{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:01:31Z","timestamp":1776888091668,"version":"3.51.2"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,8]],"date-time":"2023-10-08T00:00:00Z","timestamp":1696723200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,8]],"date-time":"2023-10-08T00:00:00Z","timestamp":1696723200000},"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"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,8]]},"DOI":"10.1109\/icip49359.2023.10222130","type":"proceedings-article","created":{"date-parts":[[2023,9,11]],"date-time":"2023-09-11T17:58:31Z","timestamp":1694455111000},"page":"51-55","source":"Crossref","is-referenced-by-count":6,"title":["Local-Global Contrast for Learning Voice-Face Representations"],"prefix":"10.1109","author":[{"given":"Guangyu","family":"Chen","sequence":"first","affiliation":[{"name":"Renmin University of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Deyuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shenyang Aerospace University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Liu","sequence":"additional","affiliation":[{"name":"Renmin University of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyong","family":"Du","sequence":"additional","affiliation":[{"name":"Renmin University of China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_5"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240601"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20873-8_18"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA47822.2019.8945863"},{"key":"ref6","article-title":"Disjoint mapping network for cross-modal matching of voices and faces","author":"Wen","year":"2018"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3050089"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3512527.3531364"},{"key":"ref9","article-title":"Large-margin softmax loss for convolutional neural networks","author":"Liu","year":"2016"},{"key":"ref10","article-title":"Voice-face cross-modal matching and retrieval: A benchmark","author":"Xiong","year":"2019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401302"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747704"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01608"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00879"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413710"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3071243"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00184"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/526"},{"key":"ref19","article-title":"Improved deep metric learning with multi-class n-pair loss objective","year":"2016"},{"key":"ref20","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref21","article-title":"Supervised contrastive learning","volume-title":"Proc. of NeurIPS","author":"Khosla"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01229"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00148"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_31"},{"key":"ref25","article-title":"Understanding contrastive representation learning through alignment and uniformity on the hypersphere","volume-title":"Proc. of ICML","author":"Wang"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00252"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"}],"event":{"name":"2023 IEEE International Conference on Image Processing (ICIP)","location":"Kuala Lumpur, Malaysia","start":{"date-parts":[[2023,10,8]]},"end":{"date-parts":[[2023,10,11]]}},"container-title":["2023 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10221937\/10221892\/10222130.pdf?arnumber=10222130","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T20:17:16Z","timestamp":1709324236000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10222130\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,8]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icip49359.2023.10222130","relation":{},"subject":[],"published":{"date-parts":[[2023,10,8]]}}}