{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T14:55:59Z","timestamp":1784300159788,"version":"3.55.0"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2020,4,1]],"date-time":"2020-04-01T00:00:00Z","timestamp":1585699200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,4,1]],"date-time":"2020-04-01T00:00:00Z","timestamp":1585699200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,4,1]],"date-time":"2020-04-01T00:00:00Z","timestamp":1585699200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100013290","name":"National Key Research and Development Program of China Stem Cell and Translational Research","doi-asserted-by":"publisher","award":["SQ2018AAA010010"],"award-info":[{"award-number":["SQ2018AAA010010"]}],"id":[{"id":"10.13039\/501100013290","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61751209"],"award-info":[{"award-number":["61751209"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1611461"],"award-info":[{"award-number":["U1611461"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["51605428"],"award-info":[{"award-number":["51605428"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Hikvision-Zhejiang University Joint Research Center"},{"name":"Zhejiang University-Tongdun Technology Joint Laboratory of Artificial Intelligence"},{"name":"Zhejiang University iFLYTEK Joint Research Center"},{"DOI":"10.13039\/501100012455","name":"China Knowledge Centre for Engineering Sciences and Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012455","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Engineering Research Center of Digital Library"},{"DOI":"10.13039\/100010449","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010449","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2020,4]]},"DOI":"10.1109\/tmm.2019.2935678","type":"journal-article","created":{"date-parts":[[2019,8,23]],"date-time":"2019-08-23T19:54:07Z","timestamp":1566590047000},"page":"1032-1041","source":"Crossref","is-referenced-by-count":50,"title":["Frame Augmented Alternating Attention Network for Video Question Answering"],"prefix":"10.1109","volume":"22","author":[{"given":"Wenqiao","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7356-9711","authenticated-orcid":false,"given":"Siliang","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3052-4820","authenticated-orcid":false,"given":"Yanpeng","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiliang","family":"Pu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yueting","family":"Zhuang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"2440","article-title":"End-to-end memory networks","author":"sukhbaatar","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref33","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref32","article-title":"LSTM neural networks for language modeling","author":"sundermeyer","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21236\/ADA531042"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref35","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","author":"chen","year":"0","journal-title":"Proc 49th Annual Meeting Assoc for Comp Linguistics Human Language Tech"},{"key":"ref34","article-title":"Temporal attention filters for human activity recognition in videos","author":"piergiovanni","year":"2016","journal-title":"arXiv 1605 08140"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019127"},{"key":"ref40","first-page":"265","article-title":"Tensorflow: A system for large-scale machine learning","volume":"16","author":"abadi","year":"0","journal-title":"Proc Symp Oper Syst Des Implementation"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2015.66"},{"key":"ref12","first-page":"2953","article-title":"Exploring models and data for image question answering","author":"ren","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref15","article-title":"Bottom-up and top-down attention for image captioning and VQA","author":"anderson","year":"2017","journal-title":"arXiv 1707 07998"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2648498"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2267205"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123364"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2017.2654445"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2673412"},{"key":"ref27","article-title":"Co-attending free-form regions and detections with multi-modal multiplicative feature embedding for visual question answering","author":"lu","year":"2017","journal-title":"arXiv 1711 06794"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2610324"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/155"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00642"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2631881"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"286","DOI":"10.1109\/TSC.2015.2446991","article-title":"Question quality analysis and prediction in community question answering services with coupled mutual reinforcement","volume":"10","author":"coutts","year":"2017","journal-title":"IEEE Trans Services Comput"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2229971"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2008.917359"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2817340"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2375793"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.149"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.155"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.499"},{"key":"ref41","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref23","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","author":"lu","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080655"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9046171\/08811730.pdf?arnumber=8811730","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:55:20Z","timestamp":1651074920000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8811730\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,4]]},"references-count":41,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2019.2935678","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,4]]}}}