{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T12:33:12Z","timestamp":1769171592684,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T00:00:00Z","timestamp":1602460800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2020QNA5024"],"award-info":[{"award-number":["2020QNA5024"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004731","name":"Natural Science Foundation of Zhejiang Province","doi-asserted-by":"publisher","award":["LR19F020006"],"award-info":[{"award-number":["LR19F020006"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012659","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61625107, 61751209, 61836002"],"award-info":[{"award-number":["61625107, 61751209, 61836002"]}],"id":[{"id":"10.13039\/501100012659","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Program of China","award":["2018AAA0101900, 2018AAA0100603"],"award-info":[{"award-number":["2018AAA0101900, 2018AAA0100603"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,10,12]]},"DOI":"10.1145\/3394171.3413518","type":"proceedings-article","created":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T13:10:44Z","timestamp":1602508244000},"page":"4373-4382","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":51,"title":["DeVLBert"],"prefix":"10.1145","author":[{"given":"Shengyu","family":"Zhang","sequence":"first","affiliation":[{"name":"Zhejiang University, Hang Zhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tan","family":"Jiang","sequence":"additional","affiliation":[{"name":"ZhangJiang University, Hang Zhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tan","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Cheng Du, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kun","family":"Kuang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hang Zhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhou","family":"Zhao","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hang Zhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianke","family":"Zhu","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hang Zhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jin","family":"Yu","sequence":"additional","affiliation":[{"name":"Alibaba Group, Bei Jing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongxia","family":"Yang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hang Zhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Wu","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hang Zhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,10,12]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"crossref","unstructured":"Joshua D Angrist and J\u00f6rn-Steffen Pischke. 2008. Mostly harmless econometrics: An empiricist's companion. Princeton university press.  Joshua D Angrist and J\u00f6rn-Steffen Pischke. 2008. Mostly harmless econometrics: An empiricist's companion. Princeton university press.","DOI":"10.2307\/j.ctvcm4j72"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"e_1_3_2_2_4_1","first-page":"978","volume-title":"New York: Basic Books","author":"Aronow Peter M","year":"2020"},{"key":"e_1_3_2_2_5_1","volume-title":"7th International Conference on Learning Representations, ICLR 2019","author":"Bau David","year":"2019"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.3115\/1225403.1225421"},{"key":"e_1_3_2_2_7_1","volume-title":"Proceedings of the Thirty-First Conference on Uncertainty in Artificial Intelligence, UAI 2015","author":"Chalupka Krzysztof","year":"2015"},{"key":"e_1_3_2_2_8_1","unstructured":"Yen-Chun Chen Linjie Li Licheng Yu Ahmed El Kholy Faisal Ahmed Zhe Gan Yu Cheng and Jingjing Liu. 2019. UNITER: Learning UNiversal Image-TExt Representations. CoRR Vol. abs\/1909.11740 (2019). http:\/\/arxiv.org\/abs\/1909.11740  Yen-Chun Chen Linjie Li Licheng Yu Ahmed El Kholy Faisal Ahmed Zhe Gan Yu Cheng and Jingjing Liu. 2019. UNITER: Learning UNiversal Image-TExt Representations. CoRR Vol. abs\/1909.11740 (2019). http:\/\/arxiv.org\/abs\/1909.11740"},{"key":"e_1_3_2_2_9_1","volume-title":"Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019","author":"Conneau Alexis","year":"2019"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_2_11_1","first-page":"19","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019","volume":"1","author":"Devlin Jacob","year":"2019"},{"key":"e_1_3_2_2_12_1","volume-title":"Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019","author":"Dong Li","year":"2019"},{"key":"e_1_3_2_2_13_1","volume-title":"Proceedings of the 34th