{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T06:51:07Z","timestamp":1762325467861,"version":"3.37.3"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,28]],"date-time":"2022-05-28T00:00:00Z","timestamp":1653696000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,28]],"date-time":"2022-05-28T00:00:00Z","timestamp":1653696000000},"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":[[2022,5,28]]},"DOI":"10.1109\/iscas48785.2022.9937852","type":"proceedings-article","created":{"date-parts":[[2022,11,11]],"date-time":"2022-11-11T20:38:08Z","timestamp":1668199088000},"page":"3125-3129","source":"Crossref","is-referenced-by-count":2,"title":["Spatio-temporal Super-resolution Network: Enhance Visual Representations for Video Captioning"],"prefix":"10.1109","author":[{"given":"Quanhui","family":"Cao","sequence":"first","affiliation":[{"name":"Tongji University,Department of Computer Science &#x0026; Technology,Shanghai,P. R. China"}]},{"given":"Pengjie","family":"Tang","sequence":"additional","affiliation":[{"name":"Jinggangshan University,College of Electronic and Information Engineering,Ji&#x2019;an,P. R. China"}]},{"given":"Hanli","family":"Wang","sequence":"additional","affiliation":[{"name":"Tongji University,Department of Computer Science &#x0026; Technology,Shanghai,P. R. China"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/CVPR42600.2020.00343"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1145\/3394171.3413667"},{"key":"ref12","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc NeurIPS&#x2019;17"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1007\/978-3-030-58568-6_13"},{"key":"ref14","first-page":"8339","article-title":"Memoryattended recurrent network for video captioning","author":"pei","year":"2019","journal-title":"Proc CVPR&#x2019;19"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/TMM.2019.2924576"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/TPAMI.2019.2920899"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.18653\/v1\/P17-1117"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/TPAMI.2019.2940007"},{"key":"ref19","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","author":"chen","year":"2011","journal-title":"Proc ACL-HLT&#x2019;11"},{"key":"ref28","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR&#x2019;15"},{"key":"ref4","first-page":"847","article-title":"TVT: Two-view transformer network for video captioning","author":"chen","year":"2018","journal-title":"Proc ACML&#x2019;18"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1109\/CVPR42600.2020.00377"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/CVPR.2016.117"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/CVPR42600.2020.01088"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1609\/aaai.v35i3.16353"},{"key":"ref8","first-page":"3119","article-title":"Non-autoregressive coarse-tofine video captioning","author":"yang","year":"2021","journal-title":"Proc AAAI&#x2019;21"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/CVPR42600.2020.01329"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/ICCV.2015.512"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/ICCV.2019.00273"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/ICCV.2015.515"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/CVPR.2016.571"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref21","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proc ACL&#x2019;02"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref23","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Proc ACL&#x2019;04 Workshop"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1109\/CVPR.2017.502"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1109\/CVPR.2016.90"}],"event":{"name":"2022 IEEE International Symposium on Circuits and Systems (ISCAS)","start":{"date-parts":[[2022,5,27]]},"location":"Austin, TX, USA","end":{"date-parts":[[2022,6,1]]}},"container-title":["2022 IEEE International Symposium on Circuits and Systems (ISCAS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9937201\/9937203\/09937852.pdf?arnumber=9937852","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,28]],"date-time":"2022-11-28T20:23:28Z","timestamp":1669667008000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9937852\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,28]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/iscas48785.2022.9937852","relation":{},"subject":[],"published":{"date-parts":[[2022,5,28]]}}}