{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T07:12:22Z","timestamp":1772694742204,"version":"3.50.1"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"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":["81860318"],"award-info":[{"award-number":["81860318"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Kunming University of Science and Technology Talent Introduction Research Fund Project","award":["KKZ3202203020"],"award-info":[{"award-number":["KKZ3202203020"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Med. Imaging"],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/tmi.2025.3617289","type":"journal-article","created":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T17:36:45Z","timestamp":1759772205000},"page":"1075-1087","source":"Crossref","is-referenced-by-count":0,"title":["Beyond Static Knowledge: Dynamic Context-Aware Cross-Modal Contrastive Learning for Medical Visual Question Answering"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-9398-4245","authenticated-orcid":false,"given":"Rui","family":"Yang","sequence":"first","affiliation":[{"name":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, Yunnan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4543-0111","authenticated-orcid":false,"given":"Lijun","family":"Liu","sequence":"additional","affiliation":[{"name":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, Yunnan, China"}]},{"given":"Xupeng","family":"Feng","sequence":"additional","affiliation":[{"name":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, Yunnan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9572-951X","authenticated-orcid":false,"given":"Wei","family":"Peng","sequence":"additional","affiliation":[{"name":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, Yunnan, China"}]},{"given":"Xiaobing","family":"Yang","sequence":"additional","affiliation":[{"name":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, Yunnan, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102270"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2023.102611"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"136507","DOI":"10.1109\/ACCESS.2023.3335216","article-title":"A critical analysis of benchmarks, techniques, and models in medical visual question answering","volume":"11","author":"Al-Hadhrami","year":"2023","journal-title":"IEEE Access"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-1354-1_1"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"50626","DOI":"10.1109\/ACCESS.2020.2980024","article-title":"CGMVQA: A new classification and generative model for medical visual question answering","volume":"8","author":"Ren","year":"2020","journal-title":"IEEE Access"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-79103-1_25"},{"key":"ref7","first-page":"6126","article-title":"Eye-gaze guided multi-modal alignment for medical representation learning","volume-title":"Proc. NeurIPS","volume":"37","author":"Ma"},{"issue":"4","key":"ref8","doi-asserted-by":"crossref","first-page":"1886","DOI":"10.1109\/JBHI.2023.3294249","article-title":"K-PathVQA: Knowledge-aware multimodal representation for pathology visual question answering","volume":"28","author":"Naseem","year":"2024","journal-title":"IEEE J. Biomed. Health Informat."},{"issue":"2","key":"ref9","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2022.103241","article-title":"Medical knowledge-based network for patient-oriented visual question answering","volume":"60","author":"Huang","year":"2023","journal-title":"Inf. Process. Manage."},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00502"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-024-01390-4"},{"key":"ref12","article-title":"ChunkRAG: Novel LLM-chunk filtering method for RAG systems","author":"Sukhvinder Singh","year":"2024","journal-title":"arXiv:2410.19572"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-24318-0_67"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI48211.2021.9434010"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2018.251"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32251-9_57"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI48211.2021.9434063"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-eacl.88"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref20","first-page":"1571","article-title":"Bilinear attention networks","volume-title":"Proc. NeurIPS","author":"Kim"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00637"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2022.109763","article-title":"AMAM: An attention-based multimodal alignment model for medical visual question answering","volume":"255","author":"Pan","year":"2022","journal-title":"Knowl.-Based Syst."},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.1016\/j.artmed.2023.102667","article-title":"Asymmetric cross-modal attention network with multimodal augmented mixup for medical visual question answering","volume":"144","author":"Li","year":"2023","journal-title":"Artif. Intell. Med."},{"issue":"2","key":"ref24","doi-asserted-by":"crossref","first-page":"832","DOI":"10.1109\/TMI.2023.3322868","article-title":"A dual-attention learning network with word and sentence embedding for medical visual question answering","volume":"43","author":"Huang","year":"2024","journal-title":"IEEE Trans. Med. Imag."},{"key":"ref25","first-page":"33536","article-title":"Multi-granularity cross-modal alignment for generalized medical visual representation learning","volume-title":"Proc. NeurIPS","author":"Wang"},{"issue":"2","key":"ref26","doi-asserted-by":"crossref","DOI":"10.1016\/j.jnlest.2022.100159","article-title":"Knowledge graph and knowledge reasoning: A systematic review","volume":"20","author":"Tian","year":"2022","journal-title":"J. Electron. Sci. Technol."},{"key":"ref27","doi-asserted-by":"crossref","first-page":"494","DOI":"10.1016\/j.neucom.2021.05.101","article-title":"Knowledge graph representation and reasoning","volume":"461","author":"Cambria","year":"2021","journal-title":"Neurocomputing"},{"key":"ref28","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2022.109459","article-title":"Federated knowledge graph completion via embedding-contrastive learning","volume":"252","author":"Chen","year":"2022","journal-title":"Knowl.-Based Syst."},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-022-04934-1"},{"issue":"1","key":"ref30","first-page":"1","article-title":"Learning entity and relation embeddings for knowledge graph completion","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"29","author":"Lin"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1117\/12.3056789"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-93417-4_38"},{"key":"ref33","first-page":"4710","article-title":"Learning attention-based embeddings for relation prediction in knowledge graphs","volume-title":"Proc. 57th Annu. Meeting Assoc. Comput. Linguistics","author":"Nathani"},{"key":"ref34","first-page":"2417","article-title":"Modality-aware integration with large language models for knowledge-based visual question answering","volume-title":"Proc. 62nd Annu. Meeting Assoc. Comput. Linguistics","volume":"1","author":"Dong"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000065"},{"key":"ref36","article-title":"Towards medical artificial general intelligence via knowledge-enhanced multimodal pretraining","author":"Lin","year":"2023","journal-title":"arXiv:2304.14204"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref38","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.128614","article-title":"Decoupled semantic graph neural network for knowledge graph embedding","volume":"611","author":"Li","year":"2025","journal-title":"Neurocomputing"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref40","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1016\/j.patrec.2021.07.002","article-title":"Visual question answering in the medical domain based on deep learning approaches: A comprehensive study","volume":"150","author":"Al-Sadi","year":"2021","journal-title":"Pattern Recognit. Lett."},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1148\/rg.266065168"},{"key":"ref42","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2023.103018","article-title":"Mapping medical image-text to a joint space via masked modeling","volume":"91","author":"Chen","year":"2024","journal-title":"Med. Image Anal."},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3232411"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121526"},{"key":"ref45","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.128730","article-title":"VG-CALF: A vision-guided cross-attention and late-fusion network for radiology images in medical visual question answering","volume":"613","author":"Lameesa","year":"2025","journal-title":"Neurocomputing"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI53787.2023.10230743"},{"key":"ref47","article-title":"HuatuoGPT-vision, towards injecting medical visual knowledge into multimodal LLMs at scale","author":"Chen","year":"2024","journal-title":"arXiv:2406.19280"},{"key":"ref48","article-title":"MMedAgent-RL: Optimizing multi-agent collaboration for multimodal medical reasoning","author":"Xia","year":"2025","journal-title":"arXiv:2506.00555"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.319"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2024.103805"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.129999"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01228-7"}],"container-title":["IEEE Transactions on Medical Imaging"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/42\/11421252\/11192609.pdf?arnumber=11192609","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T06:31:41Z","timestamp":1772692301000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11192609\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":52,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tmi.2025.3617289","relation":{},"ISSN":["0278-0062","1558-254X"],"issn-type":[{"value":"0278-0062","type":"print"},{"value":"1558-254X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}