{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T14:42:45Z","timestamp":1777128165207,"version":"3.51.4"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100007219","name":"Natural Science Foundation of Shanghai, China","doi-asserted-by":"publisher","award":["22ZR1418400"],"award-info":[{"award-number":["22ZR1418400"]}],"id":[{"id":"10.13039\/100007219","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1109\/tnnls.2024.3377636","type":"journal-article","created":{"date-parts":[[2024,3,26]],"date-time":"2024-03-26T16:27:46Z","timestamp":1711470466000},"page":"5059-5069","source":"Crossref","is-referenced-by-count":4,"title":["Latent Attention Network With Position Perception for Visual Question Answering"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6270-7771","authenticated-orcid":false,"given":"Jing","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8342-5896","authenticated-orcid":false,"given":"Xiaoqiang","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3759-2041","authenticated-orcid":false,"given":"Zhe","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai, China"}],"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":"10.1109\/TNNLS.2020.3017530"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.416"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref6","article-title":"Visual entailment task for visually-grounded language learning","author":"Xie","year":"2018","journal-title":"arXiv:1811.10582"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1044"},{"key":"ref8","article-title":"Hadamard product for low-rank bilinear pooling","author":"Kim","year":"2016","journal-title":"arXiv:1610.04325"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018102"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2817340"},{"key":"ref11","article-title":"Bilinear attention networks","author":"Kim","year":"2018","journal-title":"arXiv:1805.07932"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.642"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01041"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3104937"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.02.006"},{"key":"ref16","article-title":"Simple baseline for visual question answering","author":"Zhou","year":"2015","journal-title":"arXiv:1512.02167"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"ref18","article-title":"ABC-CNN: An attention based convolutional neural network for visual question answering","author":"Chen","year":"2015","journal-title":"arXiv:1511.05960"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_28"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.02.022"},{"key":"ref21","article-title":"Interpretable counting for visual question answering","author":"Trott","year":"2017","journal-title":"arXiv:1712.08697"},{"key":"ref22","article-title":"Learning to count objects in natural images for visual question answering","author":"Zhang","year":"2018","journal-title":"arXiv:1802.05766"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00558"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01028"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.353"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3222871"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3175605"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3050918"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3142771"},{"key":"ref31","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00680"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3016083"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3135655"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16328"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01034"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00377"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00845"},{"key":"ref40","first-page":"1324","article-title":"Learning to count objects in images","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"23","author":"Lempitsky"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018076"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref46","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3097180"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1049\/ipr2.12421"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00637"},{"key":"ref51","article-title":"SA-VQA: Structured alignment of visual and semantic representations for visual question answering","author":"Xiong","year":"2022","journal-title":"arXiv:2201.10654"},{"key":"ref52","article-title":"UNIMO: Towards unified-modal understanding and generation via cross-modal contrastive learning","author":"Li","year":"2020","journal-title":"arXiv:2012.15409"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref55","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","author":"Su","year":"2019","journal-title":"arXiv:1908.08530"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01278"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2021.10.028"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240513"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.107956"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2975093"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106639"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10908444\/10479185.pdf?arnumber=10479185","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T18:39:23Z","timestamp":1764959963000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10479185\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":63,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3377636","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}