{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,20]],"date-time":"2025-07-20T03:47:57Z","timestamp":1752983277390,"version":"3.37.3"},"reference-count":48,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,12,6]],"date-time":"2022-12-06T00:00:00Z","timestamp":1670284800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,6]],"date-time":"2022-12-06T00:00:00Z","timestamp":1670284800000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003347","name":"Fudan University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003347","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,12,6]]},"DOI":"10.1109\/bibm55620.2022.9995473","type":"proceedings-article","created":{"date-parts":[[2023,1,2]],"date-time":"2023-01-02T19:09:24Z","timestamp":1672686564000},"page":"567-574","source":"Crossref","is-referenced-by-count":13,"title":["MHKD-MVQA: Multimodal Hierarchical Knowledge Distillation for Medical Visual Question Answering"],"prefix":"10.1109","author":[{"given":"Jianfeng","family":"Wang","sequence":"first","affiliation":[{"name":"Fudan University,Academy for Engineering and Technology,Shanghai,P.R. China"}]},{"given":"Shuokang","family":"Huang","sequence":"additional","affiliation":[{"name":"Imperial College London,London,United Kingdom,SW7 2AZ"}]},{"given":"Huifang","family":"Du","sequence":"additional","affiliation":[{"name":"Tongji University,College of Design and Innovation,Shanghai,P.R. China"}]},{"given":"Yu","family":"Qin","sequence":"additional","affiliation":[{"name":"Imperial College London,London,United Kingdom,SW7 2AZ"}]},{"given":"Haofen","family":"Wang","sequence":"additional","affiliation":[{"name":"Tongji University,College of Design and Innovation,Shanghai,P.R. China"}]},{"given":"Wenqiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Fudan University,Academy for Engineering and Technology,Shanghai,P.R. China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2023.102611"},{"key":"ref3","article-title":"Vqa-med: Overview of the medical visual question answering task at imageclef 2019","volume":"2","author":"Abacha","year":"2019","journal-title":"CLEF (Working Notes)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2018.251"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32251-9_57"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87240-3_7"},{"key":"ref7","article-title":"Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","author":"Wang","year":"2022","journal-title":"arXiv preprint arXiv:2202.03052"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2980024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3460426.3463584"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87196-3_20"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI48211.2021.9434063"},{"key":"ref12","article-title":"Revisiting few-sample bert fine-tuning","author":"Zhang","year":"2020","journal-title":"arXiv preprint arXiv:2006.05987"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21375"},{"key":"ref14","first-page":"1607","article-title":"Born again neural networks","volume-title":"International Conference on Machine Learning","author":"Furlanello"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.03.005"},{"key":"ref17","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume":"32","author":"Lu","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01392-1"},{"key":"ref21","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref22","article-title":"Clip-td: Clip targeted distillation for vision-language tasks","author":"Wang","year":"2022","journal-title":"arXiv preprint arXiv:2201.05729"},{"key":"ref23","article-title":"Does clip benefit visual question answering in the medical domain as much as it does in the general domain?","volume":"abs\/2112.13906","author":"Eslami","year":"2021","journal-title":"ArXiv"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747087"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00363"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683438"},{"key":"ref28","article-title":"Fitnets: Hints for thin deep nets","author":"Romero","year":"2014","journal-title":"arXiv preprint arXiv:1412.6550"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i15.17610"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16865"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00409"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00511"},{"key":"ref33","first-page":"10096","article-title":"Efficientnetv2: Smaller models and faster training","volume-title":"International Conference on Machine Learning","author":"Tan"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref35","article-title":"Meal v2: Boosting vanilla resnet-50 to 80%+ top-1 accuracy on imagenet without tricks","author":"Shen","year":"2020","journal-title":"arXiv preprint arXiv:2009.08453"},{"key":"ref36","first-page":"200","article-title":"Multimodal few-shot learning with frozen language models","volume":"34","author":"Tsimpoukelli","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01364-6_20"},{"key":"ref38","first-page":"18661","article-title":"Supervised contrastive learning","volume":"33","author":"Khosla","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref39","article-title":"How transferable are features in deep neural networks?","volume":"27","author":"Yosinski","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref40","article-title":"Distilling knowledge via intermediate classifiers","author":"Asadian","year":"2021","journal-title":"arXiv preprint arXiv:2103.00497"},{"key":"ref41","article-title":"Zhejiang university at imageclef 2019 visual question answering in the medical domain","author":"Yan","year":"2019","journal-title":"CLEF"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1044"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413761"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref45","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv preprint arXiv:1409.1556"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19\u20131423"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"}],"event":{"name":"2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","start":{"date-parts":[[2022,12,6]]},"location":"Las Vegas, NV, USA","end":{"date-parts":[[2022,12,8]]}},"container-title":["2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9994793\/9994847\/09995473.pdf?arnumber=9995473","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T12:39:26Z","timestamp":1706791166000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9995473\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,6]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/bibm55620.2022.9995473","relation":{},"subject":[],"published":{"date-parts":[[2022,12,6]]}}}