{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T19:26:48Z","timestamp":1792524408720,"version":"4.5.0"},"reference-count":67,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":365,"URL":"http:\/\/www.elsevier.com\/open-access\/userlicense\/1.0\/"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100003471","name":"Harbin Engineering University","doi-asserted-by":"publisher","award":["KYWZ120240601"],"award-info":[{"award-number":["KYWZ120240601"]}],"id":[{"id":"10.13039\/501100003471","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013139","name":"Humanities and Social Science Fund of Ministry of Education of the People's Republic of China","doi-asserted-by":"publisher","award":["23YJAZH079"],"award-info":[{"award-number":["23YJAZH079"]}],"id":[{"id":"10.13039\/501100013139","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Biomedical Informatics"],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1016\/j.jbi.2024.104748","type":"journal-article","created":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T12:33:40Z","timestamp":1731414820000},"page":"104748","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":18,"special_numbering":"C","title":["Cross-Modal self-supervised vision language pre-training with multiple objectives for medical visual question answering"],"prefix":"10.1016","volume":"160","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7032-8429","authenticated-orcid":false,"given":"Gang","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8891-554X","authenticated-orcid":false,"given":"Jinlong","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4234-1579","authenticated-orcid":false,"given":"Pengfei","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zixu","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6542-649X","authenticated-orcid":false,"given":"Shenjun","family":"Zhong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.jbi.2024.104748_b1","series-title":"Medical visual question answering: A survey","author":"Lin","year":"2021"},{"key":"10.1016\/j.jbi.2024.104748_b2","doi-asserted-by":"crossref","unstructured":"O. Kovaleva, C. Shivade, S. Kashyap, K. Kanjaria, J. Wu, D. Ballah, A. Coy, A. Karargyris, Y. Guo, D.B. Beymer, et al., Towards visual dialog for radiology, in: Proceedings of the 19th SIGBioMed Workshop on Biomedical Language Processing, 2020, pp. 60\u201369.","DOI":"10.18653\/v1\/2020.bionlp-1.6"},{"key":"10.1016\/j.jbi.2024.104748_b3","series-title":"CLEF (Working Notes)","article-title":"VQA-Med: Overview of the medical visual question answering task at imageclef 2019","volume":"Vol. 2","author":"Abacha","year":"2019"},{"issue":"1","key":"10.1016\/j.jbi.2024.104748_b4","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/sdata.2018.251","article-title":"A dataset of clinically generated visual questions and answers about radiology images","volume":"5","author":"Lau","year":"2018","journal-title":"Sci. Data"},{"key":"10.1016\/j.jbi.2024.104748_b5","doi-asserted-by":"crossref","unstructured":"X. He, Towards Visual Question Answering on Pathology Images., in: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Vol. 2, 2021.","DOI":"10.18653\/v1\/2021.acl-short.90"},{"key":"10.1016\/j.jbi.2024.104748_b6","doi-asserted-by":"crossref","unstructured":"Y. Goyal, T. Khot, D. Summers-Stay, D. Batra, D. Parikh, Making the v in vqa matter: Elevating the role of image understanding in visual question answering, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 6904\u20136913.","DOI":"10.1109\/CVPR.2017.670"},{"key":"10.1016\/j.jbi.2024.104748_b7","series-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"248","article-title":"Imagenet: A large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"10.1016\/j.jbi.2024.104748_b8","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1146\/annurev-bioeng-071516-044442","article-title":"Deep learning in medical image analysis","volume":"19","author":"Shen","year":"2017","journal-title":"Ann. Rev. Biomed. Eng."},{"issue":"5","key":"10.1016\/j.jbi.2024.104748_b9","doi-asserted-by":"crossref","first-page":"1299","DOI":"10.1109\/TMI.2016.2535302","article-title":"Convolutional neural networks for medical image analysis: Full training or fine tuning?","volume":"35","author":"Tajbakhsh","year":"2016","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.jbi.2024.104748_b10","first-page":"180","article-title":"Radiology objects in context (ROCO): a multimodal image dataset","author":"Pelka","year":"2018"},{"key":"10.1016\/j.jbi.2024.104748_b11","series-title":"Medicat: A dataset of medical images, captions, and textual references","author":"Subramanian","year":"2020"},{"key":"10.1016\/j.jbi.2024.104748_b12","series-title":"CEUR Workshop Proceedings","first-page":"1294","article-title":"Overview of ImageCLEFmedical 