{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:50:16Z","timestamp":1765309816187,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["No.2023YFC3502902, 2021YFF1201100"],"award-info":[{"award-number":["No.2023YFC3502902, 2021YFF1201100"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206197, 62436006"],"award-info":[{"award-number":["62206197, 62436006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Sanya Science and Technology Special Fund","award":["No. 2024KFJX04"],"award-info":[{"award-number":["No. 2024KFJX04"]}]},{"name":"Beijing Natural Science Foundation","award":["No. L257018, No. L246024"],"award-info":[{"award-number":["No. L257018, No. L246024"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755273","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:26:38Z","timestamp":1761377198000},"page":"3991-4000","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Medical Vision-Language Pre-training with Multimodal Variational Masked Autoencoder for Robust Medical VQA"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3100-5886","authenticated-orcid":false,"given":"Dexuan","family":"Xu","sequence":"first","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1579-5857","authenticated-orcid":false,"given":"Yanyuan","family":"Chen","sequence":"additional","affiliation":[{"name":"Augusta University, Augusta, GA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1138-1828","authenticated-orcid":false,"given":"Yu","family":"Huang","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4304-3944","authenticated-orcid":false,"given":"Shihao","family":"E","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5618-3366","authenticated-orcid":false,"given":"Yiwei","family":"Lou","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9517-7332","authenticated-orcid":false,"given":"Yongzhi","family":"Cao","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7680-9504","authenticated-orcid":false,"given":"Hanpin","family":"Wang","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1004-0140","authenticated-orcid":false,"given":"Meikang","family":"Qiu","sequence":"additional","affiliation":[{"name":"Augusta University, Augusta, GA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01442"},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of CLEF (Conference and Labs of the Evaluation Forum) 2019 Working Notes.","author":"Abacha Asma Ben","year":"2019","unstructured":"Asma Ben Abacha, Sadid A Hasan, Vivek V Datla, Dina Demner-Fushman, and Henning M\u00fcller. 2019. Vqa-med: Overview of the medical visual question answering task at imageclef 2019. In Proceedings of CLEF (Conference and Labs of the Evaluation Forum) 2019 Working Notes. 9-12 September 2019."},{"key":"e_1_3_2_1_3_1","volume-title":"International conference on learning representations.","author":"Buckman Jacob","year":"2018","unstructured":"Jacob Buckman, Aurko Roy, Colin Raffel, and Ian Goodfellow. 2018. Thermometer encoding: One hot way to resist adversarial examples. In International conference on learning representations."},{"key":"e_1_3_2_1_4_1","first-page":"1422","article-title":"METC-MVAE: Mobile Encrypted Traffic Classification With Masked Variational Autoencoders. In 2022 IEEE 24th Int Conf on High Performance Computing & Communications; 8th Int Conf on Data Science & Systems; 20th Int Conf on Smart City; 8th Int Conf on Dependability in Sensor, Cloud & Big Data Systems & Application (HPCC\/DSS\/SmartCity\/DependSys)","author":"Cai Wei","year":"2022","unstructured":"Wei Cai, Zhen Li, Peipei Fu, Chengshang Hou, Gang Xiong, and Gaopeng Gou. 2022. METC-MVAE: Mobile Encrypted Traffic Classification With Masked Variational Autoencoders. In 2022 IEEE 24th Int Conf on High Performance Computing & Communications; 8th Int Conf on Data Science & Systems; 20th Int Conf on Smart City; 8th Int Conf on Dependability in Sensor, Cloud & Big Data Systems & Application (HPCC\/DSS\/SmartCity\/DependSys). IEEE, 1422-1429.","journal-title":"IEEE"},{"key":"e_1_3_2_1_5_1","first-page":"39","article-title":"Towards evaluating the robustness of neural networks. In 2017 ieee symposium on security and privacy (sp)","author":"Carlini Nicholas","year":"2017","unstructured":"Nicholas Carlini and David Wagner. 