{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T15:58:46Z","timestamp":1772553526566,"version":"3.50.1"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585280","type":"print"},{"value":"9783030585297","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\/978-3-030-58529-7_26","type":"book-chapter","created":{"date-parts":[[2020,11,12]],"date-time":"2020-11-12T09:06:09Z","timestamp":1605171969000},"page":"437-453","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":35,"title":["Semantic Equivalent Adversarial Data Augmentation for Visual Question Answering"],"prefix":"10.1007","author":[{"given":"Ruixue","family":"Tang","sequence":"first","affiliation":[]},{"given":"Chao","family":"Ma","sequence":"additional","affiliation":[]},{"given":"Wei Emma","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Qi","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Xiaokang","family":"Yang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,11,13]]},"reference":[{"key":"26_CR1","doi-asserted-by":"crossref","unstructured":"Agarwal, V., Shetty, R., Fritz, M.: Towards causal VQA: revealing and reducing spurious correlations by invariant and covariant semantic editing. arXiv preprint arXiv:1912.07538 (2019)","DOI":"10.1109\/CVPR42600.2020.00971"},{"key":"26_CR2","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 the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"26_CR3","doi-asserted-by":"crossref","unstructured":"Andreas, J., Rohrbach, M., Darrell, T., Klein, D.: Learning to compose neural networks for question answering. arXiv preprint arXiv:1601.01705 (2016)","DOI":"10.18653\/v1\/N16-1181"},{"key":"26_CR4","doi-asserted-by":"crossref","unstructured":"Andreas, J., Rohrbach, M., Darrell, T., Klein, D.: Neural module networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 39\u201348 (2016)","DOI":"10.1109\/CVPR.2016.12"},{"key":"26_CR5","unstructured":"Belinkov, Y., Bisk, Y.: Synthetic and natural noise both break neural machine translation. arXiv preprint arXiv:1711.02173 (2017)"},{"key":"26_CR6","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, pp. 2612\u20132620 (2017)","DOI":"10.1109\/ICCV.2017.285"},{"key":"26_CR7","doi-asserted-by":"crossref","unstructured":"Blohm, M., Jagfeld, G., Sood, E., Yu, X., Vu, N.T.: Comparing attention-based convolutional and recurrent neural networks: Success and limitations in machine reading comprehension. arXiv preprint arXiv:1808.08744 (2018)","DOI":"10.18653\/v1\/K18-1011"},{"key":"26_CR8","unstructured":"Carlini, N.,et al.: On evaluating adversarial robustness. arXiv preprint arXiv:1902.06705 (2019)"},{"key":"26_CR9","unstructured":"Ebrahimi, J., Lowd, D., Dou, D.: On adversarial examples for character-level neural machine translation. arXiv preprint arXiv:1806.09030 (2018)"},{"key":"26_CR10","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. arXiv preprint arXiv:1606.01847 (2016)","DOI":"10.18653\/v1\/D16-1044"},{"key":"26_CR11","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"26_CR12","unstructured":"Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)"},{"key":"26_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 the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6904\u20136913 (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"26_CR14","doi-asserted-by":"crossref","unstructured":"Hu, R., Andreas, J., Rohrbach, M., Darrell, T., Saenko, K.: Learning to reason: End-to-end module networks for visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 804\u2013813 (2017)","DOI":"10.1109\/ICCV.2017.93"},{"key":"26_CR15","doi-asserted-by":"crossref","unstructured":"Iyyer, M., Wieting, J., Gimpel, K., Zettlemoyer, L.: Adversarial example generation with syntactically controlled paraphrase networks. arXiv preprint arXiv:1804.06059 (2018)","DOI":"10.18653\/v1\/N18-1170"},{"key":"26_CR16","doi-asserted-by":"crossref","unstructured":"Jain, U., Zhang, Z., Schwing, A.G.: Creativity: generating diverse questions using variational autoencoders. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6485\u20136494 (2017)","DOI":"10.1109\/CVPR.2017.575"},{"key":"26_CR17","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.cviu.2017.06.005","volume":"163","author":"K Kafle","year":"2017","unstructured":"Kafle, K., Kanan, C.: Visual question answering: datasets, algorithms, and future challenges. Comput. Vis. Image Underst. 163, 3\u201320 (2017)","journal-title":"Comput. Vis. Image Underst."},{"key":"26_CR18","doi-asserted-by":"crossref","unstructured":"Kafle, K., Yousefhussien, M., Kanan, C.: Data augmentation for visual question answering. In: Proceedings of the 10th International Conference on Natural Language Generation, pp. 198\u2013202 (2017)","DOI":"10.18653\/v1\/W17-3529"},{"key":"26_CR19","unstructured":"Kim, J.H., Jun, J., Zhang, B.T.: Bilinear attention networks. In: Advances in Neural Information Processing Systems, pp. 1564\u20131574 (2018)"},{"key":"26_CR20","unstructured":"Kim, J.H., On, K.W., Lim, W., Kim, J., Ha, J.W., Zhang, B.T.: Hadamard product for low-rank bilinear pooling. arXiv preprint arXiv:1610.04325 (2016)"},{"key":"26_CR21","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"issue":"1","key":"26_CR22","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). https:\/\/doi.org\/10.1007\/s11263-016-0981-7","journal-title":"Int. J. Comput. Vis."