{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:26:13Z","timestamp":1772907973033,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":28,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819962068","type":"print"},{"value":"9789819962075","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-981-99-6207-5_4","type":"book-chapter","created":{"date-parts":[[2023,9,19]],"date-time":"2023-09-19T08:45:34Z","timestamp":1695113134000},"page":"58-71","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Overcoming Language Priors with\u00a0Counterfactual Inference for\u00a0Visual Question Answering"],"prefix":"10.1007","author":[{"given":"Zhibo","family":"Ren","sequence":"first","affiliation":[]},{"given":"Huizhen","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Muhua","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Yichao","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Tong","family":"Xiao","sequence":"additional","affiliation":[]},{"given":"Jingbo","family":"Zhu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,9,20]]},"reference":[{"key":"4_CR1","doi-asserted-by":"crossref","unstructured":"Agrawal, A., Batra, D., Parikh, D.: Analyzing the behavior of visual question answering models. In: Proceedings of EMNLP, pp. 1955\u20131960 (2016)","DOI":"10.18653\/v1\/D16-1203"},{"key":"4_CR2","doi-asserted-by":"crossref","unstructured":"Agrawal, A., Batra, D., Parikh, D., Kembhavi, A.: Don\u2019t just assume; look and answer: overcoming priors for visual question answering. In: Proceedings of CVPR, pp. 4971\u20134980 (2018)","DOI":"10.1109\/CVPR.2018.00522"},{"key":"4_CR3","doi-asserted-by":"crossref","unstructured":"Agrawal, V., Shetty, R., Fritz, M.: Towards causal VQA: revealing and reducing spurious correlations by invariant and covariant semantic editing. In: Proceedings of CVPR, pp. 9690\u20139698 (2019)","DOI":"10.1109\/CVPR42600.2020.00971"},{"key":"4_CR4","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: Proceedings of CVPR, pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"4_CR5","doi-asserted-by":"crossref","unstructured":"Andreas, J., Rohrbach, M., Darrell, T., Klein, D.: Neural module networks. In: Proceedings of CVPR, pp. 39\u201348 (2016)","DOI":"10.1109\/CVPR.2016.12"},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: Proceedings of ICCV, pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"4_CR7","unstructured":"Cad\u00e8ne, R., Dancette, C., Ben-younes, H., Cord, M., Parikh, D.: Rubi: reducing unimodal biases for visual question answering. In: Proceedings of NeurIPS, pp. 839\u2013850 (2019)"},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"Chen, L., Yan, X., Xiao, J., Zhang, H., Pu, S., Zhuang, Y.: Counterfactual samples synthesizing for robust visual question answering. In: Proceedings of CVPR, pp. 10797\u201310806 (2020)","DOI":"10.1109\/CVPR42600.2020.01081"},{"key":"4_CR9","doi-asserted-by":"crossref","unstructured":"Clark, C., Yatskar, M., Zettlemoyer, L.: Don\u2019t take the easy way out: ensemble based methods for avoiding known dataset biases. In: Proceedings of EMNLP-IJCNLP, pp. 4067\u20134080 (2019)","DOI":"10.18653\/v1\/D19-1418"},{"key":"4_CR10","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1016\/j.cviu.2017.10.001","volume":"163","author":"A Das","year":"2017","unstructured":"Das, A., Agrawal, H., Zitnick, L., Parikh, D., Batra, D.: Human attention in visual question answering: do humans and deep networks look at the same regions? Comput. Vis. Image Underst. 163, 90\u2013100 (2017)","journal-title":"Comput. Vis. Image Underst."},{"key":"4_CR11","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL-HLT, pp. 4171\u20134186 (2019)"},{"key":"4_CR12","doi-asserted-by":"crossref","unstructured":"Gokhale, T., Banerjee, P., Baral, C., Yang, Y.: MUTANT: a training paradigm for out-of-distribution generalization in visual question answering. In: Proceedings of EMNLP, pp. 878\u2013892 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.63"},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"Goyal, Y., Khot, T., Summers-Stay, D., Batra, D., Parikh, D.: Making the V in VQA matter: elevating the role of image understanding in visual question answering. In: Proceedings of CVPR, pp. 6325\u20136334 (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"4_CR14","doi-asserted-by":"crossref","unstructured":"Jing, C., Wu, Y., Zhang, X., Jia, Y., Wu, Q.: Overcoming language priors in VQA via decomposed linguistic representations. In: Proceedings of AAAI, pp. 11181\u201311188 (2020)","DOI":"10.1609\/aaai.v34i07.6776"},{"key":"4_CR15","doi-asserted-by":"crossref","unstructured":"Kafle, K., Kanan, C.: An analysis of visual question answering algorithms. In: Proceedings of CVPR, pp. 1983\u20131991 (2017)","DOI":"10.1109\/ICCV.2017.217"},{"key":"4_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1007\/978-3-030-58601-0_2","volume-title":"Computer Vision \u2013 ECCV 2020","author":"G KV","year":"2020","unstructured":"KV, G., Mittal, A.: Reducing language biases in visual question answering with visually-grounded question encoder. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12358, pp. 18\u201334. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58601-0_2"},{"key":"4_CR17","doi-asserted-by":"crossref","unstructured":"Liang, Z., Jiang, W., Hu, H., Zhu, J.: Learning to contrast the counterfactual samples for robust visual question answering. In: Proceedings of EMNLP, pp. 3285\u20133292 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.265"},{"key":"4_CR18","doi-asserted-by":"crossref","unstructured":"Niu, Y., Tang, K., Zhang, H., Lu, Z., Hua, X., Wen, J.: Counterfactual VQA: a cause-effect look at language bias. In: Proceedings of CVPR, pp. 12700\u201312710 (2021)","DOI":"10.1109\/CVPR46437.2021.01251"},{"key":"4_CR19","unstructured":"Pan, J., Goyal, Y., Lee, S.: Question-conditional counterfactual image generation for VQA. arXiv, preprint arXiv:1911.06352 (2019)"},{"key":"4_CR20","doi-asserted-by":"crossref","unstructured":"Park, D.H., et al.: Multimodal explanations: justifying decisions and pointing to the evidence. In: Proceedings of CVPR, pp. 8779\u20138788 (2018)","DOI":"10.1109\/CVPR.2018.00915"},{"key":"4_CR21","unstructured":"Ramakrishnan, S., Agrawal, A., Lee, S.: Overcoming language priors in visual question answering with adversarial regularization. In: Proceedings of NeurIPS, pp. 1548\u20131558 (2018)"},{"key":"4_CR22","unstructured":"Ren, S., He, K., Girshick, R.B., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Proceedings of NeurIPS, pp. 91\u201399 (2015)"},{"key":"4_CR23","doi-asserted-by":"crossref","unstructured":"Teney, D., Abbasnejad, E., van den Hengel, A.: Unshuffling data for improved generalization in visual question answering. In: Proceedings of ICCV, pp. 1397\u20131407 (2021)","DOI":"10.1109\/ICCV48922.2021.00145"},{"key":"4_CR24","unstructured":"Teney, D., Abbasnejad, E., Kafle, K., Shrestha, R., Kanan, C., van den Hengel, A.: On the value of out-of-distribution testing: an example of goodhart\u2019s law. In: Proceedings of NeurIPS (2020)"},{"key":"4_CR25","doi-asserted-by":"crossref","unstructured":"Wu, Q., Wang, P., Shen, C., Dick, A.R., van den Hengel, A.: Ask me anything: free-form visual question answering based on knowledge from external sources. In: Proceedings of CVPR, pp. 4622\u20134630 (2016)","DOI":"10.1109\/CVPR.2016.500"},{"key":"4_CR26","doi-asserted-by":"crossref","unstructured":"Yang, Z., He, X., Gao, J., Deng, L., Smola, A.J.: Stacked attention networks for image question answering. In: Proceedings of CVPR, pp. 21\u201329 (2016)","DOI":"10.1109\/CVPR.2016.10"},{"key":"4_CR27","doi-asserted-by":"crossref","unstructured":"Yu, Z., Yu, J., Cui, Y., Tao, D., Tian, Q.: Deep modular co-attention networks for visual question answering. In: Proceedings of CVPR, pp. 6281\u20136290 (2019)","DOI":"10.1109\/CVPR.2019.00644"},{"key":"4_CR28","doi-asserted-by":"crossref","unstructured":"Zhu, X., Mao, Z., Liu, C., Zhang, P., Wang, B., Zhang, Y.: Overcoming language priors with self-supervised learning for visual question answering. In: Proceedings of IJCAI, pp. 1083\u20131089 (2020)","DOI":"10.24963\/ijcai.2020\/151"}],"container-title":["Lecture Notes in Computer Science","Chinese Computational Linguistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-6207-5_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,19]],"date-time":"2023-09-19T08:45:59Z","timestamp":1695113159000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-6207-5_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9789819962068","9789819962075"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-6207-5_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"20 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CCL","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China National Conference on Chinese Computational Linguistics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Harbin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 August 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 August 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cncl2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}