{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T02:56:00Z","timestamp":1763348160024,"version":"3.37.3"},"reference-count":37,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/OAPA.html"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["71331008","61105124"],"award-info":[{"award-number":["71331008","61105124"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2018]]},"DOI":"10.1109\/access.2018.2873570","type":"journal-article","created":{"date-parts":[[2018,10,4]],"date-time":"2018-10-04T19:11:32Z","timestamp":1538680292000},"page":"57923-57932","source":"Crossref","is-referenced-by-count":8,"title":["Multimodal Local Perception Bilinear Pooling for Visual Question Answering"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8413-7220","authenticated-orcid":false,"given":"Mingrui","family":"Lao","sequence":"first","affiliation":[]},{"given":"Yanming","family":"Guo","sequence":"additional","affiliation":[]},{"given":"Hui","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Xin","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"journal-title":"A focused dynamic attention model for visual question answering","year":"2016","author":"ilievski","key":"ref33"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"journal-title":"Neural Networks Module","year":"2015","author":"andreas","key":"ref31"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.500"},{"journal-title":"Learning visual knowledge memory networks for visual question answering","year":"2018","author":"su","key":"ref37"},{"journal-title":"Tips and tricks for visual question answering Learnings from the 2017 challenge","year":"2017","author":"teney","key":"ref36"},{"journal-title":"Training recurrent answering units with joint loss minimization for vqa","year":"2016","author":"noh","key":"ref35"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1181"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2587640"},{"key":"ref11","first-page":"375","article-title":"Knowing when to look: Adaptive attention via a visual sentinel for image captioning","author":"lu","year":"2016","journal-title":"Proc CVPR"},{"key":"ref12","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 ECCV"},{"journal-title":"ABC-CNN An attention based convolutional neural network for visual question answering","year":"2016","author":"chen","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.499"},{"journal-title":"Co-attending free-form regions and detections with multi-modal multiplicative feature embedding for visual question answering","year":"2016","author":"lu","key":"ref16"},{"key":"ref17","first-page":"6","article-title":"Bottom-up and top-down attention for image captioning and visual question answering","author":"anderson","year":"2018","journal-title":"Proc CVPR"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref19","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","author":"lu","year":"2016","journal-title":"Proc NIPS"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.11"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015349"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2807412"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248084"},{"key":"ref6","article-title":"Hadamard product for low-rank bilinear pooling","author":"kim","year":"2017","journal-title":"Proc ICLR"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.9"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1044"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247814"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2519449"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0966-6"},{"key":"ref20","first-page":"299","article-title":"Dual attention networks for multimodal reasoning and matching","author":"nam","year":"2016","journal-title":"Proc CVPR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.442"},{"journal-title":"Simple baseline for visual question answering","year":"2015","author":"zhou","key":"ref21"},{"key":"ref24","first-page":"1449","article-title":"Bilinear CNN models for fine-grained visual recognition","author":"lin","year":"2016","journal-title":"Proc ICCV"},{"key":"ref23","first-page":"693","article-title":"Finding frequent items in data streams","author":"charikar","year":"2002","journal-title":"Proc ICALP"},{"key":"ref26","first-page":"601","article-title":"LSTM neural networks for language modeling","author":"sundermeyer","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8274985\/08481352.pdf?arnumber=8481352","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T19:16:02Z","timestamp":1643224562000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8481352\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/access.2018.2873570","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2018]]}}}