{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T16:15:44Z","timestamp":1782836144671,"version":"3.54.5"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020AAA0108800"],"award-info":[{"award-number":["2020AAA0108800"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61877050"],"award-info":[{"award-number":["61877050"]}],"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":["61937001"],"award-info":[{"award-number":["61937001"]}],"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":["62020194"],"award-info":[{"award-number":["62020194"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Innovative Research Group of the National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61721002"],"award-info":[{"award-number":["61721002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Innovation Research Team of Ministry of Education","award":["IRT_17R86"],"award-info":[{"award-number":["IRT_17R86"]}]},{"name":"Project of China Knowledge Center for Engineering Science and Technology"},{"name":"Ministry of Education-China Mobile Communications Corporation (MoE-CMCC) \u201cArtifical Intelligence\u201d Project","award":["MCM20190701"],"award-info":[{"award-number":["MCM20190701"]}]},{"DOI":"10.13039\/501100012456","name":"National Social Science Fund of China","doi-asserted-by":"publisher","award":["18XXW005"],"award-info":[{"award-number":["18XXW005"]}],"id":[{"id":"10.13039\/501100012456","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Statistical Science Research Project","award":["2020LY103"],"award-info":[{"award-number":["2020LY103"]}]},{"name":"Ministry of Education Humanities and Social Sciences Fund","award":["17YJA860028"],"award-info":[{"award-number":["17YJA860028"]}]},{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","award":["202006280344"],"award-info":[{"award-number":["202006280344"]}],"id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017596","name":"Natural Science Basic Research Plan in Shaanxi Province of China","doi-asserted-by":"publisher","award":["2020JM-070"],"award-info":[{"award-number":["2020JM-070"]}],"id":[{"id":"10.13039\/501100017596","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":[[2023,3]]},"DOI":"10.1109\/tnnls.2021.3105284","type":"journal-article","created":{"date-parts":[[2021,8,30]],"date-time":"2021-08-30T20:53:40Z","timestamp":1630356820000},"page":"1380-1394","source":"Crossref","is-referenced-by-count":38,"title":["Multitask Learning for Visual Question Answering"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7432-3238","authenticated-orcid":false,"given":"Jie","family":"Ma","sequence":"first","affiliation":[{"name":"National Engineering Laboratory for Big Data Analytics, School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6004-0675","authenticated-orcid":false,"given":"Jun","family":"Liu","sequence":"additional","affiliation":[{"name":"National Engineering Laboratory for Big Data Analytics, School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5650-0600","authenticated-orcid":false,"given":"Qika","family":"Lin","sequence":"additional","affiliation":[{"name":"National Engineering Laboratory for Big Data Analytics, School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9116-0736","authenticated-orcid":false,"given":"Bei","family":"Wu","sequence":"additional","affiliation":[{"name":"National Engineering Laboratory for Big Data Analytics, School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3193-3658","authenticated-orcid":false,"given":"Yaxian","family":"Wang","sequence":"additional","affiliation":[{"name":"National Engineering Laboratory for Big Data Analytics, School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2816-4384","authenticated-orcid":false,"given":"Yang","family":"You","sequence":"additional","affiliation":[{"name":"Department of Computer Science, High Performance Computing for Artificial Intelligence Laboratory, National University of Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00380"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.03.005"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.540"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2754246"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d16-1044"},{"key":"ref9","first-page":"2397","article-title":"Dynamic memory networks for visual and textual question answering","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Xiong"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/179"},{"key":"ref12","article-title":"Hadamard product for low-rank bilinear pooling","volume-title":"5th Int. Conf. Learn. Represent. (ICLR)","author":"Kim"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00444"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00681"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref16","first-page":"1564","article-title":"Bilinear attention networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Kim"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00680"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00522"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00979"},{"key":"ref20","first-page":"1","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL-HLT","author":"Devlin"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_28"},{"key":"ref25","article-title":"A focused dynamic attention model for visual question answering","author":"Ilievski","year":"2016","journal-title":"arXiv:1604.01485"},{"key":"ref26","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":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.232"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2019.05.001"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00637"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00757"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2943456"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref33","first-page":"740","volume-title":"Microsoft COCO: Common Objects in Context in European Conference on Computer Vision","author":"Lin","year":"2014"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00520"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007379606734"},{"key":"ref36","article-title":"Embodied multimodal multitask learning","author":"Chaplot","year":"2019","journal-title":"arXiv:1902.01385"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_17"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1194"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2016.2568758"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2626959"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2014.2311123"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240687"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref46","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Vaswani"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3115\/1225403.1225421"},{"key":"ref48","article-title":"Layer normalization","author":"Lei Ba","year":"2016","journal-title":"arXiv:1607.06450"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01072"},{"key":"ref50","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Represent. (ICLR), Conf. Track","author":"Kingma"},{"key":"ref51","article-title":"Learning to count objects in natural images for visual question answering","volume-title":"Proc. 6th Int. Conf. Learn. Represent. (ICLR)","author":"Zhang"},{"key":"ref52","article-title":"Pythia v0.1: The winning entry to the VQA challenge 2018","author":"Jiang","year":"2018","journal-title":"arXiv:1807.09956"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2817340"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00209"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00592"},{"key":"ref56","volume-title":"Detectron","author":"Girshick","year":"2018"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.121"},{"key":"ref58","first-page":"8334","article-title":"Learning conditioned graph structures for interpretable visual question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Norcliffe-Brown"},{"key":"ref59","first-page":"4967","article-title":"A simple neural network module for relational reasoning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Santoro"},{"key":"ref60","article-title":"Compositional attention networks for machine reasoning","volume-title":"Proc. 6th Int. Conf. Learn. Represent. (ICLR)","author":"Hudson"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10056374\/09525040.pdf?arnumber=9525040","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T00:01:55Z","timestamp":1705017715000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9525040\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3]]},"references-count":60,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2021.3105284","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3]]}}}