":"Radford","year":"2025","journal-title":"Improving Language Understanding by Generative Pre-Training"},{"key":"ref21","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref22","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref23","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref24","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022","journal-title":"arXiv:2205.01068"},{"key":"ref25","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Lu"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.metrad.2023.100033"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.bionlp-1.35"},{"key":"ref28","article-title":"LLM-CXR: Instruction-finetuned LLM for CXR image understanding and generation","author":"Lee","year":"2023","journal-title":"arXiv:2305.11490"},{"key":"ref29","first-page":"28541","article-title":"LLaVA-med: Training a large language-and-vision assistant for biomedicine in one day","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref30","article-title":"Improving factual completeness and consistency of image-to-text radiology report generation","volume-title":"arXiv:2010.10042","author":"Miura","year":"2020"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00718"},{"key":"ref32","article-title":"A survey of deep learning-based radiology report generation using multimodal data","volume-title":"arXiv:2405.12833","author":"Wang","year":"2024"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.112"},{"key":"ref34","article-title":"On the automatic generation of medical imaging reports","volume-title":"arXiv:1711.08195","author":"Jing","year":"2017"},{"key":"ref35","first-page":"249","article-title":"Clinically accurate chest X-ray report generation","volume-title":"Proc. Mach. Learn. Healthcare Conf.","author":"Liu"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2018.07.007"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-019-0322-0"},{"key":"ref38","article-title":"MIMIC-CXR database(version 2.0.0)","author":"Johnson","year":"2019"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20351-1_10"},{"issue":"140","key":"ref42","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"ref43","article-title":"BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension","author":"Lewis","year":"2019","journal-title":"arXiv:1910.13461"},{"issue":"8","key":"ref44","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/BigData59044.2023.10386743"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1410-8"},{"key":"ref47","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","volume-title":"Proc. 12th Int. Conf. Learn. Represent. (ICLR)","author":"Zhu","year":"2025"},{"key":"ref48","article-title":"MiniGPT-5: Interleaved vision-and-language generation via generative vokens","author":"Zheng","year":"2023","journal-title":"arXiv:2310.02239"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16437-8_63"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-40260-7"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87199-4_7"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01354"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.387"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28038"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.23"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00968"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref59","first-page":"121","article-title":"The UMLS knowledge sources: Tools for building better user interfaces","volume-title":"Proc. Annu. Symp. Comput. Appl. Med. Care","author":"Lindberg"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1161\/01.CTR.101.23.e215"},{"key":"ref61","article-title":"Chest ImaGenome dataset for clinical reasoning","author":"Wu","year":"2021","journal-title":"arXiv:2108.00316"},{"key":"ref62","article-title":"Cross-modal memory networks for radiology report generation","volume-title":"arXiv:2204.13258","author":"Chen","year":"2022"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocv080"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref65","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Measures Mach. Transl. Summarization","author":"Banerjee"},{"key":"ref66","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Proc. Text Summarization Branches Out","author":"Lin"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.117"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/s00357-019-09345-1"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2023.102633"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01897"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01112"},{"key":"ref74","article-title":"Qwen2.5-VL technical report","volume-title":"arXiv:2502.13923","author":"Bai","year":"2025"},{"key":"ref75","article-title":"The llama 3 herd of models","author":"Grattafiori","year":"2024","journal-title":"arXiv:2407.21783"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10795784\/11218752.pdf?arnumber=11218752","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T18:43:35Z","timestamp":1763405015000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11218752\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/tip.2025.3623915","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}