{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T16:23:07Z","timestamp":1772554987337,"version":"3.50.1"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology, Taiwan","doi-asserted-by":"publisher","award":["MOST 109-2634-F-002-032"],"award-info":[{"award-number":["MOST 109-2634-F-002-032"]}],"id":[{"id":"10.13039\/501100004663","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":[[2021,11]]},"DOI":"10.1109\/tcsvt.2021.3051277","type":"journal-article","created":{"date-parts":[[2021,2,9]],"date-time":"2021-02-09T09:04:47Z","timestamp":1612861487000},"page":"4497-4507","source":"Crossref","is-referenced-by-count":35,"title":["End-to-End Video Question-Answer Generation With Generator-Pretester Network"],"prefix":"10.1109","volume":"31","author":[{"given":"Hung-Ting","family":"Su","sequence":"first","affiliation":[]},{"given":"Chen-Hsi","family":"Chang","sequence":"additional","affiliation":[]},{"given":"Po-Wei","family":"Shen","sequence":"additional","affiliation":[]},{"given":"Yu-Siang","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Ya-Liang","family":"Chang","sequence":"additional","affiliation":[]},{"given":"Yu-Cheng","family":"Chang","sequence":"additional","affiliation":[]},{"given":"Pu-Jen","family":"Cheng","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3330-0638","authenticated-orcid":false,"given":"Winston H.","family":"Hsu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3127901"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3127904"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240538"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351037"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350932"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351072"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123448"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123327"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240677"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240667"},{"key":"ref60","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"},{"key":"ref62","first-page":"13063","article-title":"Unified language model pre-training for natural language understanding and generation","author":"dong","year":"2019","journal-title":"Proc NIPS"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"},{"key":"ref63","first-page":"1","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"NAACL-HLT"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00211"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00640"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1017"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1105"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351060"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref68","first-page":"2440","article-title":"End-to-end memory networks","author":"sukhbaatar","year":"2015","journal-title":"Proc NIPS"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref2","first-page":"4334","article-title":"Leveraging video descriptions to learn video question answering","author":"zeng","year":"2017","journal-title":"Proc AAAI"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.149"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref21","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","author":"chen","year":"2011","journal-title":"Proc ACL"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00901"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00898"},{"key":"ref25","article-title":"Clevrer: Collision events for video representation and reasoning","author":"yi","year":"2020","journal-title":"Proc ICLR"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref59","article-title":"Automatic differentiation in Pytorch","author":"paszke","year":"2017","journal-title":"Proc NIPS Autodiff Workshop"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-4012"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.3115\/1614025.1614037"},{"key":"ref56","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","author":"banerjee","year":"2005","journal-title":"ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation And\/or Summarization"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref54","article-title":"Rouge: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Text Summarization Branches Out"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref52","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc NIPS"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00688"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2935678"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123420"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2897604"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018658"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_29"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053476"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019127"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-2623"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1167"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/512"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/492"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00210"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123364"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350971"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351065"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350969"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.127"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.111"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00013"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.108"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2924576"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3127895"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.497"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2867286"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/9590085\/09321516.pdf?arnumber=9321516","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:50:26Z","timestamp":1652194226000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9321516\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11]]},"references-count":70,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2021.3051277","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,11]]}}}