{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T04:52:34Z","timestamp":1783831954671,"version":"3.55.0"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030586003","type":"print"},{"value":"9783030586010","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-58601-0_2","type":"book-chapter","created":{"date-parts":[[2020,11,27]],"date-time":"2020-11-27T19:02:52Z","timestamp":1606503772000},"page":"18-34","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":46,"title":["Reducing Language Biases in Visual Question Answering with Visually-Grounded Question Encoder"],"prefix":"10.1007","author":[{"given":"Gouthaman","family":"KV","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anurag","family":"Mittal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,11,28]]},"reference":[{"key":"2_CR1","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 the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4971\u20134980 (2018)","DOI":"10.1109\/CVPR.2018.00522"},{"key":"2_CR2","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: IEEE conference on Computer Vision and Pattern Recognition, pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"2_CR4","doi-asserted-by":"crossref","unstructured":"Ben-Younes, H., Cadene, R., Cord, M., Thome, N.: MUTAN: multimodal tucker fusion for visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, vol. 3 (2017)","DOI":"10.1109\/ICCV.2017.285"},{"key":"2_CR5","first-page":"8102","volume":"33","author":"H Ben-Younes","year":"2019","unstructured":"Ben-Younes, H., Cadene, R., Thome, N., Cord, M.: BLOCK: bilinear superdiagonal fusion for visual question answering and visual relationship detection. Proc. AAAI Conf. Artif. Intell. 33, 8102\u20138109 (2019)","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Cadene, R., Ben-Younes, H., Cord, M., Thome, N.: MUREL: multimodal relational reasoning for visual question answering. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1989\u20131998 (2019)","DOI":"10.1109\/CVPR.2019.00209"},{"key":"2_CR7","unstructured":"Cadene, R., Dancette, C., Cord, M., Parikh, D., et al.: RUBi: reducing unimodal biases for visual question answering. In: Advances in Neural Information Processing Systems, pp. 839\u2013850 (2019)"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Chao, W.L., Hu, H., Sha, F.: Being negative but constructively: Lessons learnt from creating better visual question answering datasets. arXiv preprint arXiv:1704.07121 (2017)","DOI":"10.18653\/v1\/N18-1040"},{"key":"2_CR9","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: 2020 34th AAAI Conference on Artificial Intelligence (2020)","DOI":"10.1609\/aaai.v34i07.6776"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Cho, K., Van Merri\u00ebnboer, B., Bahdanau, D., Bengio, Y.: On the properties of neural machine translation: Encoder-decoder approaches. arXiv preprint arXiv:1409.1259 (2014)","DOI":"10.3115\/v1\/W14-4012"},{"key":"2_CR11","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":"2_CR12","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (2019)"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Fukui, A., Park, D.H., Yang, D., Rohrbach, A., Darrell, T., Rohrbach, M.: Multimodal compact bilinear pooling for visual question answering and visual grounding. In: Conference on Empirical Methods in Natural Language Processing, pp. 457\u2013468 (2016)","DOI":"10.18653\/v1\/D16-1044"},{"key":"2_CR14","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: IEEE Conference on Computer Vision and Pattern Recognition, pp. 6904\u20136913 (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"Gurari, D., et al..: VizWiz grand challenge: answering visual questions from blind people. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3608\u20133617 (2018)","DOI":"10.1109\/CVPR.2018.00380"},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"2_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_47","volume-title":"Computer Vision - ECCV 2018","author":"LA Hendricks","year":"2018","unstructured":"Hendricks, L.A., Burns, K., Saenko, K., Darrell, T., Rohrbach, A.: Women also snowboard: overcoming bias in captioning models. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01219-9_47"},{"issue":"8","key":"2_CR18","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"2_CR19","doi-asserted-by":"crossref","unstructured":"Hudson, D.A., Manning, C.D.: GQA: a new dataset for real-world visual reasoning and compositional question answering. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00686"},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"Huk Park, D., et al.: Multimodal explanations: justifying decisions and pointing to the evidence. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8779\u20138788 (2018)","DOI":"10.1109\/CVPR.2018.00915"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Kafle, K., Kanan, C.: An analysis of visual question answering algorithms. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.217"},{"key":"2_CR22","unstructured":"Kim, J.H., Jun, J., Zhang, B.T.: Bilinear attention networks. In: Advances in Neural Information Processing Systems, pp. 1564\u20131574 (2018)"},{"key":"2_CR23","unstructured":"Kim, J.H., On, K.W., Lim, W., Kim, J., Ha, J.W., Zhang, B.T.: Hadamard product for low-rank bilinear pooling. In: ICLR (2017)"},{"issue":"1","key":"2_CR24","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vis. 123(1), 32\u201373 (2017)","journal-title":"Int. J. Comput. Vis."