{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T16:23:34Z","timestamp":1776529414495,"version":"3.51.2"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":["61976159"],"award-info":[{"award-number":["61976159"]}],"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":["62133011"],"award-info":[{"award-number":["62133011"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Innovation Action Project of Science and Technology","award":["20511100700"],"award-info":[{"award-number":["20511100700"]}]},{"name":"Shanghai Municipal Science and Technology Major Project","award":["2021SHZDZX0100"],"award-info":[{"award-number":["2021SHZDZX0100"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2023.3279691","type":"journal-article","created":{"date-parts":[[2023,5,24]],"date-time":"2023-05-24T17:43:50Z","timestamp":1684950230000},"page":"1295-1305","source":"Crossref","is-referenced-by-count":11,"title":["Multi-Modal Structure-Embedding Graph Transformer for Visual Commonsense Reasoning"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3835-4627","authenticated-orcid":false,"given":"Jian","family":"Zhu","sequence":"first","affiliation":[{"name":"Department of Computer Science and Technology, Key Laboratory of Embedded System and Service Computing (Ministry of Education), Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9999-4871","authenticated-orcid":false,"given":"Hanli","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Key Laboratory of Embedded System and Service Computing (Ministry of Education), Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3193-6269","authenticated-orcid":false,"given":"Bin","family":"He","sequence":"additional","affiliation":[{"name":"Frontiers Science Center for Intelligent Autonomous Systems, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2021.3079278"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3097180"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2995278"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2991504"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2979010"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2990074"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3058555"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00688"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2991866"},{"key":"ref10","first-page":"15615","article-title":"TAB-VCR: Tags and attributes based VCR baselines","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lin","year":"2019"},{"key":"ref11","first-page":"5669","article-title":"Connective cognition network for directional visual commonsense reasoning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wu","year":"2019"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3091882"},{"key":"ref13","first-page":"2769","article-title":"Heterogeneous graph learning for visual commonsense reasoning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yu","year":"2019"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532038"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3025110"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3028207"},{"key":"ref18","article-title":"VisualBERT: A simple and performant baseline for vision and language","author":"Li","year":"2019"},{"key":"ref19","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Su","year":"2020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.202"},{"key":"ref22","first-page":"1931","article-title":"Unifying vision-and-language tasks via text generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cho","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107408"},{"key":"ref24","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.611"},{"key":"ref27","first-page":"1691","article-title":"Generative pretraining from pixels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref29","article-title":"Gophormer: Ego-Graph Transformer for Node Classification","author":"Zhao","year":"2021"},{"key":"ref30","first-page":"28877","article-title":"Do transformers really perform bad for graph representation?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ying","year":"2021"},{"key":"ref31","article-title":"OGBLSC: A large-scale challenge for machine learning on graphs","volume-title":"Proc. NeurIPS D&B","author":"Hu","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref34","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2014"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1152"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_44"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref38","article-title":"Hadamard product for low-rank bilinear pooling","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kim","year":"2017"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01077"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16428"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3286259"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10132535.pdf?arnumber=10132535","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:48:24Z","timestamp":1705690104000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10132535\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3279691","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}