{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T03:38:01Z","timestamp":1776310681868,"version":"3.50.1"},"reference-count":65,"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\/OAPA.html"},{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/OAPA.html"}],"funder":[{"DOI":"10.13039\/100000161","name":"National Institute of Standards and Technology","doi-asserted-by":"publisher","award":["60NANB17D156"],"award-info":[{"award-number":["60NANB17D156"]}],"id":[{"id":"10.13039\/100000161","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100013177","name":"Interior Business Center","doi-asserted-by":"publisher","award":["D17PC00340"],"award-info":[{"award-number":["D17PC00340"]}],"id":[{"id":"10.13039\/100013177","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2019,8,1]]},"DOI":"10.1109\/tpami.2018.2890628","type":"journal-article","created":{"date-parts":[[2019,1,9]],"date-time":"2019-01-09T01:05:25Z","timestamp":1546995925000},"page":"1893-1908","source":"Crossref","is-referenced-by-count":60,"title":["Focal Visual-Text Attention for Memex Question Answering"],"prefix":"10.1109","volume":"41","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2219-5569","authenticated-orcid":false,"given":"Junwei","family":"Liang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0286-8439","authenticated-orcid":false,"given":"Lu","family":"Jiang","sequence":"additional","affiliation":[]},{"given":"Liangliang","family":"Cao","sequence":"additional","affiliation":[]},{"given":"Yannis","family":"Kalantidis","sequence":"additional","affiliation":[]},{"given":"Li-Jia","family":"Li","sequence":"additional","affiliation":[]},{"given":"Alexander G.","family":"Hauptmann","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"ref38","first-page":"1693","article-title":"Teaching machines to read and comprehend","author":"hermann","year":"2015","journal-title":"Proc 28th Int Conf Neural Inf Process Syst"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00898"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00592"},{"key":"ref31","article-title":"Learning a text-video embedding from incomplete and heterogeneous data","volume":"abs 1804 2516","author":"miech","year":"2018","journal-title":"CoRR"},{"key":"ref30","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 Int Conf Neural Inf Process Syst"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00430"},{"key":"ref36","first-page":"1","article-title":"Embodied question answering","author":"das","year":"2018","journal-title":"Proc IEEE Conf Comput Vis and Pattern Recog"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00380"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00522"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref62","article-title":"ADADELTA: An adaptive learning rate method","author":"zeiler","year":"2012","journal-title":"CoRR"},{"key":"ref61","first-page":"4278","article-title":"Inception-v4, inception-ResNet and the impact of residual connections on learning","author":"szegedy","year":"2017","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/280"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.600"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.80"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.145"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.501"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/1897816.1897840"},{"key":"ref2","first-page":"101","article-title":"As we may think","volume":"176","author":"bush","year":"1945","journal-title":"The Atlantic Monthly"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3018661.3018736"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/1459359.1459376"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1007\/11788034_17","article-title":"Automatic person annotation of family photo album","author":"zhao","year":"2006","journal-title":"Proc Int Conf Image Video Retrieval"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1631272.1631420"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1240624.1240684"},{"key":"ref23","first-page":"1","article-title":"Annotating collections of photos using hierarchical event and scene models","author":"cao","year":"2008","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995680"},{"key":"ref25","first-page":"243","article-title":"Joint people, event, and location recognition in personal photo collections using cross-domain context","author":"lin","year":"2010","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00801"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1044"},{"key":"ref59","first-page":"2397","article-title":"Dynamic memory networks for visual and textual question answering","author":"xiong","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref58","article-title":"A compare-aggregate model for matching text sequences","author":"wang","year":"2016","journal-title":"CoRR"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1181"},{"key":"ref56","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1145\/2671188.2749399","article-title":"Bridging the ultimate semantic gap: A semantic search engine for internet videos","author":"jiang","year":"2015","journal-title":"Proc 5th ACM Int Conf Multimedia Retrieval"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref54","article-title":"FVQA: Fact-based visual question answering","author":"wang","year":"2016","journal-title":"CoRR"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1147"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"key":"ref10","first-page":"451","article-title":"Ask, attend and answer: Exploring question-guided spatial attention for visual question answering","author":"xu","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref11","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 28th Int Conf Neural Inf Process Syst"},{"key":"ref40","article-title":"Bidirectional attention flow for machine comprehension","author":"seo","year":"2016","journal-title":"CoRR"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.217"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1033-7"},{"key":"ref16","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":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.283"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"ref4","article-title":"MemexQA: Visual memex question answering","author":"jiang","year":"2017","journal-title":"CoRR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00642"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/957013.957146"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.149"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.540"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00637"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.501"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref45","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","author":"lu","year":"2016","journal-title":"Proc 30th Int Conf Neural Inf Process Syst"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.232"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098177"},{"key":"ref41","article-title":"Machine comprehension using match-LSTM and answer pointer","author":"wang","year":"2016","journal-title":"CoRR"},{"key":"ref44","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1016\/j.cviu.2017.10.001","article-title":"Human attention in visual question answering: Do humans and deep networks look at the same regions?","volume":"163","author":"das","year":"2017","journal-title":"Comput Vis Image Understanding"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.499"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielaam\/34\/8752185\/8603827-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/8752185\/08603827.pdf?arnumber=8603827","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,8]],"date-time":"2022-04-08T18:47:37Z","timestamp":1649443657000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8603827\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8,1]]},"references-count":65,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2018.2890628","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,8,1]]}}}