{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,12]],"date-time":"2026-04-12T00:54:30Z","timestamp":1775955270118,"version":"3.50.1"},"reference-count":57,"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":["62172261"],"award-info":[{"award-number":["62172261"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2023.3275874","type":"journal-article","created":{"date-parts":[[2023,5,12]],"date-time":"2023-05-12T17:44:40Z","timestamp":1683913480000},"page":"1065-1075","source":"Crossref","is-referenced-by-count":14,"title":["Learning to Agree on Vision Attention for Visual Commonsense Reasoning"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4694-1231","authenticated-orcid":false,"given":"Zhenyang","family":"Li","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Shandong University, Qingdao, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8691-5372","authenticated-orcid":false,"given":"Yangyang","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Computing, National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0595-6856","authenticated-orcid":false,"given":"Kejie","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Shandong University, Qingdao, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4547-3982","authenticated-orcid":false,"given":"Fan","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computing, National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1476-0273","authenticated-orcid":false,"given":"Liqiang","family":"Nie","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4846-2015","authenticated-orcid":false,"given":"Mohan","family":"Kankanhalli","sequence":"additional","affiliation":[{"name":"School of Computing, National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"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.2019.00688"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3565266"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3128322"},{"key":"ref6","first-page":"2765","article-title":"Heterogeneous\n      graph learning for visual commonsense reasoning","volume-title":"Proc. Adv.\n      Neural Inf. Process. Syst.","author":"Yu","year":"2019"},{"key":"ref7","first-page":"15589","article-title":"TAB-VCR: Tags\n      and attributes based VCR baselines","volume-title":"Proc. Adv. Neural Inf.\n      Process. Syst.","author":"Lin","year":"2019"},{"key":"ref8","first-page":"5670","article-title":"Connective\n      cognition network for directional visual commonsense reasoning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wu","year":"2019"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"ref10","first-page":"13","article-title":"Vilbert:\n      Pretraining task-agnostic visiolinguistic representations for vision-and-language\n      tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu","year":"2019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref12","first-page":"1","article-title":"VL-BERT: Pre-training of generic visual-linguistic\n      representations","volume-title":"Proc. Int. Conf. Learn.\n      Representations","author":"Su","year":"2020"},{"key":"ref13","first-page":"6616","article-title":"Large-scale adversarial training for vision-and-language\n      representation learning","volume-title":"Proc. Adv. Neural Inf. Process.\n      Syst.","author":"Gan","year":"2020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.540"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3091882"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475328"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107408"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2991866"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.763"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01589"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01073"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.499"},{"key":"ref23","first-page":"289","article-title":"Hierarchical\n      question-image co-attention for visual question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu","year":"2016"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00444"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12272"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00043"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532038"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00355"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7005"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.202"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01278"},{"key":"ref36","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning\n      with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process.\n      Syst.","author":"Li","year":"2021"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/762"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.707"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3046855"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1561\/1500000016"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/582415.582418"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s10791-009-9124-x"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1406.1078"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(89)90020-8"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123377"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_44"},{"key":"ref50","first-page":"1","article-title":"Hadamard product for low-rank bilinear\n     pooling","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kim","year":"2017"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548187"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2995278"},{"key":"ref54","article-title":"Googles neural machine translation system: Bridging the\n      gap between human and machine translation","author":"Wu","year":"2016"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0987-1"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455008"},{"key":"ref57","first-page":"1","article-title":"Adam: A method for\n      stochastic optimization","volume-title":"Proc. Int. Conf. Learn.\n      Representations","author":"Kingma","year":"2015"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10123978.pdf?arnumber=10123978","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,25]],"date-time":"2024-07-25T17:29:51Z","timestamp":1721928591000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10123978\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3275874","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}