{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T06:59:43Z","timestamp":1760597983140,"version":"3.37.3"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2021,6,1]],"date-time":"2021-06-01T00:00:00Z","timestamp":1622505600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,1]],"date-time":"2021-06-01T00:00:00Z","timestamp":1622505600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,1]],"date-time":"2021-06-01T00:00:00Z","timestamp":1622505600000},"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"],"award-info":[{"award-number":["61876130","61932009"]}],"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":[[2021,6]]},"DOI":"10.1109\/tcsvt.2020.3020877","type":"journal-article","created":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T20:57:25Z","timestamp":1598993845000},"page":"2438-2449","source":"Crossref","is-referenced-by-count":13,"title":["Hierarchical Memory Decoder for Visual Narrating"],"prefix":"10.1109","volume":"31","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\/0000-0001-6121-0384","authenticated-orcid":false,"given":"Zhou","family":"Zhao","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"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref38","first-page":"7396","article-title":"Show, reward and tell: Automatic generation of narrative paragraph from photo stream by adversarial training","author":"wang","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref33","first-page":"1112","article-title":"Hierarchical LSTMs with adaptive attention for visual captioning","volume":"42","author":"gao","year":"2020","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/381"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2846664"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350918"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3126686.3126715"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018167"},{"key":"ref34","first-page":"5523","article-title":"Middle-out decoding","author":"mehri","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/143"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123448"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00795"},{"key":"ref63","article-title":"Consensus-based sequence training for video captioning","author":"phan","year":"2017","journal-title":"arXiv 1712 09532"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2682196"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018465"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2016.2527258"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1101"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2867286"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1147"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018320"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351072"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.339"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.117"},{"key":"ref24","article-title":"Less is more: Picking informative frames for video captioning","author":"chen","year":"2018","journal-title":"arXiv 1803 01457"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00784"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2016.2527378"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01277"},{"key":"ref50","first-page":"1","article-title":"Optiongan: Learning joint reward-policy options using generative adversarial inverse reinforcement learning","author":"henderson","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref51","article-title":"A connection between generative adversarial networks, inverse reinforcement learning, and energy-based models","author":"finn","year":"2016","journal-title":"arXiv 1611 03852"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/307"},{"key":"ref58","article-title":"Delving deeper into convolutional networks for learning video representations","author":"ballas","year":"2015","journal-title":"arXiv 1511 06432"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.496"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.497"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref52","article-title":"Translating videos to natural language using deep recurrent neural networks","author":"venugopalan","year":"2014","journal-title":"arXiv 1412 4729"},{"key":"ref10","article-title":"Depthwise separable convolutions for neural machine translation","author":"kaiser","year":"2017","journal-title":"arXiv 1706 03059"},{"key":"ref11","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref12","article-title":"Accessing higher-level representations in sequential transformers with feedback memory","author":"fan","year":"2020","journal-title":"arXiv 2002 09402"},{"key":"ref13","first-page":"2440","article-title":"End-to-end memory networks","author":"sukhbaatar","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref14","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","volume":"1","author":"chen","year":"2011","journal-title":"Proc 49th Annu Meeting Assoc Comput Linguistics Hum Lang Technol"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2851077"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351060"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123327"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref3","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc Neural Inf Process Syst (NIPS)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.277"},{"key":"ref5","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014","journal-title":"arXiv 1412 3555"},{"key":"ref8","first-page":"1","article-title":"Memory networks","author":"weston","year":"2015","journal-title":"Proc ICLR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref49","article-title":"Learning robust rewards with adversarial inverse reinforcement learning","author":"fu","year":"2017","journal-title":"arXiv 1710 11248"},{"key":"ref9","article-title":"Convolutional sequence to sequence learning","author":"gehring","year":"2017","journal-title":"arXiv 1705 03122"},{"key":"ref46","article-title":"Deep reinforcement learning: An overview","author":"li","year":"2017","journal-title":"arXiv 1701 07274"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1561\/9781680835397"},{"key":"ref48","first-page":"4565","article-title":"Generative adversarial imitation learning","author":"ho","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref47","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume":"8","author":"ziebart","year":"2008","journal-title":"Proc AAAI"},{"key":"ref42","article-title":"Pixel recurrent neural networks","author":"van den oord","year":"2016","journal-title":"arXiv 1601 06759"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1044"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1083"},{"key":"ref43","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"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/9446657\/09184025.pdf?arnumber=9184025","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:50:28Z","timestamp":1652194228000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9184025\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6]]},"references-count":65,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2020.3020877","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"type":"print","value":"1051-8215"},{"type":"electronic","value":"1558-2205"}],"subject":[],"published":{"date-parts":[[2021,6]]}}}