2017. Towards evaluating the robustness of neural networks. In 2017 ieee symposium on security and privacy (sp). Ieee, 39-57.","journal-title":"Ieee"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403225"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02139"},{"key":"e_1_3_2_1_8_1","volume-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, 679-689","author":"Chen Zhihong","year":"2022","unstructured":"Zhihong Chen, Yuhao Du, Jinpeng Hu, Yang Liu, Guanbin Li, Xiang Wan, and Tsung-Hui Chang. 2022. Multi-modal masked autoencoders for medical visionand- language pre-training. In International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, 679-689."},{"key":"e_1_3_2_1_9_1","volume-title":"International conference on machine learning. PMLR, 2206-2216","author":"Croce Francesco","year":"2020","unstructured":"Francesco Croce and Matthias Hein. 2020. Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks. In International conference on machine learning. PMLR, 2206-2216."},{"key":"e_1_3_2_1_10_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_11_1","volume-title":"An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929","author":"Dosovitskiy Alexey","year":"2020","unstructured":"Alexey Dosovitskiy. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_12_1","volume-title":"Explaining and Harnessing Adversarial Examples. In 3rd International Conference on Learning Representations, ICLR","author":"Goodfellow Ian J.","year":"2015","unstructured":"Ian J. Goodfellow, Jonathon Shlens, and Christian Szegedy. 2015. Explaining and Harnessing Adversarial Examples. In 3rd International Conference on Learning Representations, ICLR 2015."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.633"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.468"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI48211.2021.9434063"},{"key":"e_1_3_2_1_18_1","volume-title":"Auto-Encoding Variational Bayes. In 2nd International Conference on Learning Representations, ICLR","author":"Diederik","year":"2014","unstructured":"Diederik P. Kingma and Max Welling. 2014. Auto-Encoding Variational Bayes. In 2nd International Conference on Learning Representations, ICLR 2014."},{"volume-title":"Artificial intelligence safety and security","author":"Kurakin Alexey","key":"e_1_3_2_1_19_1","unstructured":"Alexey Kurakin, Ian J Goodfellow, and Samy Bengio. 2018. Adversarial examples in the physical world. In Artificial intelligence safety and security. Chapman and Hall\/CRC, 99-112."},{"key":"e_1_3_2_1_20_1","volume-title":"Asma Ben Abacha, and Dina Demner-Fushman","author":"Lau Jason J","year":"2018","unstructured":"Jason J Lau, Soumya Gayen, Asma Ben Abacha, and Dina Demner-Fushman. 2018. A dataset of clinically generated visual questions and answers about radiology images. Scientific data 5, 1 (2018), 1-10."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2023.102611"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2023.3294980"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI48211.2021.9434010"},{"key":"e_1_3_2_1_24_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 364","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 364 (2019)."},{"key":"e_1_3_2_1_25_1","volume-title":"6th International Conference on Learning Representations, ICLR","author":"Madry Aleksander","year":"2018","unstructured":"Aleksander Madry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, and Adrian Vladu. 2018. Towards Deep Learning Models Resistant to Adversarial Attacks. In 6th International Conference on Learning Representations, ICLR 2018."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2016.41"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00928-1_56"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Obioma Pelka Sven Koitka Johannes R\u00fcckert Felix Nensa and Christoph M Friedrich. 2018. Radiology Objects in COntext (ROCO): a multimodal image dataset. In Intravascular Imaging and Computer Assisted Stenting and Large-Scale Annotation of Biomedical Data and Expert Label Synthesis: 7th Joint International Workshop CVII-STENT 2018 and Third International Workshop LABELS 2018 Held in Conjunction with MICCAI 2018 Granada Spain September 16 2018 Proceedings 3. Springer 180-189.","DOI":"10.1007\/978-3-030-01364-6_20"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3048038"},{"key":"e_1_3_2_1_30_1","volume-title":"International conference on machine learning. PMLR, 8748-8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748-8763."