{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T10:18:45Z","timestamp":1729678725548,"version":"3.28.0"},"reference-count":64,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"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":[[2019,6]]},"DOI":"10.1109\/cvpr.2019.00854","type":"proceedings-article","created":{"date-parts":[[2020,1,9]],"date-time":"2020-01-09T21:06:13Z","timestamp":1578603973000},"page":"8339-8348","source":"Crossref","is-referenced-by-count":155,"title":["Memory-Attended Recurrent Network for Video Captioning"],"prefix":"10.1109","author":[{"given":"Wenjie","family":"Pei","sequence":"first","affiliation":[{"name":"Tencent"}]},{"given":"Jiyuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tencent YouTu"}]},{"given":"Xiangrong","family":"Wang","sequence":"additional","affiliation":[{"name":"Delft Univ. of Technology"}]},{"given":"Lei","family":"Ke","sequence":"additional","affiliation":[{"name":"Tencent"}]},{"given":"Xiaoyong","family":"Shen","sequence":"additional","affiliation":[{"name":"Tencent"}]},{"given":"Yu-Wing","family":"Tai","sequence":"additional","affiliation":[{"name":"Tencent"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/381"},{"key":"ref38","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"CoRR abs\/1409 1556"},{"key":"ref33","article-title":"Bleu: a method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"ACL"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.497"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.497"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.117"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2984062"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.61"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2984066"},{"key":"ref60","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"ICML"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.496"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.347"},{"key":"ref28","article-title":"Learning to answer questions from image using convolutional neural network","volume":"3","author":"ma","year":"2016","journal-title":"AAAI"},{"key":"ref64","article-title":"Leveraging video descriptions to learn video question answering","author":"zeng","year":"2017","journal-title":"AAAI"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00729"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1070"},{"key":"ref2","article-title":"Delving deeper into convolutional networks for learning video representations","author":"ballas","year":"2016","journal-title":"ICLRE"},{"key":"ref1","article-title":"Bottom-up and top-down attention for image captioning and vqa","author":"anderson","year":"2017","journal-title":"CVPR"},{"key":"ref20","article-title":"The kinetics human action video dataset","author":"kay","year":"2017","journal-title":"arXiv preprint arXiv 1705 06950"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1023\/A:1020346032608"},{"key":"ref21","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv preprint arXiv 1412 6980"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00042"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref26","article-title":"Video captioning with listwise supervision","author":"liu","year":"2017","journal-title":"AAAI"},{"key":"ref25","article-title":"Rouge: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Workshop on Text Summarization Branches Out"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00795"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00795"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref57","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11531","article-title":"Memory-augmented montecarlo tree search","author":"xiao","year":"2018","journal-title":"AAAI"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00714"},{"key":"ref55","article-title":"Memory networks","author":"weston","year":"2015","journal-title":"ICLRE"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00443"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1088"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00751"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2984064"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1146"},{"key":"ref40","article-title":"End-to-end memory networks","author":"sukhbaatar","year":"2015","journal-title":"NIPS"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2729019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.337"},{"key":"ref14","article-title":"Document context neural machine translation with memory networks","author":"haffari","year":"2018","journal-title":"ACL"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-2070"},{"key":"ref18","article-title":"Recurrent fusion network for image captioning","author":"jiang","year":"2018","journal-title":"ECCV"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2984065"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639349"},{"key":"ref3","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments","author":"banerjee","year":"2005","journal-title":"ACL2 Workshop"},{"key":"ref6","article-title":"Less is more: Picking informative frames for video captioning","author":"chen","year":"2018","journal-title":"ECCV"},{"key":"ref5","article-title":"Collecting highly parallel data for paraphrase evaluation","author":"chen","year":"2011","journal-title":"ACL"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-2057"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/2818048.2820013"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1173"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref41","article-title":"Inception-v4, inception-resnet and the impact of residual connections on learning","author":"szegedy","year":"2016","journal-title":"ICLR Workshop"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"}],"event":{"name":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","start":{"date-parts":[[2019,6,15]]},"location":"Long Beach, CA, USA","end":{"date-parts":[[2019,6,20]]}},"container-title":["2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8938205\/8953184\/08953335.pdf?arnumber=8953335","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,24]],"date-time":"2023-09-24T18:57:34Z","timestamp":1695581854000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8953335\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/cvpr.2019.00854","relation":{},"subject":[],"published":{"date-parts":[[2019,6]]}}}