{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T18:43:36Z","timestamp":1761677016063,"version":"3.37.3"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"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","award":["61976231,U1611461,61573387,61172141"],"award-info":[{"award-number":["61976231,U1611461,61573387,61172141"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,7,18]]},"DOI":"10.1109\/ijcnn52387.2021.9534164","type":"proceedings-article","created":{"date-parts":[[2021,9,22]],"date-time":"2021-09-22T20:32:37Z","timestamp":1632342757000},"page":"1-8","source":"Crossref","is-referenced-by-count":2,"title":["Dense Video Captioning with Hierarchical Attention-Based Encoder-Decoder Networks"],"prefix":"10.1109","author":[{"given":"Mingjing","family":"Yu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huicheng","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zehua","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref38","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TMM.2020.2966878","article-title":"Dense video captioning using graph-based sentence summarization","author":"zhang","year":"2020","journal-title":"IEEE Trans Multimedia"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref32","first-page":"2361","article-title":"Review networks for caption generation","author":"yang","year":"0","journal-title":"Proc Adv Neural Inform Process Syst"},{"key":"ref31","first-page":"807","article-title":"Rectified linear units improve restricted boltzmann machines","author":"nair","year":"0","journal-title":"Proc 7th Int Conf Machine Learning"},{"key":"ref30","first-page":"1","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.496"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1173"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01088"},{"key":"ref40","first-page":"65","article-title":"METEOR: An automatic metric for mt evaluation with improved correlation with human judgments","author":"lavie","year":"0","journal-title":"Proc Intrin Extrin Evalua Measures Machine Transla Summariza Workshop"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01034"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2916757"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2924576"},{"key":"ref14","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Adv Neural Inform Process Syst"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2913372"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/381"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016391"},{"key":"ref18","first-page":"1","article-title":"Generating natural-language video descriptions using text-mined knowledge","author":"krishnamoorthy","year":"0","journal-title":"Proc AAAI Conf Arti Intell"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2868668"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-017-9263-6"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00782"},{"journal-title":"Relational hierarchical encoder-decoder for dense video captioning","year":"2020","author":"wang","key":"ref29"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2936526"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"},{"key":"ref7","first-page":"396","article-title":"Joint event detection and description in continuous video streams","author":"xu","year":"0","journal-title":"Proceedings of IEEE Winter Conference on Applications of Computer Vision"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.337"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00751"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00795"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00675"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018167"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3014606"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref23","first-page":"4117","article-title":"Multi-modal dense video captioning","author":"iashin","year":"0","journal-title":"Proc IEEE Conf Comput Vis and Pattern Recog"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.675"},{"key":"ref25","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"}],"event":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2021,7,18]]},"location":"Shenzhen, China","end":{"date-parts":[[2021,7,22]]}},"container-title":["2021 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9533266\/9533267\/09534164.pdf?arnumber=9534164","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T23:22:25Z","timestamp":1673306545000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9534164\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,18]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/ijcnn52387.2021.9534164","relation":{},"subject":[],"published":{"date-parts":[[2021,7,18]]}}}