{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:34:15Z","timestamp":1787013255831,"version":"build-2736575974"},"reference-count":66,"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":[{"name":"National Key Research and Development Program of China","award":["2022ZD0118802"],"award-info":[{"award-number":["2022ZD0118802"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U20B2064"],"award-info":[{"award-number":["U20B2064"]}],"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":["62372233"],"award-info":[{"award-number":["62372233"]}],"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.2024.3355640","type":"journal-article","created":{"date-parts":[[2024,1,26]],"date-time":"2024-01-26T13:55:44Z","timestamp":1706277344000},"page":"6648-6662","source":"Crossref","is-referenced-by-count":23,"title":["Unbiased Visual Question Answering by Leveraging Instrumental Variable"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9615-5757","authenticated-orcid":false,"given":"Yonghua","family":"Pan","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0903-9131","authenticated-orcid":false,"given":"Jing","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2964-426X","authenticated-orcid":false,"given":"Lu","family":"Jin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5341-5985","authenticated-orcid":false,"given":"Zechao","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3026892"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00172"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3169065"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2972830"},{"key":"ref7","article-title":"VALOR: Vision-audio-language omni-perception pretraining model and dataset","author":"Chen","year":"2023"},{"key":"ref8","article-title":"SimVLM: Simple visual language model pretraining with weak supervision","author":"Wang","year":"2022","journal-title":"Proc. Int. Conf. Learn. Representations"},{"key":"ref9","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Adv. Neural Inf. Process","author":"Lu","year":"2019"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2992888"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00688"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3275874"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00522"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00280"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/151"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00419"},{"key":"ref21","first-page":"841","article-title":"RUBi: Reducing unimodal biases for visual question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Cadene","year":"2019"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1418"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01251"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00160"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00161"},{"key":"ref26","first-page":"3784","article-title":"Debiased visual question answering from feature and sample perspectives","volume-title":"Proc. Adv. Neural Inf. Process.","author":"Wen","year":"2021"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01006"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_34"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01081"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.63"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3487042"},{"key":"ref32","first-page":"1","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2014","journal-title":"Proc. Adv. Neural Inf. Process. Deep Learn. Representation Learn. Workshop"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00377"},{"key":"ref34","first-page":"655","article-title":"Causal intervention for weakly-supervised semantic segmentation","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process.","author":"Zhang","year":"2020"},{"key":"ref35","volume-title":"Causal Inference in Statistics: A Primer","author":"Glymour","year":"2016"},{"key":"ref36","first-page":"1462","article-title":"A causal view of compositional zero-shot recognition","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process.","author":"Atzmon","year":"2020"},{"key":"ref37","first-page":"289","article-title":"A causal view on robustness of neural networks","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process.","volume":"33","author":"Zhang","year":"2020"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3058954"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.14"},{"key":"ref40","article-title":"Invariant risk minimization","author":"Arjovsky","year":"2019"},{"key":"ref41","first-page":"21720","article-title":"Kernelized heterogeneous risk minimization","volume-title":"Proc. Adv. Neural Inf. Process.","author":"Liu","year":"2021"},{"key":"ref42","first-page":"145","article-title":"Invariant risk minimization games","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"119","author":"Ahuja","year":"2020"},{"key":"ref43","first-page":"6804","article-title":"Heterogeneous risk minimization","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Liu","year":"2021"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107383"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00533"},{"key":"ref46","first-page":"8765","article-title":"Debiased contrastive learning","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process.","author":"Chuang","year":"2020"},{"key":"ref47","first-page":"18225","article-title":"Self-supervised learning disentangled group representation as feature","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang","year":"2021"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1515\/9781400829828"},{"key":"ref49","first-page":"1414","article-title":"Deep IV: A flexible approach for counterfactual prediction","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hartford","year":"2017"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3494568"},{"key":"ref51","first-page":"4096","article-title":"Valid causal inference with (some) invalid instruments","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hartford","year":"2021"},{"key":"ref52","first-page":"398","article-title":"IVY: Instrumental variable synthesis for causal inference","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Kuang","year":"2020"},{"key":"ref53","article-title":"Adversarial visual robustness by causal intervention","author":"Tang","year":"2021"},{"key":"ref54","first-page":"1","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014","journal-title":"Proc. Adv. Neural Inf. Process. Deep Learn. Representation Learn. Workshop"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref57","first-page":"1189","article-title":"Self-paced learning for latent variable models","volume-title":"Proc. Adv. Neural Inf. Process.","author":"Kumar","year":"2010"},{"key":"ref58","first-page":"2078","article-title":"Self-paced learning with diversity","volume-title":"Proc. 27th Int. Conf. Neural Inf. Process.","author":"Jiang","year":"2014"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref60","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref61","first-page":"1541","article-title":"Overcoming language priors in visual question answering with adversarial regularization","volume-title":"Proc. Adv. Neural Inf. Process.","author":"Ramakrishnan","year":"2018"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_6"},{"key":"ref63","first-page":"16292","article-title":"Introspective distillation for robust question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Niu","year":"2021"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01124"},{"key":"ref65","first-page":"407","article-title":"On the value of out-of-distribution testing: An example of goodharts law","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process.","volume":"33","author":"Teney","year":"2020"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00145"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10415346.pdf?arnumber=10415346","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,11]],"date-time":"2024-04-11T15:07:30Z","timestamp":1712848050000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10415346\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3355640","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}