{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:20:18Z","timestamp":1776889218883,"version":"3.51.2"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096424","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":24,"title":["I-Tuning: Tuning Frozen Language Models with Image for Lightweight Image Captioning"],"prefix":"10.1109","author":[{"given":"Ziyang","family":"Luo","sequence":"first","affiliation":[{"name":"Hong Kong Baptist University,Department of Computer Science,Hong Kong SAR,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhipeng","family":"Hu","sequence":"additional","affiliation":[{"name":"Zhejiang University,College of Computer Science and Technology,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yadong","family":"Xi","sequence":"additional","affiliation":[{"name":"NetEase Inc.,Fuxi AI Lab,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rongsheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"NetEase Inc.,Fuxi AI Lab,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Ma","sequence":"additional","affiliation":[{"name":"Hong Kong Baptist University,Department of Computer Science,Hong Kong SAR,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"SimVLM: Simple visual language model pretraining with weak supervision","author":"wang","year":"2022","journal-title":"ICLRE"},{"key":"ref24","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2019","journal-title":"ICLRE"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref23","author":"anderson","year":"2016","journal-title":"Spice Semantic propositional image caption evaluation"},{"key":"ref15","author":"liu","year":"2021","journal-title":"Gpt understands too"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00904"},{"key":"ref22","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","author":"banerjee","year":"2005","journal-title":"Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref21","article-title":"Bleu: a method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"ACL"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7005"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref17","article-title":"Unifying vision-and-language tasks via text generation","author":"cho","year":"2021","journal-title":"ICML"},{"key":"ref16","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","article-title":"Visual genome: Connecting language and vision using crowdsourced dense image annotations","volume":"123","author":"krishna","year":"2016","journal-title":"IJCV"},{"key":"ref8","author":"radford","year":"2019","journal-title":"Language Models are Unsupervised Multitask Learners"},{"key":"ref7","article-title":"Learning transferable visual models from natural language supervision","author":"radford","year":"2021","journal-title":"ICML"},{"key":"ref9","author":"lin","year":"2015","journal-title":"Microsoft coco Common objects in context"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_30"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-88480-2_63"},{"key":"ref6","author":"mokady","year":"2021","journal-title":"Clip-cap Clip prefix for image captioning"},{"key":"ref5","article-title":"Parameter-efficient transfer learning for NLP","author":"houlsby","year":"2019","journal-title":"ICML"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096424.pdf?arnumber=10096424","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T18:55:59Z","timestamp":1699901759000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096424\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096424","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}