},{"key":"2_CR25","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2019). https:\/\/openreview.net\/forum?id=Bkg6RiCqY7"},{"key":"2_CR26","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: ViLBERT: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In: Advances in Neural Information Processing Systems, pp. 13\u201323 (2019)"},{"key":"2_CR27","doi-asserted-by":"crossref","unstructured":"Manjunatha, V., Saini, N., Davis, L.S.: Explicit bias discovery in visual question answering models. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9562\u20139571 (2019)","DOI":"10.1109\/CVPR.2019.00979"},{"key":"2_CR28","doi-asserted-by":"crossref","unstructured":"Nguyen, D.K., Okatani, T.: Improved fusion of visual and language representations by dense symmetric co-attention for visual question answering. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 6087\u20136096 (2018)","DOI":"10.1109\/CVPR.2018.00637"},{"key":"2_CR29","unstructured":"Gao, P., You, H., Zhang, Z., Wang, X., Li, H.: Multi-modality latent interaction network for visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision (2019)"},{"key":"2_CR30","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.: GloVe: global vectors for word representation. In: Conference on Empirical Methods in Natural Language Processing, pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"2_CR31","doi-asserted-by":"crossref","unstructured":"Perez, E., Strub, F., De Vries, H., Dumoulin, V., Courville, A.: FiLM: visual reasoning with a general conditioning layer. In: 32nd AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"2_CR32","unstructured":"Ramakrishnan, S., Agrawal, A., Lee, S.: Overcoming language priors in visual question answering with adversarial regularization. In: Advances in Neural Information Processing Systems, pp. 1541\u20131551 (2018)"},{"key":"2_CR33","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., et al.: Taking a hint: leveraging explanations to make vision and language models more grounded. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2591\u20132600 (2019)","DOI":"10.1109\/ICCV.2019.00268"},{"key":"2_CR34","doi-asserted-by":"crossref","unstructured":"Shrestha, R., Kafle, K., Kanan, C.: Answer them all! Toward universal visual question answering models. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 10472\u201310481 (2019)","DOI":"10.1109\/CVPR.2019.01072"},{"key":"2_CR35","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"2_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1007\/978-3-030-01231-1_31","volume-title":"Computer Vision \u2013 ECCV 2018","author":"P Stock","year":"2018","unstructured":"Stock, P., Cisse, M.: ConvNets and ImageNet beyond accuracy: understanding mistakes and\u00a0uncovering biases. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11210, pp. 504\u2013519. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01231-1_31"},{"key":"2_CR37","doi-asserted-by":"crossref","unstructured":"Tan, H., Bansal, M.: LXMERT: learning cross-modality encoder representations from transformers. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 5103\u20135114 (2019)","DOI":"10.18653\/v1\/D19-1514"},{"key":"2_CR38","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in neural information processing systems, pp. 5998\u20136008 (2017)"},{"key":"2_CR39","unstructured":"Wu, J., Mooney, R.: Self-critical reasoning for robust visual question answering. In: Advances in Neural Information Processing Systems, pp. 8601\u20138611 (2019)"},{"key":"2_CR40","doi-asserted-by":"crossref","unstructured":"Yang, Z., He, X., Gao, J., Deng, L., Smola, A.: Stacked attention networks for image question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 21\u201329 (2016)","DOI":"10.1109\/CVPR.2016.10"},{"key":"2_CR41","doi-asserted-by":"crossref","unstructured":"Yu, Z., Yu, J., Fan, J., Tao, D.: Multi-modal factorized bilinear pooling with co-attention learning for visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, vol. 3 (2017)","DOI":"10.1109\/ICCV.2017.202"},{"key":"2_CR42","doi-asserted-by":"crossref","unstructured":"Zellers, R., Bisk, Y., Farhadi, A., Choi, Y.: From recognition to cognition: visual commonsense reasoning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6720\u20136731 (2019)","DOI":"10.1109\/CVPR.2019.00688"},{"key":"2_CR43","doi-asserted-by":"crossref","unstructured":"Zhao, J., Wang, T., Yatskar, M., Ordonez, V., Chang, K.W.: Men also like shopping: Reducing gender bias amplification using corpus-level constraints. arXiv preprint arXiv:1707.09457 (2017)","DOI":"10.18653\/v1\/D17-1323"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58601-0_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:04:16Z","timestamp":1732665856000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58601-0_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030586003","9783030586010"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58601-0_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"28 November 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1360","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"27% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"7","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic. From the ECCV Workshops 249 full papers, 18 short papers, and 21 further contributions were published out of a total of 467 submissions.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}