{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T18:28:06Z","timestamp":1780597686323,"version":"3.54.1"},"reference-count":56,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62207011"],"award-info":[{"award-number":["62207011"]}],"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":["62377009"],"award-info":[{"award-number":["62377009"]}],"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":["62407013"],"award-info":[{"award-number":["62407013"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of Hubei Province of China","award":["2025AFB653"],"award-info":[{"award-number":["2025AFB653"]}]},{"name":"Hubei Provincial Key R&D Program","award":["2025BAB011"],"award-info":[{"award-number":["2025BAB011"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3651122","type":"journal-article","created":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T18:36:32Z","timestamp":1767724592000},"page":"3228-3241","source":"Crossref","is-referenced-by-count":1,"title":["Integrating Object Interaction Self-Attention and GAN-Based Debiasing for Visual Question Answering"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0443-0094","authenticated-orcid":false,"given":"Zhifei","family":"Li","sequence":"first","affiliation":[{"name":"School of Computer Science, Hubei University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2034-3473","authenticated-orcid":false,"given":"Feng","family":"Qiu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Hubei University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2271-4540","authenticated-orcid":false,"given":"Yiran","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Hubei University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2988-2525","authenticated-orcid":false,"given":"Yujing","family":"Xia","sequence":"additional","affiliation":[{"name":"School of Computer Science, Hubei University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7784-7689","authenticated-orcid":false,"given":"Kui","family":"Xiao","sequence":"additional","affiliation":[{"name":"School of Computer Science, Hubei University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8952-215X","authenticated-orcid":false,"given":"Miao","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Hubei University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6045-5208","authenticated-orcid":false,"given":"Yan","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Hubei University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1203"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.542"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01006"},{"key":"ref6","first-page":"839","article-title":"RUBi: Reducing unimodal biases for visual question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cadne","year":"2019"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1418"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00161"},{"key":"ref9","first-page":"1548","article-title":"Overcoming language priors in visual question answering with adversarial regularization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ramakrishnan","year":"2018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01251"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00522"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref13","article-title":"Distilling the knowledge in a neural network","volume-title":"Stat","volume":"1050","author":"Hinton","year":"2015"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00380"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref17","first-page":"1571","article-title":"Bilinear attention networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kim","year":"2018"},{"key":"ref18","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu","year":"2019"},{"key":"ref19","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Su","year":"2020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01081"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.63"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.265"},{"key":"ref24","first-page":"407","article-title":"On the value of out-of-distribution testing: An example of Goodharts law","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Teney","year":"2020"},{"key":"ref25","first-page":"3784","article-title":"Debiased visual question answering from feature and sample perspectives","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"2021","author":"Wen"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/151"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_6"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.432"},{"key":"ref29","first-page":"5721","article-title":"Overcoming language priors in visual question answering via distinguishing superficially similar instances","volume-title":"Proc. 29th Int. Conf. Comput. Linguistics","author":"Wu","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01124"},{"key":"ref31","first-page":"16292","article-title":"Introspective distillation for robust question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Niu","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_2"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.311"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3292597"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3380259"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3355640"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12272"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00043"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.10.001"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00915"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00268"},{"key":"ref44","first-page":"8601","article-title":"Self-Critical reasoning for robust visual question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wu","year":"2019"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351065"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3023438"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3147385"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00260"},{"key":"ref49","first-page":"1060","article-title":"Generative adversarial text to image synthesis","volume-title":"Proc. 33nd Int. Conf. Mach. Learn.","author":"Reed","year":"2016"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01605"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref52","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Tan","year":"2019"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16234"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2014.2320500"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6776"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3128322"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11329525.pdf?arnumber=11329525","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T19:50:25Z","timestamp":1777319425000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11329525\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3651122","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}