{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T04:43:26Z","timestamp":1784609006140,"version":"3.55.0"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["FL-170100117"],"award-info":[{"award-number":["FL-170100117"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000923","name":"ARC","doi-asserted-by":"publisher","award":["DE-180101438"],"award-info":[{"award-number":["DE-180101438"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000923","name":"ARC","doi-asserted-by":"publisher","award":["DP-180103424"],"award-info":[{"award-number":["DP-180103424"]}],"id":[{"id":"10.13039\/501100000923","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":[[2023,2]]},"DOI":"10.1109\/tnnls.2021.3104937","type":"journal-article","created":{"date-parts":[[2021,8,24]],"date-time":"2021-08-24T20:05:20Z","timestamp":1629835520000},"page":"1023-1034","source":"Crossref","is-referenced-by-count":53,"title":["Bilinear Graph Networks for Visual Question Answering"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9390-3078","authenticated-orcid":false,"given":"Dalu","family":"Guo","sequence":"first","affiliation":[{"name":"School of Computer Science, Faculty of Engineering, The University of Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4756-0609","authenticated-orcid":false,"given":"Chang","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Faculty of Engineering, The University of Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5979-578X","authenticated-orcid":false,"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[{"name":"School of Computer Science, Faculty of Engineering, The University of Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/155"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1044"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00680"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.121"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01068"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref10","article-title":"Hadamard product for low-rank bilinear pooling","author":"Kim","year":"2016","journal-title":"arXiv:1610.04325"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref13","article-title":"Bilinear attention networks","author":"Kim","year":"2018","journal-title":"arXiv:1805.07932"},{"key":"ref14","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref15","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref16","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"Lu","year":"2019","journal-title":"arXiv:1908.02265"},{"key":"ref17","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","author":"Su","year":"2019","journal-title":"arXiv:1908.08530"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00052"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_41"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref23","article-title":"Dual attention networks for multimodal reasoning and matching","author":"Nam","year":"2016","journal-title":"arXiv:1611.00471"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978\u20133-319-10602-148"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01028"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"ref30","first-page":"1024","article-title":"Inductive representation learning on large graphs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hamilton"},{"key":"ref31","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2016","journal-title":"arXiv:1609.02907"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2935173"},{"key":"ref33","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2017","journal-title":"arXiv:1710.10903"},{"key":"ref34","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014","journal-title":"arXiv:1412.3555"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1009"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00730"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01041"},{"key":"ref40","first-page":"2654","article-title":"Out of the box: Reasoning with graph convolution nets for factual visual question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Narasimhan"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2754246"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413977"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01045"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413518"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00209"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref49","first-page":"901","article-title":"Weight normalization: A simple reparameterization to accelerate training of deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Salimans"},{"issue":"1","key":"ref50","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2750679"},{"key":"ref52","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref53","article-title":"Learning to count objects in natural images for visual question answering","author":"Zhang","year":"2018","journal-title":"arXiv:1802.05766"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2817340"},{"key":"ref55","article-title":"Multi-modality latent interaction network for visual question answering","author":"Gao","year":"2019","journal-title":"arXiv:1908.04289"},{"key":"ref56","article-title":"Large-scale adversarial training for vision-and-language representation learning","author":"Gan","year":"2020","journal-title":"arXiv:2006.06195"},{"key":"ref57","article-title":"StructBERT: Incorporating language structures into pre-training for deep language understanding","author":"Wang","year":"2019","journal-title":"arXiv:1908.04577"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-2124"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00522"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00204"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00268"},{"key":"ref62","article-title":"RUBi: Reducing unimodal biases in visual question answering","author":"Cadene","year":"2019","journal-title":"arXiv:1906.10169"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10036162\/09521678.pdf?arnumber=9521678","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T23:39:49Z","timestamp":1705016389000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9521678\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2]]},"references-count":62,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2021.3104937","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2]]}}}