},{"key":"e_1_3_2_1_31_1","volume-title":"Sachin Mehta, Ben Bogin, Madeleine van Zuylen, Sravanthi Parasa, Sameer Singh, Matt Gardner, and Hannaneh Hajishirzi.","author":"Subramanian Sanjay","year":"2020","unstructured":"Sanjay Subramanian, Lucy Lu Wang, Sachin Mehta, Ben Bogin, Madeleine van Zuylen, Sravanthi Parasa, Sameer Singh, Matt Gardner, and Hannaneh Hajishirzi. 2020. MedICaT: A Dataset of Medical Images, Captions, and Textual References. In Findings of EMNLP."},{"key":"e_1_3_2_1_32_1","volume-title":"International conference on machine learning. PMLR, 5025-5034","author":"Uesato Jonathan","year":"2018","unstructured":"Jonathan Uesato, Brendan O'donoghue, Pushmeet Kohli, and Aaron Oord. 2018. Adversarial risk and the dangers of evaluating against weak attacks. In International conference on machine learning. PMLR, 5025-5034."},{"key":"e_1_3_2_1_33_1","volume-title":"International conference on learning representations.","author":"Wang Yisen","year":"2019","unstructured":"Yisen Wang, Difan Zou, Jinfeng Yi, James Bailey, Xingjun Ma, and Quanquan Gu. 2019. Improving adversarial robustness requires revisiting misclassified examples. In International conference on learning representations."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.124"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.296"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.101977"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3156268"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612262"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3576915.3616617"},{"key":"e_1_3_2_1_41_1","first-page":"274","volume-title":"Algorithms and Architectures for Parallel Processing: 20th International Conference, ICA3PP 2020, New York City, NY, USA, October 2-4, 2020, Proceedings, Part II 20","author":"Zeng Yi","year":"2020","unstructured":"Yi Zeng, Han Qiu, Gerard Memmi, and Meikang Qiu. 2020. A data augmentationbased defense method against adversarial attacks in neural networks. In Algorithms and Architectures for Parallel Processing: 20th International Conference, ICA3PP 2020, New York City, NY, USA, October 2-4, 2020, Proceedings, Part II 20. Springer, 274-289."},{"key":"e_1_3_2_1_42_1","unstructured":"Sheng Zhang Yanbo Xu Naoto Usuyama Hanwen Xu Jaspreet Bagga Robert Tinn Sam Preston Rajesh Rao Mu Wei Naveen Valluri et al. 2023. Biomedclip: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs. arXiv preprint arXiv:2303.00915 (2023)."},{"key":"e_1_3_2_1_43_1","volume-title":"Machine Learning for Healthcare Conference. PMLR, 2-25","author":"Zhang Yuhao","year":"2022","unstructured":"Yuhao Zhang, Hang Jiang, Yasuhide Miura, Christopher D Manning, and Curtis P Langlotz. 2022. Contrastive learning of medical visual representations from paired images and text. In Machine Learning for Healthcare Conference. PMLR, 2-25."},{"key":"e_1_3_2_1_44_1","volume-title":"2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). IEEE, 4048-4053","author":"Zheng Fuchen","year":"2024","unstructured":"Fuchen Zheng, Xuhang Chen, Weihuang Liu, Haolun Li, Yingtie Lei, Jiahui He, Chi-Man Pun, and Shoujun Zhou. 2024. Smaformer: Synergistic multiattention transformer for medical image segmentation. In 2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). IEEE, 4048-4053."},{"key":"e_1_3_2_1_45_1","volume-title":"Advancing Radiograph Representation Learning with Masked Record Modeling. In The Eleventh International Conference on Learning Representations.","author":"Zhou Hong-Yu","year":"2023","unstructured":"Hong-Yu Zhou, Chenyu Lian, Liansheng Wang, and Yizhou Yu. 2023. Advancing Radiograph Representation Learning with Masked Record Modeling. In The Eleventh International Conference on Learning Representations."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755273","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:45:24Z","timestamp":1765309524000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755273"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":45,"alternative-id":["10.1145\/3746027.3755273","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755273","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}