{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T20:30:11Z","timestamp":1772569811250,"version":"3.50.1"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2017,12,1]],"date-time":"2017-12-01T00:00:00Z","timestamp":1512086400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Basic Research Program of China (973 Program)","doi-asserted-by":"crossref","award":["2013CB336500"],"award-info":[{"award-number":["2013CB336500"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"name":"National Youth Top-notch Talent Support Program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2017,12]]},"DOI":"10.1109\/tip.2017.2746267","type":"journal-article","created":{"date-parts":[[2017,8,28]],"date-time":"2017-08-28T14:11:05Z","timestamp":1503929465000},"page":"5656-5666","source":"Crossref","is-referenced-by-count":51,"title":["Unifying the Video and Question Attentions for Open-Ended Video Question Answering"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3161-3566","authenticated-orcid":false,"given":"Hongyang","family":"Xue","sequence":"first","affiliation":[]},{"given":"Zhou","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Deng","family":"Cai","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","author":"yu","year":"2016","journal-title":"Video captioning and retrieval models with semantic attention"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.283"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.540"},{"key":"ref35","author":"zhu","year":"2015","journal-title":"Uncovering temporal context for video question and answering"},{"key":"ref34","first-page":"4334","article-title":"Leveraging video descriptions to learn video question answering","author":"zeng","year":"2017","journal-title":"Proc AAAI"},{"key":"ref10","article-title":"TGIF-QA: Toward spatio-temporal reasoning in visual question answering","author":"jang","year":"2017","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref11","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.502"},{"key":"ref13","first-page":"3567","article-title":"Learning to answer questions from image using convolutional neural network","author":"ma","year":"2016","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref14","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 27th Inter Conf Neural Inf Process Syst"},{"key":"ref15","author":"mazaheri","year":"2016","journal-title":"Video fill in the blank with merging LSTMs"},{"key":"ref16","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"2013","journal-title":"Proc ICLR"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.11"},{"key":"ref18","first-page":"2953","article-title":"Exploring models and data for image question answering","author":"ren","year":"2015","journal-title":"Proc 28th Int Conf Neural Inf Process Syst"},{"key":"ref19","article-title":"The question generation shared task and evaluation challenge","author":"rus","year":"2009"},{"key":"ref28","author":"xu","year":"2015","journal-title":"Ask attend and answer Exploring question-guided spatial attention for visual question answering"},{"key":"ref4","first-page":"2296","article-title":"Are you talking to a machine? Dataset and methods for multilingual image question","author":"gao","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3115\/981732.981751"},{"key":"ref3","author":"chen","year":"2015","journal-title":"ABC-CNN An attention based convolutional neural network for visual question answering"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1422953112"},{"key":"ref29","author":"xu","year":"2015","journal-title":"Show attend and tell Neural image caption generation with visual attention"},{"key":"ref5","article-title":"Automatically generating reading comprehension look-back strategy: Questions from expository texts","author":"gates","year":"2008"},{"key":"ref8","first-page":"609","article-title":"Good question! Statistical ranking for question generation","author":"heilman","year":"2010","journal-title":"Proc Conf Human Language Technology Conf North Am Assoc for Computational Linguistics"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2_3"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1866029.1866080"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref20","author":"simonyan","year":"2014","journal-title":"Very Deep Convolutional Networks for Large-scale Image Recognition"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.501"},{"key":"ref21","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc 27th Int Conf Neural Inf Process Syst"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1109\/MMUL.2014.29","article-title":"Joint video and text parsing for understanding events and answering queries","volume":"21","author":"tu","year":"2014","journal-title":"IEEE Multimedia"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/8024124\/08017608.pdf?arnumber=8017608","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:40:03Z","timestamp":1641987603000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8017608\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,12]]},"references-count":36,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tip.2017.2746267","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,12]]}}}