2022\u2013caption prediction and concept detection","author":"R\u00fcckert","year":"2022"},{"key":"10.1016\/j.jbi.2024.104748_b13","series-title":"Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XXX","first-page":"104","article-title":"Uniter: Universal image-text representation learning","author":"Chen","year":"2020"},{"key":"10.1016\/j.jbi.2024.104748_b14","series-title":"International Conference on Machine Learning","first-page":"5583","article-title":"Vilt: Vision-and-language transformer without convolution or region supervision","author":"Kim","year":"2021"},{"key":"10.1016\/j.jbi.2024.104748_b15","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.jbi.2024.104748_b16","series-title":"International Conference on Machine Learning","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","author":"Jia","year":"2021"},{"key":"10.1016\/j.jbi.2024.104748_b17","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume":"34","author":"Li","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jbi.2024.104748_b18","series-title":"International Conference on Machine Learning","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","author":"Li","year":"2022"},{"key":"10.1016\/j.jbi.2024.104748_b19","series-title":"2021 IEEE 18th International Symposium on Biomedical Imaging","first-page":"1650","article-title":"Slake: A semantically-labeled knowledge-enhanced dataset for medical visual question answering","author":"Liu","year":"2021"},{"key":"10.1016\/j.jbi.2024.104748_b20","doi-asserted-by":"crossref","unstructured":"R.R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, D. Batra, Grad-cam: Visual explanations from deep networks via gradient-based localization, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 618\u2013626.","DOI":"10.1109\/ICCV.2017.74"},{"key":"10.1016\/j.jbi.2024.104748_b21","series-title":"CLEF (Working Notes)","article-title":"NLM at imageclef 2018 visual question answering in the medical domain","author":"Abacha","year":"2018"},{"key":"10.1016\/j.jbi.2024.104748_b22","article-title":"VQA-Med: Overview of the medical visual question answering task at imageclef 2019","volume":"Vol. 2","author":"Abacha","year":"2019"},{"key":"10.1016\/j.jbi.2024.104748_b23","series-title":"Experimental IR Meets Multilinguality, Multimodality, and Interaction: 9th International Conference of the CLEF Association, CLEF 2018, Avignon, France, September 10-14, 2018, Proceedings 9","first-page":"309","article-title":"Overview of imageclef 2018: Challenges, datasets and evaluation","author":"Ionescu","year":"2018"},{"key":"10.1016\/j.jbi.2024.104748_b24","series-title":"CLEF (Working Notes)","article-title":"Deep multimodal learning for medical visual question answering","author":"Shi","year":"2019"},{"key":"10.1016\/j.jbi.2024.104748_b25","series-title":"CLEF (Working Notes)","article-title":"JUST at imageclef 2019 visual question answering in the medical domain","author":"Al-Sadi","year":"2019"},{"key":"10.1016\/j.jbi.2024.104748_b26","series-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"10.1016\/j.jbi.2024.104748_b27","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"issue":"8","key":"10.1016\/j.jbi.2024.104748_b28","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"10.1016\/j.jbi.2024.104748_b29","series-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"issue":"4","key":"10.1016\/j.jbi.2024.104748_b30","doi-asserted-by":"crossref","first-page":"1234","DOI":"10.1093\/bioinformatics\/btz682","article-title":"BioBERT: a pre-trained biomedical language representation model for biomedical text mining","volume":"36","author":"Lee","year":"2020","journal-title":"Bioinformatics"},{"key":"10.1016\/j.jbi.2024.104748_b31","series-title":"Multimodal compact bilinear pooling for visual question answering and visual grounding","author":"Fukui","year":"2016"},{"key":"10.1016\/j.jbi.2024.104748_b32","doi-asserted-by":"crossref","unstructured":"Z. Yang, X. He, J. Gao, L. Deng, A. Smola, Stacked attention networks for image question answering, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 21\u201329.","DOI":"10.1109\/CVPR.2016.10"},{"key":"10.1016\/j.jbi.2024.104748_b33","article-title":"Bilinear attention networks","volume":"31","author":"Kim","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jbi.2024.104748_b34","doi-asserted-by":"crossref","unstructured":"Z. Yu, J. Yu, J. Fan, D. Tao, Multi-modal factorized bilinear pooling with co-attention learning for visual question answering, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 1821\u20131830.","DOI":"10.1109\/ICCV.2017.202"},{"key":"10.1016\/j.jbi.2024.104748_b35","series-title":"Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13\u201317, 2019, Proceedings, Part IV 22","first-page":"522","article-title":"Overcoming data limitation in medical visual question answering","author":"Nguyen","year":"2019"},{"key":"10.1016\/j.jbi.2024.104748_b36","series-title":"Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2021: 24th International Conference, Strasbourg, France, September 27\u2013October 1, 2021, Proceedings, Part V 24","first-page":"64","article-title":"Multiple meta-model quantifying for medical visual question answering","author":"Do","year":"2021"},{"key":"10.1016\/j.jbi.2024.104748_b37","doi-asserted-by":"crossref","unstructured":"L.