International Conference on Machine Learning, ICML 2017","author":"Gehring Jonas","year":"2017"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.320"},{"key":"e_1_3_2_2_16_1","volume-title":"6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings. https:\/\/openreview.net\/forum?id=BJE-4xW0W","author":"Kocaoglu Murat","year":"2018"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_2_2_18_1","volume-title":"Advances in Neural Information Processing Systems 25: 26th Annual Conference on Neural Information Processing Systems 2012. Proceedings of a meeting held","author":"Krizhevsky Alex","year":"2012"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220082"},{"key":"e_1_3_2_2_20_1","unstructured":"Li Lian Geng Zhi Xu Lei Zhang Kun Liao Beishui Huang Huaxin Ding Peng Miao Wang Jiang Zhichao Kuang Kun. 2020. Causal Inference. Engineering (2020).  Li Lian Geng Zhi Xu Lei Zhang Kun Liao Beishui Huang Huaxin Ding Peng Miao Wang Jiang Zhichao Kuang Kun. 2020. Causal Inference. Engineering (2020)."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.351"},{"key":"e_1_3_2_2_22_1","volume-title":"Munich","author":"Lee Kuang-Huei","year":"2018"},{"key":"e_1_3_2_2_23_1","unstructured":"Gen Li Nan Duan Yuejian Fang Daxin Jiang and Ming Zhou. 2019 a. Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training. CoRR Vol. abs\/1908.06066 (2019). http:\/\/arxiv.org\/abs\/1908.06066  Gen Li Nan Duan Yuejian Fang Daxin Jiang and Ming Zhou. 2019 a. Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training. CoRR Vol. abs\/1908.06066 (2019). http:\/\/arxiv.org\/abs\/1908.06066"},{"key":"e_1_3_2_2_24_1","unstructured":"Liunian Harold Li Mark Yatskar Da Yin Cho-Jui Hsieh and Kai-Wei Chang. 2019 b. VisualBERT: A Simple and Performant Baseline for Vision and Language. CoRR Vol. abs\/1908.03557 (2019). http:\/\/arxiv.org\/abs\/1908.03557  Liunian Harold Li Mark Yatskar Da Yin Cho-Jui Hsieh and Kai-Wei Chang. 2019 b. VisualBERT: A Simple and Performant Baseline for Vision and Language. CoRR Vol. abs\/1908.03557 (2019). http:\/\/arxiv.org\/abs\/1908.03557"},{"key":"e_1_3_2_2_25_1","unstructured":"Junyang Lin An Yang Yichang Zhang Jie Liu Jingren Zhou and Hongxia Yang. 2020. InterBERT: Vision-and-Language Interaction for Multi-modal Pretraining. CoRR Vol. abs\/2003.13198 (2020). https:\/\/arxiv.org\/abs\/2003.13198  Junyang Lin An Yang Yichang Zhang Jie Liu Jingren Zhou and Hongxia Yang. 2020. InterBERT: Vision-and-Language Interaction for Multi-modal Pretraining. CoRR Vol. abs\/2003.13198 (2020). https:\/\/arxiv.org\/abs\/2003.13198"},{"key":"e_1_3_2_2_26_1","volume-title":"Zurich, Switzerland","author":"Lin Tsung-Yi","year":"2014"},{"key":"e_1_3_2_2_27_1","unstructured":"Yinhan Liu Myle Ott Naman Goyal Jingfei Du Mandar Joshi Danqi Chen Omer Levy Mike Lewis Luke Zettlemoyer and Veselin Stoyanov. 2019. RoBERTa: A Robustly Optimized BERT Pretraining Approach. CoRR Vol. abs\/1907.11692 (2019). http:\/\/arxiv.org\/abs\/1907.11692  Yinhan Liu Myle Ott Naman Goyal Jingfei Du Mandar Joshi Danqi Chen Omer Levy Mike Lewis Luke Zettlemoyer and Veselin Stoyanov. 2019. RoBERTa: A Robustly Optimized BERT Pretraining Approach. CoRR Vol. abs\/1907.11692 (2019). http:\/\/arxiv.org\/abs\/1907.11692"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.14"},{"key":"e_1_3_2_2_29_1","volume-title":"Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019","author":"Lu Jiasen","year":"2019"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1017\/S0266466603004109"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1212"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"crossref","unstructured":"Yulei Niu Kaihua Tang Hanwang Zhang Zhiwu Lu Xian-Sheng Hua and Ji-Rong Wen. 2020. Counterfactual VQA: A Cause-Effect Look at Language Bias. arXiv preprint arXiv:2006.04315 (2020).  Yulei Niu Kaihua Tang Hanwang Zhang Zhiwu Lu Xian-Sheng Hua and Ji-Rong Wen. 2020. Counterfactual VQA: A Cause-Effect Look at Language Bias. arXiv preprint arXiv:2006.04315 (2020).","DOI":"10.1109\/CVPR46437.2021.01251"},{"key":"e_1_3_2_2_33_1","unstructured":"Adam Paszke Sam Gross Soumith Chintala Gregory Chanan Edward Yang Zachary DeVito Zeming Lin Alban Desmaison Luca Antiga and Adam Lerer. 2017. Automatic differentiation in PyTorch. In NIPS-W.  Adam Paszke Sam Gross Soumith Chintala Gregory Chanan Edward Yang Zachary DeVito Zeming Lin Alban Desmaison Luca Antiga and Adam Lerer. 2017. Automatic differentiation in PyTorch. In NIPS-W."},{"key":"e_1_3_2_2_34_1","unstructured":"Judea Pearl Madelyn Glymour and Nicholas P Jewell. 