{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:48:20Z","timestamp":1778082500401,"version":"3.51.4"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["ZYGX2019J073"],"award-info":[{"award-number":["ZYGX2019J073"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61772116"],"award-info":[{"award-number":["61772116"]}],"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":["61872064"],"award-info":[{"award-number":["61872064"]}],"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":["61632007"],"award-info":[{"award-number":["61632007"]}],"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":["61602049"],"award-info":[{"award-number":["61602049"]}],"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":["61872067"],"award-info":[{"award-number":["61872067"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100012542","name":"Sichuan Science and Technology Program","doi-asserted-by":"publisher","award":["2019JDTD0005"],"award-info":[{"award-number":["2019JDTD0005"]}],"id":[{"id":"10.13039\/100012542","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100012542","name":"Sichuan Science and Technology Program","doi-asserted-by":"publisher","award":["2019YFH0016"],"award-info":[{"award-number":["2019YFH0016"]}],"id":[{"id":"10.13039\/100012542","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Open Project of Zhejiang Lab","award":["2019KD0AB05"],"award-info":[{"award-number":["2019KD0AB05"]}]},{"name":"Zhejiang Lab\u2019s International Talent Fund for Young Professionals"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2021,10]]},"DOI":"10.1109\/tnnls.2020.3017530","type":"journal-article","created":{"date-parts":[[2020,9,17]],"date-time":"2020-09-17T20:01:25Z","timestamp":1600372885000},"page":"4362-4373","source":"Crossref","is-referenced-by-count":72,"title":["Rich Visual Knowledge-Based Augmentation Network for Visual Question Answering"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2675-9763","authenticated-orcid":false,"given":"Liyang","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8815-5335","authenticated-orcid":false,"given":"Shuaicheng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Donghao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengpeng","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangpeng","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2549-8322","authenticated-orcid":false,"given":"Jingkuan","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2522-6394","authenticated-orcid":false,"given":"Lianli","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1044"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018658"},{"key":"ref5","first-page":"2204","article-title":"Recurrent models of visual attention","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mnih"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref7","article-title":"Neural machine translation by jointly learning to align and translate","volume-title":"arXiv:1409.0473","author":"Bahdanau","year":"2014"},{"key":"ref8","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"arXiv:1810.04805","author":"Devlin","year":"2018"},{"key":"ref9","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"arXiv:1409.1556","author":"Simonyan","year":"2014"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-343"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00637"},{"key":"ref13","article-title":"Graph neural networks: A review of methods and applications","volume-title":"arXiv:1812.08434","author":"Zhou","year":"2018"},{"key":"ref14","article-title":"Learning representations of graph data-a survey","volume-title":"arXiv:1906.02989","author":"Kinderkhedia","year":"2019"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11164"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2708709"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.11"},{"key":"ref19","first-page":"2296","article-title":"Are you talking to a machine? Dataset and methods for multilingual image question","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gao"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.540"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350971"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.9"},{"issue":"5","key":"ref24","first-page":"1112","article-title":"Hierarchical LSTMs with adaptive attention for visual captioning","volume":"42","author":"Gao","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref25","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","volume-title":"Proc. ICML","author":"Xu"},{"key":"ref26","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.496"},{"key":"ref29","article-title":"Improving question answering with external knowledge","volume-title":"arXiv:1902.00993","author":"Pan","year":"2019"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-3023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1076"},{"key":"ref32","article-title":"Explicit knowledge-based reasoning for visual question answering","volume-title":"arXiv:1511.02570","author":"Wang","year":"2015"},{"issue":"4","key":"ref33","first-page":"56","article-title":"YAGO2: A spatially and temporally enhanced knowledge base from Wikipedia","volume":"52","author":"Hoffart","year":"2009","journal-title":"Commun. ACM"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-76298-0_52"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00207"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref37","article-title":"Efficient estimation of word representations in vector space","volume-title":"arXiv:1301.3781","author":"Mikolov","year":"2013"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00522"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2754246"},{"key":"ref41","article-title":"Adam: A method for stochastic optimization","volume-title":"arXiv:1412.6980","author":"Kingma","year":"2014"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01305-2"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2729019"},{"key":"ref44","first-page":"1564","article-title":"Bilinear attention networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kim"},{"key":"ref45","article-title":"Learning to count objects in natural images for visual question answering","volume-title":"arXiv:1802.05766","author":"Zhang","year":"2018"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2851077"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9559436\/09199272.pdf?arnumber=9199272","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,24]],"date-time":"2024-01-24T01:19:48Z","timestamp":1706059188000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9199272\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10]]},"references-count":46,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2020.3017530","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,10]]}}}