-M. Zhan, B. Liu, L. Fan, J. Chen, X.-M. Wu, Medical visual question answering via conditional reasoning, in: Proceedings of the 28th ACM International Conference on Multimedia, 2020, pp. 2345\u20132354.","DOI":"10.1145\/3394171.3413761"},{"issue":"5","key":"10.1016\/j.jbi.2024.104748_b38","doi-asserted-by":"crossref","first-page":"1532","DOI":"10.1109\/TMI.2022.3232411","article-title":"Medical visual question answering via conditional reasoning and contrastive learning","volume":"42","author":"Liu","year":"2023","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.jbi.2024.104748_b39","series-title":"Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2021: 24th International Conference, Strasbourg, France, September 27\u2013October 1, 2021, Proceedings, Part II 24","first-page":"210","article-title":"Contrastive pre-training and representation distillation for medical visual question answering based on radiology images","author":"Liu","year":"2021"},{"issue":"11","key":"10.1016\/j.jbi.2024.104748_b40","doi-asserted-by":"crossref","first-page":"3385","DOI":"10.1109\/TMI.2022.3185113","article-title":"Anomaly matters: An anomaly-oriented model for medical visual question answering","volume":"41","author":"Cong","year":"2022","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.jbi.2024.104748_b41","series-title":"2022 IEEE International Conference on Bioinformatics and Biomedicine","first-page":"567","article-title":"MHKD-MVQA: Multimodal hierarchical knowledge distillation for medical visual question answering","author":"Wang","year":"2022"},{"key":"10.1016\/j.jbi.2024.104748_b42","series-title":"Findings of the Association for Computational Linguistics: EACL 2023","first-page":"1151","article-title":"PubMedCLIP: How much does CLIP benefit visual question answering in the medical domain?","author":"Eslami","year":"2023"},{"key":"10.1016\/j.jbi.2024.104748_b43","doi-asserted-by":"crossref","unstructured":"F. Cong, S. Xu, L. Guo, Y. Tian, Caption-Aware Medical VQA via Semantic Focusing and Progressive Cross-Modality Comprehension, in: Proceedings of the 30th ACM International Conference on Multimedia, 2022, pp. 3569\u20133577.","DOI":"10.1145\/3503161.3548122"},{"key":"10.1016\/j.jbi.2024.104748_b44","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume":"32","author":"Lu","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jbi.2024.104748_b45","series-title":"Lxmert: Learning cross-modality encoder representations from transformers","author":"Tan","year":"2019"},{"key":"10.1016\/j.jbi.2024.104748_b46","series-title":"Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XXX 16","first-page":"121","article-title":"Oscar: Object-semantics aligned pre-training for vision-language tasks","author":"Li","year":"2020"},{"key":"10.1016\/j.jbi.2024.104748_b47","first-page":"6616","article-title":"Large-scale adversarial training for vision-and-language representation learning","volume":"33","author":"Gan","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jbi.2024.104748_b48","doi-asserted-by":"crossref","unstructured":"P. Zhang, X. Li, X. Hu, J. Yang, L. Zhang, L. Wang, Y. Choi, J. Gao, Vinvl: Revisiting visual representations in vision-language models, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 5579\u20135588.","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"10.1016\/j.jbi.2024.104748_b49","first-page":"32897","article-title":"Vlmo: Unified vision-language pre-training with mixture-of-modality-experts","volume":"35","author":"Bao","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jbi.2024.104748_b50","series-title":"Coca: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022"},{"key":"10.1016\/j.jbi.2024.104748_b51","series-title":"2020 IEEE International Conference on Bioinformatics and Biomedicine","first-page":"1999","article-title":"A comparison of pre-trained vision-and-language models for multimodal representation learning across medical images and reports","author":"Li","year":"2020"},{"issue":"12","key":"10.1016\/j.jbi.2024.104748_b52","doi-asserted-by":"crossref","first-page":"6070","DOI":"10.1109\/JBHI.2022.3207502","article-title":"Multi-modal understanding and generation for medical images and text via vision-language pre-training","volume":"26","author":"Moon","year":"2022","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"10.1016\/j.jbi.2024.104748_b53","series-title":"2021 