{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:20:21Z","timestamp":1780636821431,"version":"3.54.1"},"reference-count":14,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"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\/501100003819","name":"Natural Science Foundation of Hubei Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003819","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,7,15]]},"DOI":"10.1109\/icme57554.2024.10688369","type":"proceedings-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T17:24:16Z","timestamp":1727717056000},"page":"1-6","source":"Crossref","is-referenced-by-count":9,"title":["Cross-Modal Adapter: Parameter-Efficient Transfer Learning Approach for Vision-Language Models"],"prefix":"10.1109","author":[{"given":"Juncheng","family":"Yang","sequence":"first","affiliation":[{"name":"Wuhan University,School of Computer Science,Wuhan,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zuchao","family":"Li","sequence":"additional","affiliation":[{"name":"Wuhan University,School of Computer Science,Wuhan,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuai","family":"Xie","sequence":"additional","affiliation":[{"name":"JD Explore Academy,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weiping","family":"Zhu","sequence":"additional","affiliation":[{"name":"Wuhan University,School of Computer Science,Wuhan,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Yu","sequence":"additional","affiliation":[{"name":"Wuhan University,School of Computer Science,Wuhan,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shijun","family":"Li","sequence":"additional","affiliation":[{"name":"Wuhan University,School of Computer Science,Wuhan,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford"},{"key":"ref2","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","author":"Jia"},{"key":"ref3","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"ICML","author":"Li"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"ref6","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref8","first-page":"2790","article-title":"Parameter-efficient transfer learning for nlp","volume-title":"ICML","author":"Houlsby"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref10","article-title":"Graphadapter: Tuning vision-language models with dual knowledge graph","author":"Li","year":"2023","journal-title":"NeurIPS"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01049"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref14","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"ICLR","author":"Dosovitskiy"}],"event":{"name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","location":"Niagara Falls, ON, Canada","start":{"date-parts":[[2024,7,15]]},"end":{"date-parts":[[2024,7,19]]}},"container-title":["2024 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10685847\/10687354\/10688369.pdf?arnumber=10688369","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T06:43:43Z","timestamp":1727765023000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10688369\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,15]]},"references-count":14,"URL":"https:\/\/doi.org\/10.1109\/icme57554.2024.10688369","relation":{},"subject":[],"published":{"date-parts":[[2024,7,15]]}}}