{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T19:59:30Z","timestamp":1790798370911,"version":"4.1.0"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3655504","type":"journal-article","created":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T20:40:43Z","timestamp":1768941643000},"page":"4029-4041","source":"Crossref","is-referenced-by-count":0,"title":["Semantic-Spatial Subgraph-Based Relational Reasoning for Visual Question Answering"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-7472-4014","authenticated-orcid":false,"given":"Yike","family":"Wu","sequence":"first","affiliation":[{"name":"University of Technology Sydney","place":["Ultimo, NSW, Australia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9628-9563","authenticated-orcid":false,"given":"Jiahao","family":"Xia","sequence":"additional","affiliation":[{"name":"University of Technology Sydney","place":["Ultimo, NSW, Australia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2262-6261","authenticated-orcid":false,"given":"Jingcheng","family":"Ke","sequence":"additional","affiliation":[{"name":"National Tsing Hua University","place":["Hsinchu, Taiwan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9097-2318","authenticated-orcid":false,"given":"Chia-Wen","family":"Lin","sequence":"additional","affiliation":[{"name":"National Tsing Hua University","place":["Hsinchu, Taiwan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7240-3541","authenticated-orcid":false,"given":"Jian","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Technology Sydney","place":["Ultimo, NSW, Australia"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref2","first-page":"4974","article-title":"A simple neural network module for relational reasoning","volume":"30","author":"Santoro","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.344"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01039"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00209"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01041"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref8","article-title":"Compositional attention networks for machine reasoning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hudson","year":"2018"},{"key":"ref9","first-page":"1571","article-title":"Bilinear attention networks","volume":"31","author":"Kim","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350922"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00070"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i12.29315"},{"key":"ref15","first-page":"8344","article-title":"Learning conditioned graph structures for interpretable visual question answering","volume":"31","author":"Norcliffe-Brown","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3104937"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19997"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00504"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01973"},{"key":"ref20","first-page":"8017","article-title":"Subgraph neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Alsentzer","year":"2020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449822"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1021\/jm00106a046"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-007-0103-5"},{"key":"ref24","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref27","article-title":"Hierarchical question-image co-attention for visual question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu","year":"2016"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_1"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00637"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2972830"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01045"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.12"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_4"},{"key":"ref34","article-title":"Graph attention networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Velikovi","year":"2018"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01007"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/153"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3097171"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3120544"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3310332"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.20"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01879"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/bti1007"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_21"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00207"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_13"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428430"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01002"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00650"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"issue":"531","key":"ref52","article-title":"Learning by abstraction: The neural state machine","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Hudson","year":"2019"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3104937"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16452-1_37"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11359037.pdf?arnumber=11359037","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T19:23:58Z","timestamp":1790796238000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11359037\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3655504","relation":{},"ISSN":["1941-0077","1520-9210"],"issn-type":[{"value":"1941-0077","type":"electronic"},{"value":"1520-9210","type":"print"}],"subject":[],"published":{"date-parts":[[2026]]}}}