{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:18:51Z","timestamp":1761895131258,"version":"build-2065373602"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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\/100014345","name":"Strong","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100014345","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209993","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Cross-modal Semantic Consistency via Key Token Alignment for Image-text Retrieval"],"prefix":"10.1109","author":[{"given":"Huilong","family":"Lin","sequence":"first","affiliation":[{"name":"Guangzhou University,School of Computer Science and Cyber Engineering,Guangzhou,China"}]},{"given":"Yangtao","family":"Wang","sequence":"additional","affiliation":[{"name":"Guangzhou University,School of Computer Science and Cyber Engineering,Guangzhou,China"}]},{"given":"Meie","family":"Fang","sequence":"additional","affiliation":[{"name":"Guangzhou University,School of Computer Science and Cyber Engineering,Guangzhou,China"}]},{"given":"Yanzhao","family":"Xie","sequence":"additional","affiliation":[{"name":"Guangzhou University,School of Computer Science and Cyber Engineering,Guangzhou,China"}]},{"given":"Da","family":"Chen","sequence":"additional","affiliation":[{"name":"Guangzhou University,School of Computer Science and Cyber Engineering,Guangzhou,China"}]},{"given":"Xiaocui","family":"Li","sequence":"additional","affiliation":[{"name":"Hunan University of Technology and Business,Changsha,China"}]},{"given":"Weilong","family":"Peng","sequence":"additional","affiliation":[{"name":"Guangzhou University,School of Computer Science and Cyber Engineering,Guangzhou,China"}]},{"given":"Siyuan","family":"Chen","sequence":"additional","affiliation":[{"name":"Guangzhou University,School of Computer Science and Cyber Engineering,Guangzhou,China"}]},{"given":"Maobin","family":"Tang","sequence":"additional","affiliation":[{"name":"Guangzhou University,School of Computer Science and Cyber Engineering,Guangzhou,China"}]},{"given":"Ping","family":"Li","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University,Hong Kong,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00337"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3679619"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3255839"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01553"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01521"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01847"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"ICLR","author":"Dosovitskiy","key":"ref8"},{"article-title":"Channel vision transformers: An image is worth 1 x 16 x 16 words","volume-title":"ICLR","author":"Bao","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20202"},{"article-title":"EVEREST: efficient masked video autoencoder by removing redundant spatiotemporal tokens","volume-title":"ICML","author":"Hwang","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00585"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02485"},{"article-title":"VSE++: improving visual-semantic embeddings with hard negatives","volume-title":"BMVC","author":"Faghri","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00462"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28001"},{"key":"ref18","first-page":"4171","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019","journal-title":"NAACL-HLT"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16209"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11209993.pdf?arnumber=11209993","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:43:40Z","timestamp":1761889420000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209993\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209993","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}