{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T15:52:38Z","timestamp":1775145158661,"version":"3.50.1"},"reference-count":66,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61902027"],"award-info":[{"award-number":["61902027"]}],"id":[{"id":"10.13039\/501100001809","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.2021.3135655","type":"journal-article","created":{"date-parts":[[2022,2,7]],"date-time":"2022-02-07T15:51:26Z","timestamp":1644249086000},"page":"4160-4171","source":"Crossref","is-referenced-by-count":22,"title":["Bilateral Cross-Modality Graph Matching Attention for Feature Fusion in Visual Question Answering"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1473-3956","authenticated-orcid":false,"given":"Jianjian","family":"Cao","sequence":"first","affiliation":[{"name":"Department of Computer Science, Beijing Institute of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6022-5952","authenticated-orcid":false,"given":"Xiameng","family":"Qin","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9386-9677","authenticated-orcid":false,"given":"Sanyuan","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Beijing Institute of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2656-3082","authenticated-orcid":false,"given":"Jianbing","family":"Shen","sequence":"additional","affiliation":[{"name":"Department of Computer and Information Science, State Key Laboratory of Internet of Things for Smart City, University of Macau, Macau, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref2","article-title":"Pythia v0.1: The winning entry to the VQA challenge 2018","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Jiang"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref4","first-page":"1","article-title":"Bilinear attention networks","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Kim"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00680"},{"key":"ref6","article-title":"Multi-modal learning with prior visual relation reasoning","volume-title":"Proc. ACM Multimedia (MM)","author":"Yang"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00206"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093297"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.121"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.41"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d16-1044"},{"key":"ref12","first-page":"1","article-title":"Hadamard product for low-rank bilinear pooling","volume-title":"Proc. ICLR","author":"Kim"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"key":"ref14","first-page":"8344","article-title":"Learning conditioned graph structures for interpretable visual question answering","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Norcliffe-Brown"},{"key":"ref15","article-title":"Scene graph reasoning with prior visual relationship for visual question answering","volume-title":"Proc. ACM Multimedia (MM)","author":"Yang"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00997"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2009916.2010010"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413679"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref21","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Lu"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3063611"},{"key":"ref23","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Ren"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00209"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01041"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_23"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01081"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00279"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-934613-03-3.50037-4"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2019.2932058"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2908982"},{"key":"ref32","article-title":"Deep compositional question answering with neural module networks","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Andreas"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2021.3125981"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_4"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1118"},{"key":"ref37","first-page":"1","article-title":"Compositional attention networks for machine reasoning","volume-title":"Proc. ICLR","author":"Hudson"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_29"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1142\/S0218001414500013"},{"key":"ref40","doi-asserted-by":"crossref","DOI":"10.1016\/j.patrec.2018.09.024","article-title":"Exploiting multi-layer graph factorization for multi-attributed graph matching","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Park"},{"key":"ref41","first-page":"3335","article-title":"Kergm: Kernelized graph matching","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Zhang"},{"key":"ref42","first-page":"3835","article-title":"Graph matching networks for learning the similarity of graph structured objects","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Li"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1304"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00284"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00315"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/p14-5010"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1116-0"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2936503"},{"key":"ref51","article-title":"Microsoft coco captions: Data collection and evaluation server","author":"Chen","year":"2015","journal-title":"arXiv:1504.00325"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01039"},{"key":"ref54","first-page":"1","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Chung"},{"key":"ref55","article-title":"A focused dynamic attention model for visual question answering","volume-title":"Proc. Eur. Conf. Comput. Vis. (ECCV)","author":"Ilievski"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220036"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00637"},{"key":"ref58","first-page":"1","article-title":"Reciprocal attention fusion for visual question answering","volume-title":"Proc. BMVC","author":"Farazi"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00678"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2817340"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019316"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018102"},{"key":"ref63","first-page":"1","article-title":"Learning to count objects in natural images for visual question answering","volume-title":"Proc. ICLR","author":"Zhang"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018997"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_26"},{"key":"ref66","article-title":"Graph reasoning networks for visual question answering","author":"Guo","year":"2019","journal-title":"arXiv:1907.09815"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10908444\/09705535.pdf?arnumber=9705535","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T18:38:55Z","timestamp":1764959935000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9705535\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":66,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2021.3135655","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}