{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T16:46:05Z","timestamp":1784738765072,"version":"3.55.0"},"reference-count":49,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,7,18]]},"DOI":"10.1109\/ijcnn52387.2021.9533855","type":"proceedings-article","created":{"date-parts":[[2021,9,20]],"date-time":"2021-09-20T21:27:41Z","timestamp":1632173261000},"page":"1-10","source":"Crossref","is-referenced-by-count":3,"title":["Visual-Semantic Dual Channel Network for Visual Question Answering"],"prefix":"10.1109","author":[{"given":"Xin","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiaohong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ting","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yubo","family":"Jia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"European Conference on Computer Vision"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"1532","DOI":"10.3115\/v1\/D14-1162","article-title":"Glove: Global vectors for word representation","author":"pennington","year":"2014","journal-title":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00444"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9206815"},{"key":"ref36"},{"key":"ref35"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2817340"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.121"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1018"},{"key":"ref29","first-page":"9199","article-title":"Towards real-time object detection with region proposal networks","author":"faster","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref1","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.08.009"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.494"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00756"},{"key":"ref24","first-page":"5","article-title":"Du-alvd: An adaptive dual encoding model for deep visual understanding in visual dialogue","volume":"1","author":"jiang","year":"2020","journal-title":"AAAI"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2890628"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/2766462.2767738"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1348"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018876"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413943"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1207\/s15516709cog0402_2"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/0167-2789(90)90087-6"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.325"},{"key":"ref17","author":"santoro","year":"2017","journal-title":"A simple neural network module for relational reasoning"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2019.115648"},{"key":"ref19","article-title":"Multimodal graph networks for compositional generalization in visual question answering","volume":"33","author":"saqur","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref3","first-page":"2953","article-title":"Exploring models and data for image question answering","volume":"28","author":"ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_34"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1164"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref7","first-page":"8604","article-title":"Self-critical reasoning for robust visual question answering","author":"wu","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00678"},{"key":"ref9","first-page":"1","article-title":"Design and deployment of an image polarity detector with visual attention","author":"ragusa","year":"2021","journal-title":"Cognitive Computation"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_29"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00637"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00209"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_2"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00729"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref44","first-page":"1821","article-title":"Multi-modal factorized bilinear pooling with co-attention learning for visual question answering","author":"yu","year":"2017","journal-title":"Proceedings of the IEEE International Conference on Computer Vision"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.232"}],"event":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","location":"Shenzhen, China","start":{"date-parts":[[2021,7,18]]},"end":{"date-parts":[[2021,7,22]]}},"container-title":["2021 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9533266\/9533267\/09533855.pdf?arnumber=9533855","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:46:15Z","timestamp":1652197575000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9533855\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,18]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/ijcnn52387.2021.9533855","relation":{},"subject":[],"published":{"date-parts":[[2021,7,18]]}}}