{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T10:20:30Z","timestamp":1740133230603,"version":"3.37.3"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"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":["61602405","61836002","61751209"],"award-info":[{"award-number":["61602405","61836002","61751209"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Joint Research Program of ZJU"},{"name":"Hikvision Research Institute"},{"DOI":"10.13039\/100006112","name":"Microsoft Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006112","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2019,8]]},"DOI":"10.1109\/tip.2019.2902106","type":"journal-article","created":{"date-parts":[[2019,2,27]],"date-time":"2019-02-27T20:34:42Z","timestamp":1551299682000},"page":"3860-3872","source":"Crossref","is-referenced-by-count":25,"title":["Multi-Turn Video Question Answering via Hierarchical Attention Context Reinforced Networks"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6121-0384","authenticated-orcid":false,"given":"Zhou","family":"Zhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4195-5770","authenticated-orcid":false,"given":"Zhu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinghua","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Deng","family":"Cai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1062"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1046"},{"key":"ref31","first-page":"3400","article-title":"Mechanism-aware neural machine for dialogue response generation","author":"zhou","year":"2017","journal-title":"Proc AAAI"},{"key":"ref30","first-page":"3252","article-title":"Coherent dialogue with attention-based language models","author":"mei","year":"2017","journal-title":"Proc AAAI"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1045"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1230"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1127"},{"key":"ref28","first-page":"3288","article-title":"Multiresolution recurrent neural networks: An application to dialogue response generation","author":"serban","year":"2017","journal-title":"Proc AAAI"},{"key":"ref27","first-page":"829","article-title":"Dialog-based language learning","author":"weston","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref29","first-page":"5610","article-title":"Hierarchical recurrent attention network for response generation","author":"xing","year":"2018","journal-title":"Proc AAAI"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1033-7"},{"key":"ref1","first-page":"4334","article-title":"Leveraging video descriptions to learn video question answering","author":"zeng","year":"2017","journal-title":"Proc AAAI"},{"journal-title":"Visual Question Answering A Survey of Methods and Datasets","year":"2016","author":"wu","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2808685"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00688"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/512"},{"key":"ref26","first-page":"3776","article-title":"Building end-to-end dialogue systems using generative hierarchical neural network models","author":"serban","year":"2016","journal-title":"Proc AAAI"},{"key":"ref25","first-page":"3295","article-title":"A hierarchical latent variable encoder-decoder model for generating dialogues","author":"serban","year":"2017","journal-title":"Proc AAAI"},{"journal-title":"Very Deep Convolutional Networks for Large-scale Image Recognition","year":"2014","author":"simonyan","key":"ref50"},{"journal-title":"Efficient Estimation of Word Representations in Vector Space","year":"2013","author":"mikolov","key":"ref51"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms7210"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7287.001.0001"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.3115\/981732.981751"},{"key":"ref52","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref11","first-page":"1682","article-title":"A multi-world approach to question answering about real-world scenes based on uncertain input","author":"malinowski","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-2117"},{"key":"ref12","first-page":"361","article-title":"Multimodal residual learning for visual QA","author":"kim","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2852503"},{"key":"ref15","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","author":"lu","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.499"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00801"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.121"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.501"},{"journal-title":"Video fill in the blank with merging LSTMs","year":"2016","author":"mazaheri","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.149"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/492"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/513"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref9","first-page":"4655","article-title":"Visual question answering with question representation update (QRU)","author":"li","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.128"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00443"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-11752-2_15"},{"key":"ref47","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","author":"chen","year":"2011","journal-title":"Proc Ann Meeting Assoc for Computational Linguistics"},{"key":"ref42","first-page":"2440","article-title":"End-to-end memory networks","author":"sukhbaatar","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref41","volume":"7700","author":"orr","year":"2003","journal-title":"Neural Networks Tricks of the Trade"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/365"},{"journal-title":"An Actor-Critic Algorithm for Sequence Prediction","year":"2016","author":"bahdanau","key":"ref43"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/8736481\/08654010.pdf?arnumber=8654010","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T20:52:07Z","timestamp":1657745527000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8654010\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8]]},"references-count":55,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tip.2019.2902106","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"type":"print","value":"1057-7149"},{"type":"electronic","value":"1941-0042"}],"subject":[],"published":{"date-parts":[[2019,8]]}}}