{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T01:00:52Z","timestamp":1730250052616,"version":"3.28.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"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":[[2024,7,15]]},"DOI":"10.1109\/icme57554.2024.10688059","type":"proceedings-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T17:24:16Z","timestamp":1727717056000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Symmetrical Two-Stream with Selective Sampling for Diversifying Video Captions"],"prefix":"10.1109","author":[{"given":"Jin","family":"Wang","sequence":"first","affiliation":[{"name":"Tianjin University,College of Intelligence and Computing,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yahong","family":"Han","sequence":"additional","affiliation":[{"name":"Tianjin University,College of Intelligence and Computing,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00728"},{"article-title":"Collecting highly parallel data for paraphrase evaluation","volume-title":"ACL","author":"Chen","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref4","article-title":"Auto-captions on gif: A largescale videosentence dataset for vision-language pretraining","author":"Pan","year":"2020","journal-title":"ACM MM"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s42979-021-00487-x"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018167"},{"article-title":"Delving deeper into the decoder for video captioning","volume-title":"ECAI","author":"Chen","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.161"},{"article-title":"Univilm: A unified video and language pre-training model for multimodal understanding and generation","volume-title":"CVPR","author":"Luo","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.340"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2022.103581"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00877"},{"article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"ref19","volume":"abs\/1906.05743","author":"Sun","year":"2019","journal-title":"Contrastive bidirectional transformer for temporal representation learning"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01277"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2021.3063423"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2022.05.021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16788-1_25"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01742"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01816"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01426"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383531"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_43"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3479207"},{"key":"ref30","article-title":"Expectation-maximization contrastive learning for compact video-and-language representations","author":"Jin","year":"2022","journal-title":"NeurlPS"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02193"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01925"}],"event":{"name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2024,7,15]]},"location":"Niagara Falls, ON, Canada","end":{"date-parts":[[2024,7,19]]}},"container-title":["2024 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10685847\/10687354\/10688059.pdf?arnumber=10688059","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T06:39:26Z","timestamp":1727764766000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10688059\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,15]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icme57554.2024.10688059","relation":{},"subject":[],"published":{"date-parts":[[2024,7,15]]}}}