{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T03:33:29Z","timestamp":1782963209113,"version":"3.54.5"},"reference-count":60,"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\/501100001381","name":"National Research Foundation Singapore","doi-asserted-by":"publisher","award":["RIE2025"],"award-info":[{"award-number":["RIE2025"]}],"id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Industry Alignment Fund (Cisco-National University of Singapore","award":["I2101E0002"],"award-info":[{"award-number":["I2101E0002"]}]},{"name":"Artificial Intelligence (AI) Singapore Program","award":["AISG2-TC-2022-004"],"award-info":[{"award-number":["AISG2-TC-2022-004"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62406036"],"award-info":[{"award-number":["62406036"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Social Media Processing (SMP)-Zhipu.AI Large Model Cross-Disciplinary Fund","award":["ZPCG20241029322"],"award-info":[{"award-number":["ZPCG20241029322"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tip.2025.3558446","type":"journal-article","created":{"date-parts":[[2025,4,11]],"date-time":"2025-04-11T18:07:35Z","timestamp":1744394855000},"page":"2421-2434","source":"Crossref","is-referenced-by-count":9,"title":["Cross-Modal Knowledge Diffusion-Based Generation for Difference-Aware Medical VQA"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5650-0600","authenticated-orcid":false,"given":"Qika","family":"Lin","sequence":"first","affiliation":[{"name":"Saw Swee Hock School of Public Health, National University of Singapore, Queenstown, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"He","sequence":"additional","affiliation":[{"name":"Saw Swee Hock School of Public Health, National University of Singapore, Queenstown, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7695-1633","authenticated-orcid":false,"given":"Yifan","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4712-0547","authenticated-orcid":false,"given":"Fangzhi","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an, Shaanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3030-1280","authenticated-orcid":false,"given":"Erik","family":"Cambria","sequence":"additional","affiliation":[{"name":"College of Computing and Data Science, Nanyang Technological University, Jurong West, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5338-6248","authenticated-orcid":false,"given":"Mengling","family":"Feng","sequence":"additional","affiliation":[{"name":"Saw Swee Hock School of Public Health, National University of Singapore, Queenstown, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.743"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.133"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-14305-w"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3381435"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3273390"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28279"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-022-01981-2"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3193288"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102795"},{"key":"ref10","article-title":"EsurvFusion: An evidential multimodal survival fusion model based on Gaussian random fuzzy numbers","author":"Huang","year":"2024","journal-title":"arXiv:2412.01215"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102017"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102134"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599819"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3238511"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3626235"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2023.102611"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413761"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3232411"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3090866"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3139333"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI48211.2021.9434010"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2022.103241"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2023.3294249"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20218"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3328224"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00263"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3365104"},{"key":"ref28","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL-HLT","author":"Devlin"},{"key":"ref29","article-title":"Diffusion-LM improves controllable text generation","volume-title":"Proc. NeurIPS","author":"Li"},{"key":"ref30","article-title":"DiffuSeq: Sequence to sequence text generation with diffusion models","volume-title":"Proc. ICLR","author":"Gong"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-15555-y"},{"key":"ref33","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":"ref34","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. ICLR","author":"Dosovitskiy"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-022-00936-9"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3231463"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3306910"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380027"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532016"},{"key":"ref40","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NeurIPS","author":"Ho"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.919"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00198"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref44","article-title":"Gemini: A family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv:2312.11805"},{"key":"ref45","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"OpenAI","year":"2023"},{"key":"ref46","article-title":"Many-shot in-context learning","author":"Agarwal","year":"2024","journal-title":"arXiv:2404.11018"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.3115\/1626355.1626389"},{"key":"ref49","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text Summarization Branches Out"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref51","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. NeurIPS","volume":"28","author":"Ren"},{"key":"ref52","article-title":"Chest ImaGenome dataset for clinical reasoning","volume-title":"Proc. NeurIPS","author":"Wu"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6989"},{"key":"ref54","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref55","article-title":"Can GPT-4V(ision) serve medical applications? Case studies on GPT-4V for multimodal medical diagnosis","author":"Wu","year":"2023","journal-title":"arXiv:2310.09909"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2025.3536008"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.102963"},{"key":"ref58","article-title":"Self-supervised quantized representation for seamlessly integrating knowledge graphs with large language models","author":"Lin","year":"2025","journal-title":"arXiv:2501.18119"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.71"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-44824-z"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10795784\/10964089.pdf?arnumber=10964089","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T17:42:51Z","timestamp":1745602971000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10964089\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/tip.2025.3558446","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}