{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T12:46:53Z","timestamp":1770468413151,"version":"3.49.0"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LGF22F020014"],"award-info":[{"award-number":["LGF22F020014"]}]},{"name":"National Key Research and Development Program of China","award":["2020YFB1707700"],"award-info":[{"award-number":["2020YFB1707700"]}]},{"name":"National Key Research and Development Program of China","award":["2022YFB3304100"],"award-info":[{"award-number":["2022YFB3304100"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2024.3368922","type":"journal-article","created":{"date-parts":[[2024,2,22]],"date-time":"2024-02-22T19:45:39Z","timestamp":1708631139000},"page":"7462-7474","source":"Crossref","is-referenced-by-count":6,"title":["Multi-Level Objective Alignment Transformer for Fine-Grained Oral Panoramic X-Ray Report Generation"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4545-7197","authenticated-orcid":false,"given":"Nan","family":"Gao","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology College of Software, Zhejiang University of Technology, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7938-6724","authenticated-orcid":false,"given":"Renyuan","family":"Yao","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology College of Software, Zhejiang University of Technology, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2077-9608","authenticated-orcid":false,"given":"Ronghua","family":"Liang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology College of Software, Zhejiang University of Technology, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6122-0574","authenticated-orcid":false,"given":"Peng","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology College of Software, Zhejiang University of Technology, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3501-7476","authenticated-orcid":false,"given":"Tianshuang","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Stomatology, Hangzhou Stomatology Hospital, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8302-1338","authenticated-orcid":false,"given":"Yuanjie","family":"Dang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology College of Software, Zhejiang University of Technology, Hangzhou, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(18)32279-7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-021-06684-2"},{"issue":"31","key":"ref3","first-page":"152","article-title":"Study on quality evaluation index system of running medical records for public hospitals in Beijing","volume":"14","author":"Du","year":"2017","journal-title":"China Med. Herald"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6989"},{"key":"ref5","first-page":"1530","article-title":"Hybrid retrieval-generation reinforced agent for medical image report generation","volume-title":"Proc. NeurIPS","author":"Li","year":"2018"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00943"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1657"},{"key":"ref8","first-page":"11137","article-title":"Image captioning: Transforming objects into words","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Herdade","year":"2019"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1240"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00928-1_52"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32226-7_80"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.imu.2021.100557"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87234-2_28"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01354"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.387"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16328"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_33"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01897"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref26","first-page":"11137","article-title":"Image captioning: Transforming objects into words","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Herdade","year":"2019"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01034"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2021.3072479"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3169061"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2021.3093725"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.118474"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01763"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref35","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","volume":"162","author":"Li","year":"2022"},{"key":"ref36","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li","year":"2021"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.251"},{"key":"ref38","first-page":"13","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu","year":"2019"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref40","first-page":"32897","article-title":"VLMo: Unified vision-language pre-training with mixture-of-modality-experts","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Wang","year":"2022"},{"key":"ref41","first-page":"25994","article-title":"Multi-grained vision language pre-training: Aligning texts with visual concepts","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"162","author":"Zeng","year":"2022"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26263"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00312"},{"key":"ref45","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","volume-title":"Proc. 40th Annu. Meeting Assoc. Comput. Linguistics","author":"Papineni","year":"2002"},{"key":"ref46","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Meas. Mach. Transl. Summarization","author":"Banerjee","year":"2005"},{"key":"ref47","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Proc. Text Summarization Branches Out","author":"Lin","year":"2004"},{"key":"ref48","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-019-0322-0"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01750"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref53","first-page":"1","article-title":"BERTScore: Evaluating text generation with BERT","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2020"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87199-4_7"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102510"},{"key":"ref56","first-page":"113","article-title":"AutoAugment: Learning augmentation policies from data","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Cubuk","year":"2018"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10443573.pdf?arnumber=10443573","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:54:35Z","timestamp":1725904475000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10443573\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3368922","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}