{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T21:15:31Z","timestamp":1773695731175,"version":"3.50.1"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446878","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"1731-1735","source":"Crossref","is-referenced-by-count":12,"title":["Sam-Guided Enhanced Fine-Grained Encoding with Mixed Semantic Learning for Medical Image Captioning"],"prefix":"10.1109","author":[{"given":"Zhenyu","family":"Zhang","sequence":"first","affiliation":[{"name":"Zhejiang University-University of Illinois Urbana-Champaign Institute, Zhejiang University,China"}]},{"given":"Benlu","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang University-University of Illinois Urbana-Champaign Institute, Zhejiang University,China"}]},{"given":"Weijie","family":"Liang","sequence":"additional","affiliation":[{"name":"Zhejiang University-University of Illinois Urbana-Champaign Institute, Zhejiang University,China"}]},{"given":"Yizhi","family":"Li","sequence":"additional","affiliation":[{"name":"Zhejiang University-University of Illinois Urbana-Champaign Institute, Zhejiang University,China"}]},{"given":"Xuechen","family":"Guo","sequence":"additional","affiliation":[{"name":"Zhejiang University-University of Illinois Urbana-Champaign Institute, Zhejiang University,China"}]},{"given":"Guanhong","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang University-University of Illinois Urbana-Champaign Institute, Zhejiang University,China"}]},{"given":"Shiyan","family":"Li","sequence":"additional","affiliation":[{"name":"Sir Run Run Shaw Hospital, Zhejiang University School of Medicine,China"}]},{"given":"Gaoang","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang University-University of Illinois Urbana-Champaign Institute, Zhejiang University,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"ref2","first-page":"2","article-title":"Contrastive learning of medical visual representations from paired images and text","volume-title":"Machine Learning for Healthcare Conference","author":"Zhang"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01954"},{"key":"ref4","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","author":"Li","year":"2021","journal-title":"NeurIPS"},{"key":"ref5","article-title":"Learning transferable visual models from natural language supervision","author":"Alec","year":"2021","journal-title":"ICML"},{"key":"ref6","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","author":"Li","year":"2022","journal-title":"ICML"},{"key":"ref7","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"ICML"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.11834\/jig.211021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.191"},{"key":"ref12","first-page":"180","article-title":"Radiology objects in context (roco): a multimodal image dataset","volume-title":"Proceedings of the 7th Joint International Workshop, CVII-STENT 2018 and Third International Workshop, LABELS 2018, held in conjunction with MICCAI 2018","author":"Obioma"},{"key":"ref13","article-title":"Opt: Open pre-trained transformer language models","author":"Zhang","year":"2022"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref15","first-page":"311","article-title":"Bleu: a method for automatic evaluation of machine translation","volume-title":"Proceedings of the 40th annual meeting of the Association for Computational Linguistics","author":"Papineni"},{"key":"ref16","first-page":"65","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments","volume-title":"Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization","author":"Banerjee"},{"key":"ref17","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text summarization branches out"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref19","article-title":"Bertscore: Evaluating text generation with bert","volume-title":"8th International Conference on Learning Representations","author":"Zhang"},{"key":"ref20","first-page":"27263","article-title":"Bartscore: Evaluating generated text as text generation","author":"Weizhe","year":"2021","journal-title":"NeurIPS"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.704"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10446878.pdf?arnumber=10446878","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:46:02Z","timestamp":1722573962000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446878\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446878","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}