{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T03:48:15Z","timestamp":1761709695397,"version":"3.37.3"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2020,11,1]],"date-time":"2020-11-01T00:00:00Z","timestamp":1604188800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,11,1]],"date-time":"2020-11-01T00:00:00Z","timestamp":1604188800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,11,1]],"date-time":"2020-11-01T00:00:00Z","timestamp":1604188800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["61876130","61932009","U1509206"],"award-info":[{"award-number":["61876130","61932009","U1509206"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2020,11]]},"DOI":"10.1109\/tcsvt.2019.2956593","type":"journal-article","created":{"date-parts":[[2019,11,28]],"date-time":"2019-11-28T22:33:25Z","timestamp":1574980405000},"page":"4299-4308","source":"Crossref","is-referenced-by-count":34,"title":["Convolutional Reconstruction-to-Sequence for Video Captioning"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2024-2678","authenticated-orcid":false,"given":"Aming","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2768-1398","authenticated-orcid":false,"given":"Yahong","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0512-880X","authenticated-orcid":false,"given":"Yi","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8690-987X","authenticated-orcid":false,"given":"Qinghua","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2139-8807","authenticated-orcid":false,"given":"Fei","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proc ACL"},{"key":"ref38","first-page":"612","article-title":"Augmenting supervised neural networks with unsupervised objectives for large-scale image classification","author":"zhang","year":"2016","journal-title":"Proc ICML"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.201"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00013"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.273"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.334"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"ref36","first-page":"7008","article-title":"Self-critical sequence training for image captioning","author":"rennie","year":"2016","journal-title":"Proc CVPR"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.127"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.108"},{"key":"ref60","article-title":"Consensus-based sequence training for video captioning","author":"phan","year":"2017","journal-title":"arXiv 1712 09532"},{"key":"ref61","article-title":"Multimodal memory modelling for video captioning","author":"wang","year":"2016","journal-title":"arXiv 1611 05592"},{"key":"ref28","first-page":"3059","article-title":"Weakly supervised dense event captioning in videos","author":"duan","year":"2018","journal-title":"Proc NeurIPS"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.364"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.208"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref1","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc NeurIPS"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2016.2527258"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.117"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2016.2527378"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.147"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.339"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2682196"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2846664"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.497"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123448"},{"key":"ref58","first-page":"5518","article-title":"Middle-out decoding","author":"mehri","year":"2018","journal-title":"Proc NeurIPS"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018167"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00795"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123327"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.111"},{"key":"ref53","article-title":"Delving deeper into convolutional networks for learning video representations","author":"ballas","year":"2016","journal-title":"Proc ICLR"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.496"},{"key":"ref10","first-page":"1243","article-title":"Convolutional sequence to sequence learning","author":"gehring","year":"2017","journal-title":"Proc ICML"},{"key":"ref11","article-title":"Depthwise separable convolutions for neural machine translation","author":"kaiser","year":"2017","journal-title":"arXiv 1706 03059"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.138"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00583"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref15","article-title":"Multi-scale context aggregation by dilated convolutions","author":"yu","year":"2016","journal-title":"Proc ICLR"},{"key":"ref16","article-title":"Pixel recurrent neural networks","author":"van den oord","year":"2016","journal-title":"arXiv 1601 06759"},{"key":"ref17","first-page":"4790","article-title":"Conditional image generation with PixelCNN decoders","author":"van den oord","year":"2016","journal-title":"Proc NeurIPS"},{"key":"ref18","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","author":"chen","year":"2011","journal-title":"Proc ACL"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref3","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014","journal-title":"arXiv 1412 3555"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.277"},{"key":"ref8","article-title":"Memory networks","author":"weston","year":"2014","journal-title":"arXiv 1410 3916"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1150"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/381"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1044"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"key":"ref47","article-title":"Hadamard product for low-rank bilinear pooling","author":"kim","year":"2017","journal-title":"Proc ICLR"},{"key":"ref42","article-title":"Translating videos to natural language using deep recurrent neural networks","author":"venugopalan","year":"2014","journal-title":"arXiv 1412 4729"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/9242342\/08917665.pdf?arnumber=8917665","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T14:39:24Z","timestamp":1651070364000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8917665\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,11]]},"references-count":61,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2019.2956593","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"type":"print","value":"1051-8215"},{"type":"electronic","value":"1558-2205"}],"subject":[],"published":{"date-parts":[[2020,11]]}}}