{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T08:03:32Z","timestamp":1742976212448,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":24,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819714162"},{"type":"electronic","value":"9789819714179"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-981-97-1417-9_29","type":"book-chapter","created":{"date-parts":[[2024,5,21]],"date-time":"2024-05-21T07:05:03Z","timestamp":1716275103000},"page":"310-321","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Generating Type-Related Instances and Metric Learning to Overcoming Language Priors in VQA"],"prefix":"10.1007","author":[{"given":"Chongxiang","family":"Sun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengtao","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenliang","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jia","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,5,22]]},"reference":[{"key":"29_CR1","doi-asserted-by":"crossref","unstructured":"Antol, S., Agrawal, A., Lu, J., et al.: VQA: visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"29_CR2","doi-asserted-by":"crossref","unstructured":"Agrawal A, Batra D, Parikh D.: Analyzing the behavior of visual question answering models. In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp.1955\u20131960 (2016)","DOI":"10.18653\/v1\/D16-1203"},{"key":"29_CR3","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 the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 4069\u20134082 (2019)","DOI":"10.18653\/v1\/D19-1418"},{"key":"29_CR4","unstructured":"Cadene, R., Dancette, C., Cord, M., et al.: RUBi: reducing unimodal biases for visual question answering. In: Advances in Neural Information Processing Systems (NIPS) (2019)"},{"key":"29_CR5","unstructured":"Wu, J., Mooney, R.: Self-critical reasoning for robust visual question answering. In: Advances in Neural Information Processing Systems (NIPS), pp. 8604\u20138614 (2019)"},{"key":"29_CR6","doi-asserted-by":"crossref","unstructured":"Si, Q., Lin, Z., Zheng, M., et al.: Check it again: progressive visual question answering via visual entailment. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, pp. 4101\u20134110 (2021)","DOI":"10.18653\/v1\/2021.acl-long.317"},{"key":"29_CR7","doi-asserted-by":"crossref","unstructured":"Tan, H., Bansal, M.: LXMERT: learning cross-modality encoder representations from transformers. In: Proceedings of the 2019 Conference on EMNLP-IJCNLP, pp. 5100\u20135111 (2019)","DOI":"10.18653\/v1\/D19-1514"},{"key":"29_CR8","doi-asserted-by":"crossref","unstructured":"Liang, Z., Hu, H., Zhu, J.: LPF: a language-prior feedback objective function for de-biased visual question answering. In: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 1955\u20131959 (2021)","DOI":"10.1145\/3404835.3462981"},{"key":"29_CR9","unstructured":"Ramakrishnan, S., Agrawal, A., Lee, S.: Overcoming language priors in visual question answering with adversarial regularization. In: Advances in Neural Information Processing System (NIPS), pp. 1548\u20131558 (2018)"},{"key":"29_CR10","doi-asserted-by":"crossref","unstructured":"Liang, Z., Jiang, W., Hu, H., et al.: Learning to contrast the counterfactual samples for robust visual question answering. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 3285\u20133292 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.265"},{"key":"29_CR11","doi-asserted-by":"crossref","unstructured":"Chen, L., Yan, X., Xiao, J., et al.: Counterfactual samples synthesizing for robust visual question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10800\u201310809 (2020)","DOI":"10.1109\/CVPR42600.2020.01081"},{"key":"29_CR12","doi-asserted-by":"crossref","unstructured":"Si, Q., Liu, Y., Meng, F., et al.: Towards robust visual question answering: making the most of biased samples via contrastive learning. In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 6650\u20136662 (2022)","DOI":"10.18653\/v1\/2022.findings-emnlp.495"},{"key":"29_CR13","doi-asserted-by":"crossref","unstructured":"Zhu, X., Mao, Z., Liu, C., et al.: Overcoming language priors with self-supervised learning for visual question answering. In: Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, pp. 1083\u20131089 (2020)","DOI":"10.24963\/ijcai.2020\/151"},{"key":"29_CR14","unstructured":"Wu, Y., Zhao, Y., Zhao, S., et al.: Overcoming language priors in visual question answering via distinguishing superficially similar instances. In: Proceedings of the 29th International Conference on Computational Linguistics, pp. 5721\u20135729 (2022)"},{"key":"29_CR15","unstructured":"Mahabadi, R.K., Henderson, J.: Simple but effective techniques to reduce biases. arXiv:1909.06321 (2019)"},{"key":"29_CR16","doi-asserted-by":"crossref","unstructured":"Anderson, P., He, X., Buehler, C., 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 (CVPR), pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"issue":"1","key":"29_CR17","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1162\/neco.1995.7.1.72","volume":"7","author":"DG Lowe","year":"1995","unstructured":"Lowe, D.G.: Similarity metric learning for a variable-kernel classifier. Neural Comput. 7(1), 72\u201385 (1995)","journal-title":"Neural Comput."},{"key":"29_CR18","doi-asserted-by":"crossref","unstructured":"Wang, X., Han, X., Huang, W., et al.: Multi-similarity loss with general pair weighting for deep metric learning. In: Proceedings of the IEEE\/CVF Conference Computer Vision and Pattern Recognition (CVPR), pp. 5022\u20135030 (2019)","DOI":"10.1109\/CVPR.2019.00516"},{"key":"29_CR19","doi-asserted-by":"crossref","unstructured":"Agrawal, A., Batra, D., Parikh, D., et al.: 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 (CVPR), pp. 4971\u20134980 (2018)","DOI":"10.1109\/CVPR.2018.00522"},{"key":"29_CR20","doi-asserted-by":"crossref","unstructured":"Yang, Z., He, X., Gao, J., et al.: Stacked attention networks for image question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 21\u201329 (2016)","DOI":"10.1109\/CVPR.2016.10"},{"key":"29_CR21","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Lee, S., Shen, Y., et al.: Taking a hint: leveraging explanations to make vision and language models more grounded. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 2591\u20132600 (2019)","DOI":"10.1109\/ICCV.2019.00268"},{"key":"29_CR22","doi-asserted-by":"crossref","unstructured":"Jing, C., Wu, Y., Zhang, X., et al.: Overcoming language priors in VQA via decomposed language representations. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 11181\u201311188 (2020)","DOI":"10.1609\/aaai.v34i07.6776"},{"key":"29_CR23","doi-asserted-by":"crossref","unstructured":"Niu, Y., Tang, K., Zhang, H., et al.: Counterfactual VQA: a cause-effect look at language bias. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12700\u201312710 (2021)","DOI":"10.1109\/CVPR46437.2021.01251"},{"key":"29_CR24","doi-asserted-by":"crossref","unstructured":"Goyal, Y., Khot, T., Summers-Stay, D., et al.: 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 (CVPR), pp. 6904\u20136913 (2017)","DOI":"10.1109\/CVPR.2017.670"}],"container-title":["Lecture Notes in Computer Science","Advances in Brain Inspired Cognitive Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-1417-9_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,21]],"date-time":"2024-05-21T07:10:49Z","timestamp":1716275449000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-1417-9_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819714162","9789819714179"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-1417-9_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"22 May 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"BICS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Brain Inspired Cognitive Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kuala Lumpur","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malaysia","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":"5 August 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 August 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"bics2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"58","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":"36","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":"62% - 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":"5","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)"}}]}}