2016. Causal inference in statistics: A primer. John Wiley & Sons.  Judea Pearl Madelyn Glymour and Nicholas P Jewell. 2016. Causal inference in statistics: A primer. John Wiley & Sons."},{"key":"e_1_3_2_2_35_1","unstructured":"Jiaxin Qi Yulei Niu Jianqiang Huang and Hanwang Zhang. 2019. Two Causal Principles for Improving Visual Dialog. CoRR Vol. abs\/1911.10496 (2019). http:\/\/arxiv.org\/abs\/1911.10496  Jiaxin Qi Yulei Niu Jianqiang Huang and Hanwang Zhang. 2019. Two Causal Principles for Improving Visual Dialog. CoRR Vol. abs\/1911.10496 (2019). http:\/\/arxiv.org\/abs\/1911.10496"},{"key":"e_1_3_2_2_36_1","volume-title":"Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015","author":"Ren Shaoqing","year":"2015"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1014"},{"key":"e_1_3_2_2_39_1","volume-title":"3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings. http:\/\/arxiv.org\/abs\/1409","author":"Simonyan Karen","year":"2015"},{"key":"e_1_3_2_2_40_1","volume-title":"Proceedings of the 36th International Conference on Machine Learning, ICML 2019","author":"Song Kaitao","year":"2019"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.5555\/2627435.2670313"},{"key":"e_1_3_2_2_42_1","volume-title":"8th International Conference on Learning Representations, ICLR 2020","author":"Su Weijie","year":"2020"},{"key":"e_1_3_2_2_43_1","unstructured":"Chen Sun Fabien Baradel Kevin Murphy and Cordelia Schmid. 2019 a. Contrastive Bidirectional Transformer for Temporal Representation Learning. CoRR Vol. abs\/1906.05743 (2019). http:\/\/arxiv.org\/abs\/1906.05743  Chen Sun Fabien Baradel Kevin Murphy and Cordelia Schmid. 2019 a. Contrastive Bidirectional Transformer for Temporal Representation Learning. CoRR Vol. abs\/1906.05743 (2019). http:\/\/arxiv.org\/abs\/1906.05743"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"e_1_3_2_2_46_1","unstructured":"Kaihua Tang Yulei Niu Jianqiang Huang Jiaxin Shi and Hanwang Zhang. 2020. Unbiased Scene Graph Generation from Biased Training. CoRR Vol. abs\/2002.11949 (2020). https:\/\/arxiv.org\/abs\/2002.11949  Kaihua Tang Yulei Niu Jianqiang Huang Jiaxin Shi and Hanwang Zhang. 2020. Unbiased Scene Graph Generation from Biased Training. CoRR Vol. abs\/2002.11949 (2020). https:\/\/arxiv.org\/abs\/2002.11949"},{"key":"e_1_3_2_2_47_1","volume-title":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017","author":"Vaswani Ashish","year":"2017"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.541"},{"key":"e_1_3_2_2_49_1","unstructured":"Tan Wang Jianqiang Huang Hanwang Zhang and Qianru Sun. 2020. Visual Commonsense R-CNN. CoRR Vol. abs\/2002.12204 (2020). https:\/\/arxiv.org\/abs\/2002.12204  Tan Wang Jianqiang Huang Hanwang Zhang and Qianru Sun. 2020. Visual Commonsense R-CNN. CoRR Vol. abs\/2002.12204 (2020). https:\/\/arxiv.org\/abs\/2002.12204"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1488"},{"key":"e_1_3_2_2_51_1","volume-title":"Proceedings of the 32nd International Conference on Machine Learning, ICML 2015","author":"Xu Kelvin","year":"2015"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00232"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"crossref","unstructured":"Zekun Yang and Tianlin Liu. 2020. Causally Denoise Word Embeddings Using Half-Sibling Regression.. In Association for the Advancement of Artificial Intelligence.  Zekun Yang and Tianlin Liu. 2020. Causally Denoise Word Embeddings Using Half-Sibling Regression.. In Association for the Advancement of Artificial Intelligence.","DOI":"10.1609\/aaai.v34i05.6485"}],"event":{"name":"MM '20: The 28th ACM International Conference on Multimedia","location":"Seattle WA USA","acronym":"MM '20","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 28th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394171.3413518","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3394171.3413518","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:47:13Z","timestamp":1750193233000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394171.3413518"}},"subtitle":["Learning Deconfounded Visio-Linguistic Representations"],"short-title":[],"issued":{"date-parts":[[2020,10,12]]},"references-count":53,"alternative-id":["10.1145\/3394171.3413518","10.1145\/3394171"],"URL":"https:\/\/doi.org\/10.1145\/3394171.3413518","relation":{},"subject":[],"published":{"date-parts":[[2020,10,12]]},"assertion":[{"value":"2020-10-12","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}