{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T10:37:39Z","timestamp":1768905459936,"version":"3.49.0"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,7,5]],"date-time":"2021-07-05T00:00:00Z","timestamp":1625443200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,5]],"date-time":"2021-07-05T00:00:00Z","timestamp":1625443200000},"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\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,7,5]]},"DOI":"10.1109\/icme51207.2021.9428201","type":"proceedings-article","created":{"date-parts":[[2021,6,9]],"date-time":"2021-06-09T21:14:21Z","timestamp":1623273261000},"page":"1-6","source":"Crossref","is-referenced-by-count":11,"title":["Combine Early and Late Fusion Together: A Hybrid Fusion Framework for Image-Text Matching"],"prefix":"10.1109","author":[{"given":"Yifan","family":"Wang","sequence":"first","affiliation":[{"name":"University of Electronic Science and Technology of China,Center for Future Media & School of Computer Science and Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xing","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China,Center for Future Media & School of Computer Science and Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Yu","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China,Center for Future Media & School of Computer Science and Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruicong","family":"Xu","sequence":"additional","affiliation":[{"name":"Meituan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zuo","family":"Cao","sequence":"additional","affiliation":[{"name":"Meituan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heng","family":"Tao Shen","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China,Center for Future Media & School of Computer Science and Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2967597"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2928180"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2797921"},{"key":"ref13","article-title":"Hadamard prod-uct for low-rank bilinear pooling","author":"kim","year":"2017","journal-title":"ICLRE"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350875"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00048"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107351"},{"key":"ref17","first-page":"12","article-title":"VSE++: improving visual-semantic embeddings with hard negatives","author":"faghri","year":"2018","journal-title":"BMVC"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00645"},{"key":"ref19","article-title":"Microsoft COCO: common objects in con-text","author":"lin","year":"2014","journal-title":"ECCV"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1219"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00586"},{"key":"ref6","article-title":"Exploring visual relationship for image captioning","author":"yao","year":"2018","journal-title":"ECCV"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01072"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093614"},{"key":"ref7","first-page":"212","article-title":"Stacked cross attention for image-text matching","author":"lee","year":"2018","journal-title":"ECCV"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01267"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01093"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"}],"event":{"name":"2021 IEEE International Conference on Multimedia and Expo (ICME)","location":"Shenzhen, China","start":{"date-parts":[[2021,7,5]]},"end":{"date-parts":[[2021,7,9]]}},"container-title":["2021 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9428049\/9428068\/09428201.pdf?arnumber=9428201","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T21:28:00Z","timestamp":1656365280000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9428201\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,5]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icme51207.2021.9428201","relation":{},"subject":[],"published":{"date-parts":[[2021,7,5]]}}}