},{"key":"26_CR23","unstructured":"Kurakin, A., Goodfellow, I., Bengio, S.: Adversarial examples in the physical world. arXiv preprint arXiv:1607.02533 (2016)"},{"key":"26_CR24","unstructured":"Kurakin, A., Goodfellow, I., Bengio, S.: Adversarial machine learning at scale. arXiv preprint arXiv:1611.01236 (2016)"},{"key":"26_CR25","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Visual question generation as dual task of visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6116\u20136124 (2018)","DOI":"10.1109\/CVPR.2018.00640"},{"key":"26_CR26","unstructured":"Lu, J., Yang, J., Batra, D., Parikh, D.: Hierarchical question-image co-attention for visual question answering. In: Advances in Neural Information Processing Systems, pp. 289\u2013297 (2016)"},{"key":"26_CR27","unstructured":"Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks. arXiv preprint arXiv:1706.06083 (2017)"},{"key":"26_CR28","doi-asserted-by":"crossref","unstructured":"Mallinson, J., Sennrich, R., Lapata, M.: Paraphrasing revisited with neural machine translation. In: Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pp. 881\u2013893 (2017)","DOI":"10.18653\/v1\/E17-1083"},{"key":"26_CR29","unstructured":"Norcliffe-Brown, W., Vafeias, S., Parisot, S.: Learning conditioned graph structures for interpretable visual question answering. In: Advances in Neural Information Processing Systems, pp. 8334\u20138343 (2018)"},{"key":"26_CR30","doi-asserted-by":"crossref","unstructured":"Patro, B., Namboodiri, V.P.: Differential attention for visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7680\u20137688 (2018)","DOI":"10.1109\/CVPR.2018.00801"},{"key":"26_CR31","unstructured":"Peng, G., et al.: Dynamic fusion with intra-and inter-modality attention flow for visual question answering. arXiv preprint arXiv:1812.05252 (2018)"},{"key":"26_CR32","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: GloVe: global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"26_CR33","doi-asserted-by":"crossref","unstructured":"Ray, A., Sikka, K., Divakaran, A., Lee, S., Burachas, G.: Sunny and dark outside?! Improving answer consistency in VQA through entailed question generation. arXiv preprint arXiv:1909.04696 (2019)","DOI":"10.18653\/v1\/D19-1596"},{"key":"26_CR34","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.T., Singh, S., Guestrin, C.: Semantically equivalent adversarial rules for debugging NLP models. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 856\u2013865 (2018)","DOI":"10.18653\/v1\/P18-1079"},{"key":"26_CR35","doi-asserted-by":"crossref","unstructured":"Shah, M., Chen, X., Rohrbach, M., Parikh, D.: Cycle-consistency for robust visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6649\u20136658 (2019)","DOI":"10.1109\/CVPR.2019.00681"},{"key":"26_CR36","doi-asserted-by":"crossref","unstructured":"Sharma, V., Vaibhav, A., Chaudhary, S., Patel, L., Morency, L.: Attend and attack: attention guided adversarial attacks on visual question answering models (2018)","DOI":"10.18653\/v1\/P17-3008"},{"issue":"1","key":"26_CR37","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1186\/s40537-019-0197-0","volume":"6","author":"C Shorten","year":"2019","unstructured":"Shorten, C., Khoshgoftaar, T.M.: A survey on image data augmentation for deep learning. J. Big Data 6(1), 60 (2019). https:\/\/doi.org\/10.1186\/s40537-019-0197-0","journal-title":"J. Big Data"},{"key":"26_CR38","unstructured":"Szegedy, C., et al.: Intriguing properties of neural networks. arXiv preprint arXiv:1312.6199 (2013)"},{"key":"26_CR39","doi-asserted-by":"crossref","unstructured":"Teney, D., Anderson, P., He, X., Van Den Hengel, A.: Tips and tricks for visual question answering: learnings from the 2017 challenge. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4223\u20134232 (2018)","DOI":"10.1109\/CVPR.2018.00444"},{"key":"26_CR40","doi-asserted-by":"crossref","unstructured":"Wei, J.W., Zou, K.: EDA: easy data augmentation techniques for boosting performance on text classification tasks. arXiv preprint arXiv:1901.11196 (2019)","DOI":"10.18653\/v1\/D19-1670"},{"key":"26_CR41","doi-asserted-by":"crossref","unstructured":"Xie, C., Tan, M., Gong, B., Wang, J., Yuille, A., Le, Q.V.: Adversarial examples improve image recognition. arXiv preprint arXiv:1911.09665 (2019)","DOI":"10.1109\/CVPR42600.2020.00090"},{"key":"26_CR42","unstructured":"Xie, Z., et al.: Data noising as smoothing in neural network language models. arXiv preprint arXiv:1703.02573 (2017)"},{"key":"26_CR43","doi-asserted-by":"crossref","unstructured":"Xu, X., Chen, X., Liu, C., Rohrbach, A., Darrell, T., Song, D.: Fooling vision and language models despite localization and attention mechanism. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4951\u20134961 (2018)","DOI":"10.1109\/CVPR.2018.00520"},{"key":"26_CR44","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":"26_CR45","unstructured":"Yu, A.W., et al.: QANet: combining local convolution with global self-attention for reading comprehension. arXiv preprint arXiv:1804.09541 (2018)"},{"key":"26_CR46","unstructured":"Zhang, Y., Hare, J., Pr\u00fcgel-Bennett, A.: Learning to count objects in natural images for visual question answering. arXiv preprint arXiv:1802.05766 (2018)"}],"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\/978-3-030-58529-7_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T00:35:39Z","timestamp":1731371739000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58529-7_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585280","9783030585297"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58529-7_26","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":"13 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)"}}]}}