{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T02:21:23Z","timestamp":1725762083470},"reference-count":25,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,7,5]]},"DOI":"10.1109\/icme51207.2021.9428380","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":7,"title":["Auxiliary Bi-Level Graph Representation for Cross-Modal Image-Text Retrieval"],"prefix":"10.1109","author":[{"given":"Xian","family":"Zhong","sequence":"first","affiliation":[{"name":"Wuhan University of Technology,School of Computer Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengwei","family":"Yang","sequence":"additional","affiliation":[{"name":"Wuhan University of Technology,School of Computer Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mang","family":"Ye","sequence":"additional","affiliation":[{"name":"Wuhan University,School of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenxin","family":"Huang","sequence":"additional","affiliation":[{"name":"Hubei University,School of Computer Science and Information Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingling","family":"Yuan","sequence":"additional","affiliation":[{"name":"Wuhan University of Technology,School of Computer Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chia-Wen","family":"Lin","sequence":"additional","affiliation":[{"name":"National Tsing Hua University,Department of Electrical Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref11","article-title":"Microsoft COCO: common objects in context","author":"lin","year":"2014","journal-title":"ECCV"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICME46284.2020.9102913"},{"key":"ref13","article-title":"Exploring visual relationship for image captioning","author":"yao","year":"2018","journal-title":"ECCV"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00611"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref16","article-title":"SPICE: semantic propositional image caption evaluation","author":"anderson","year":"2016","journal-title":"ECCV"},{"key":"ref17","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"NACC"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref19","article-title":"VSE++: Improving visual-semantic embeddings with hard negatives","author":"faghri","year":"2018","journal-title":"BMVC"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00359"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2017.8019356"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6455"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3372278.3390709"},{"key":"ref8","article-title":"Augmentation invariant and instance spreading feature for softmax embedding","author":"ye","year":"2020","journal-title":"TPAMI"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2017.8019549"},{"key":"ref1","article-title":"Deep learning for person re-identification: A survey and outlook","author":"ye","year":"2021","journal-title":"TPAMI"},{"key":"ref9","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"2017","journal-title":"ICLRE"},{"key":"ref20","article-title":"Stacked cross attention for image-text matching","author":"lee","year":"2018","journal-title":"ECCV"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018489"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350869"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054758"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01302"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093614"}],"event":{"name":"2021 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2021,7,5]]},"location":"Shenzhen, China","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\/09428380.pdf?arnumber=9428380","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T21:27:21Z","timestamp":1656365241000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9428380\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,5]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icme51207.2021.9428380","relation":{},"subject":[],"published":{"date-parts":[[2021,7,5]]}}}