{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:35:44Z","timestamp":1740101744595,"version":"3.37.3"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100014219","name":"National Science Fund for Distinguished Young Scholars","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100014219","id-type":"DOI","asserted-by":"publisher"}]},{"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10097061","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["Trust Your Partner\u2019s Friends: Hierarchical Cross-Modal Contrastive Pre-Training for Video-Text Retrieval"],"prefix":"10.1109","author":[{"given":"Yuhan","family":"Xiang","sequence":"first","affiliation":[{"name":"School of Infomatics, Xiamen University,Media Analytics and Computing Lab,Department of Artificial Intelligence,P.R. China,361005"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaijian","family":"Liu","sequence":"additional","affiliation":[{"name":"SenseTime Group Limited"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shixiang","family":"Tang","sequence":"additional","affiliation":[{"name":"The University of Sydney"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Bai","sequence":"additional","affiliation":[{"name":"The University of Sydney"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Zhu","sequence":"additional","affiliation":[{"name":"SenseTime Group Limited"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Zhao","sequence":"additional","affiliation":[{"name":"SenseTime Group Limited"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xianming","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Infomatics, Xiamen University,Media Analytics and Computing Lab,Department of Artificial Intelligence,P.R. China,361005"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.544"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_29"},{"article-title":"Unifying visual-semantic embeddings with multimodal neural language models","year":"2014","author":"Kiros","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.20"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00365"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/492"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00294"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01939"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00791"},{"article-title":"Support-set bottlenecks for video-text representation learning","year":"2020","author":"Patrick","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16822"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10097061.pdf?arnumber=10097061","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T22:55:16Z","timestamp":1709247316000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10097061\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10097061","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}