{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T17:09:27Z","timestamp":1780765767270,"version":"3.54.1"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tpami.2023.3290012","type":"journal-article","created":{"date-parts":[[2023,6,27]],"date-time":"2023-06-27T17:35:14Z","timestamp":1687887314000},"page":"1-16","source":"Crossref","is-referenced-by-count":34,"title":["Counterfactual Samples Synthesizing and Training for Robust Visual Question Answering"],"prefix":"10.1109","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6148-9709","authenticated-orcid":false,"given":"Long","family":"Chen","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Kowloon, Hong Kong SAR"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9628-1940","authenticated-orcid":false,"given":"Yuhang","family":"Zheng","sequence":"additional","affiliation":[{"name":"College of Computer Science, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6332-3382","authenticated-orcid":false,"given":"Yulei","family":"Niu","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Columbia University, New York, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7374-8739","authenticated-orcid":false,"given":"Hanwang","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Xiao","sequence":"additional","affiliation":[{"name":"College of Computer Science, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1418"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.317"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1203"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.542"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00522"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00280"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.12"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d16-1044"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01081"},{"key":"ref15","article-title":"Overcoming language priors in visual question answering with adversarial regularization","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","volume":"31","author":"Ramakrishnan"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-1801"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1084"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00115"},{"key":"ref20","article-title":"RUBi: Reducing unimodal biases in visual question answering","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","volume":"32","author":"Cadene"},{"key":"ref21","article-title":"Simple but effective techniques to reduce biases","author":"Mahabadi","year":"2019"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01251"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00161"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/371"},{"key":"ref25","first-page":"18661","article-title":"Supervised contrastive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Khosla"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00471"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.265"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00163"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/151"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref32","article-title":"Vl-BERT: Pre-training of generic visual-linguistic representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Su"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_44"},{"key":"ref36","first-page":"16292","article-title":"Introspective distillation for robust question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Niu"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12272"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11197"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00043"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00268"},{"key":"ref41","first-page":"8604","article-title":"Self-critical reasoning for robust visual question answering","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Wu"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00681"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00971"},{"key":"ref45","article-title":"Question-conditioned counterfactual image generation for VQA","author":"Pan","year":"2019"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.63"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1045"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.512"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_6"},{"key":"ref50","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"issue":"1","key":"ref53","first-page":"411","article-title":"spaCy 2: Natural language understanding with bloom embeddings, convolutional neural networks and incremental parsing","volume":"7","author":"Honnibal","year":"2017","journal-title":"To appear"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref55","article-title":"Attention is not explanation","volume-title":"Proc. Annu. Meeting Assoc. Comput. Linguistics","author":"Jain"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01045"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00209"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01006"},{"key":"ref60","first-page":"1397","article-title":"Unshuffling data for improved generalization","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Teney"},{"key":"ref61","first-page":"407","article-title":"On the value of out-of-distribution testing: An example of goodharts law","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Teney"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref63","article-title":"Bilinear attention networks","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Kim"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/4359286\/10164132.pdf?arnumber=10164132","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T03:51:26Z","timestamp":1710388286000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10164132\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3290012","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}