IEEE 18th International Symposium on Biomedical Imaging","first-page":"1033","article-title":"Mmbert: Multimodal bert pretraining for improved medical vqa","author":"Khare","year":"2021"},{"key":"10.1016\/j.jbi.2024.104748_b54","series-title":"Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2022: 25th International Conference, Singapore, September 18\u201322, 2022, Proceedings, Part V","first-page":"679","article-title":"Multi-modal masked autoencoders for medical vision-and-language pre-training","author":"Chen","year":"2022"},{"key":"10.1016\/j.jbi.2024.104748_b55","series-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"10.1016\/j.jbi.2024.104748_b56","doi-asserted-by":"crossref","unstructured":"K. He, H. Fan, Y. Wu, S. Xie, R. Girshick, Momentum contrast for unsupervised visual representation learning, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 9729\u20139738.","DOI":"10.1109\/CVPR42600.2020.00975"},{"issue":"2","key":"10.1016\/j.jbi.2024.104748_b57","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1073\/pnas.98.2.381","article-title":"PubMed central: The GenBank of the published literature","volume":"98","author":"Roberts","year":"2001","journal-title":"Proc. Natl. Acad. Sci."},{"key":"10.1016\/j.jbi.2024.104748_b58","series-title":"Proceedings of the AMIA Symposium","first-page":"1075","article-title":"PEIR digital library: Online resources and authoring system","author":"Jones","year":"2001"},{"key":"10.1016\/j.jbi.2024.104748_b59","doi-asserted-by":"crossref","unstructured":"E.D. Cubuk, B. Zoph, J. Shlens, Q.V. Le, Randaugment: Practical automated data augmentation with a reduced search space, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020, pp. 702\u2013703.","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"10.1016\/j.jbi.2024.104748_b60","series-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"10.1016\/j.jbi.2024.104748_b61","series-title":"UnICLAM: Contrastive representation learning with adversarial masking for unified and interpretable medical vision question answering","author":"Zhan","year":"2022"},{"key":"10.1016\/j.jbi.2024.104748_b62","series-title":"Self-supervised vision-language pretraining for medical visual question answering","author":"Li","year":"2022"},{"issue":"11","key":"10.1016\/j.jbi.2024.104748_b63","doi-asserted-by":"crossref","first-page":"3332","DOI":"10.1109\/TMI.2022.3185008","article-title":"VQAMix: Conditional triplet mixup for medical visual question answering","volume":"41","author":"Gong","year":"2022","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.jbi.2024.104748_b64","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":"10.1016\/j.jbi.2024.104748_b65","series-title":"ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"4838","article-title":"Type-aware medical visual question answering","author":"Zhang","year":"2022"},{"key":"10.1016\/j.jbi.2024.104748_b66","doi-asserted-by":"crossref","unstructured":"H. Gong, G. Chen, S. Liu, Y. Yu, G. Li, Cross-modal self-attention with multi-task pre-training for medical visual question answering, in: Proceedings of the 2021 International Conference on Multimedia Retrieval, 2021, pp. 456\u2013460.","DOI":"10.1145\/3460426.3463584"},{"issue":"4","key":"10.1016\/j.jbi.2024.104748_b67","doi-asserted-by":"crossref","first-page":"1681","DOI":"10.1109\/JBHI.2022.3163751","article-title":"Vision-language transformer for interpretable pathology visual question answering","volume":"27","author":"Naseem","year":"2023","journal-title":"IEEE J. Biomed. Health Inf."}],"container-title":["Journal of Biomedical Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1532046424001667?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1532046424001667?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T04:19:17Z","timestamp":1764562757000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1532046424001667"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":67,"alternative-id":["S1532046424001667"],"URL":"https:\/\/doi.org\/10.1016\/j.jbi.2024.104748","relation":{"has-preprint":[{"id-type":"doi","id":"10.36227\/techrxiv.23810730.v1","asserted-by":"object"}]},"ISSN":["1532-0464"],"issn-type":[{"value":"1532-0464","type":"print"}],"subject":[],"published":{"date-parts":[[2024,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Cross-Modal self-supervised vision language pre-training with multiple objectives for medical visual question answering","name":"articletitle","label":"Article Title"},{"value":"Journal of Biomedical Informatics","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jbi.2024.104748","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2024 Elsevier Inc.","name":"copyright","label":"Copyright"}],"article-number":"104748"}}