{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T11:18:05Z","timestamp":1777288685620,"version":"3.51.4"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"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":["61702176"],"award-info":[{"award-number":["61702176"]}],"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":["2017JJ3038"],"award-info":[{"award-number":["2017JJ3038"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Foundation of Changsha Technological Plan","award":["kq1706020"],"award-info":[{"award-number":["kq1706020"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2019]]},"DOI":"10.1109\/access.2019.2908035","type":"journal-article","created":{"date-parts":[[2019,3,28]],"date-time":"2019-03-28T18:52:25Z","timestamp":1553799145000},"page":"40771-40781","source":"Crossref","is-referenced-by-count":41,"title":["Co-Attention Network With Question Type for Visual Question Answering"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8774-8115","authenticated-orcid":false,"given":"Chao","family":"Yang","sequence":"first","affiliation":[]},{"given":"Mengqi","family":"Jiang","sequence":"additional","affiliation":[]},{"given":"Bin","family":"Jiang","sequence":"additional","affiliation":[]},{"given":"Weixin","family":"Zhou","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5224-4048","authenticated-orcid":false,"given":"Keqin","family":"Li","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref33","first-page":"151","article-title":"Question type guided attention in visual question answering","author":"shi","year":"2018","journal-title":"Proc ECCV"},{"key":"ref32","author":"fu","year":"2018","journal-title":"Dual attention network for scene segmentation"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref30","first-page":"4929","article-title":"Deep semantic role labeling with self-attention","author":"tan","year":"2017","journal-title":"Proc AAAI"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.217"},{"key":"ref35","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc NIPS"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref28","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc NIPS"},{"key":"ref27","first-page":"3664","article-title":"High-order attention models for visual question answering","author":"schwartz","year":"2017","journal-title":"Proc NIPS"},{"key":"ref29","author":"lin","year":"2017","journal-title":"A structured self-attentive sentence embedding"},{"key":"ref2","author":"chen","year":"2015","journal-title":"Microsoft COCO captions Data collection and evaluation server"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/nrn755"},{"key":"ref22","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc ICML"},{"key":"ref21","author":"bahdanau","year":"2014","journal-title":"Neural machine translation by jointly learning to align and translate"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.499"},{"key":"ref23","author":"chen","year":"2015","journal-title":"ABC-CNN An attention based convolutional neural network for visual question answering"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2844789"},{"key":"ref25","first-page":"21","article-title":"Stacked attention networks for image question answering","author":"yang","year":"2015","journal-title":"Proc CVPR"},{"key":"ref10","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 NIPS"},{"key":"ref11","first-page":"2953","article-title":"Exploring models and data for image question answering","author":"ren","year":"2015","journal-title":"Proc NIPS"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00444"},{"key":"ref12","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 NIPS"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.540"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref15","first-page":"1","article-title":"Hadamard product for low-rank bilinear pooling","author":"kim","year":"2017","journal-title":"Proc ICLR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2873570"},{"key":"ref18","first-page":"6975","article-title":"Visual question answering with memory-augmented networks","author":"ma","year":"2017","journal-title":"Proc CVPR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2018.12.004"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.560"},{"key":"ref3","first-page":"241","article-title":"Deep image retrieval: Learning global representations for image search","author":"gordo","year":"2016","journal-title":"Proc ECCV"},{"key":"ref6","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":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2661334.2661407"},{"key":"ref8","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","author":"lu","year":"2016","journal-title":"Proc NIPS"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1044"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.232"},{"key":"ref46","first-page":"6325","article-title":"Making the V in VQA matter: Elevating the role of image understanding in visual question answering","author":"goyal","year":"2016","journal-title":"Proc CVPR"},{"key":"ref45","first-page":"361","article-title":"Multimodal residual learning for visual QA","author":"kim","year":"2016","journal-title":"Proc NIPS"},{"key":"ref48","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc ECCV"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.145"},{"key":"ref42","author":"ilievski","year":"2016","journal-title":"A focused dynamic attention model for visual question answering"},{"key":"ref41","first-page":"30","article-title":"Image question answering using convolutional neural network with dynamic parameter prediction","author":"noh","year":"2015","journal-title":"Proc CVPR"},{"key":"ref44","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"},{"key":"ref43","first-page":"2397","article-title":"Dynamic memory networks for visual and textual question answering","author":"xiong","year":"2016","journal-title":"Proc ICML"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8600701\/08676009.pdf?arnumber=8676009","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T01:28:59Z","timestamp":1643246939000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8676009\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/access.2019.2908035","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]}}}