{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T03:23:32Z","timestamp":1742959412070,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":28,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819756148"},{"type":"electronic","value":"9789819756155"}],"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\/978-981-97-5615-5_22","type":"book-chapter","created":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T13:12:02Z","timestamp":1722604322000},"page":"264-277","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["VQA-PDF: Purifying Debiased Features for Robust Visual Question Answering Task"],"prefix":"10.1007","author":[{"given":"Yandong","family":"Bi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huajie","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengting","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongli","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Baocai","family":"Yin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,8,3]]},"reference":[{"key":"22_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: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4971\u20134980 (2018)","DOI":"10.1109\/CVPR.2018.00522"},{"key":"22_CR2","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., et al.: Taking a hint: leveraging explanations to make vision and language models more grounded. In: ICCV, pp. 2591\u20132600 (2019)","DOI":"10.1109\/ICCV.2019.00268"},{"key":"22_CR3","unstructured":"Wu, J., Mooney, R.: Self-critical reasoning for robust visual question answering. In: NeurIPS, vol. 32, pp. 8601\u20138611 (2019)"},{"key":"22_CR4","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: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10 800\u201310 809 (2020)","DOI":"10.1109\/CVPR42600.2020.01081"},{"key":"22_CR5","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: EMNLP, pp. 878\u201389 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.63"},{"key":"22_CR6","unstructured":"Cadene, R., Dancette, C., Ben-Younes, H., Cord, M., Parikh, D.: RUBi: reducing unimodal biases in visual question answering. In: Advances in Neural Information Processing Systems (NeurIPS), pp. 839\u2013850 (2019)"},{"key":"22_CR7","unstructured":"Ramakrishnan, S., Agrawal, A., Lee, S.: Overcoming language priors in visual question answering with adversarial regularization. In: Advances in Neural Information Processing Systems (NeurIPS), vol. 31, pp. 1548\u20131558 (2018)"},{"key":"22_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: ACM SIGIR, pp. 1955\u20131959 (2021)","DOI":"10.1145\/3404835.3462981"},{"key":"22_CR9","unstructured":"Niu, Y., Tang, K., Zhang, H., Lu, Z., Hua, X.-S., Wen, J.-R.: Counterfactual VQA: a cause-effect look at language bias. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12 700\u201312 710 (2021)"},{"key":"22_CR10","unstructured":"Wen, Z., Xu, G., Tan, M., Wu, Q., Wu, Q.: Debiased visual question answering from feature and sample perspectives. In: Advances in Neural Information Processing Systems (NeurIPS), vol. 34, pp. 3784\u20133796 (2021)"},{"key":"22_CR11","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 (CVPR), pp. 6904\u20136913 (2017)","DOI":"10.1109\/CVPR.2017.670"},{"issue":"2","key":"22_CR12","doi-asserted-by":"publisher","first-page":"1135","DOI":"10.1109\/TCSVT.2023.3291379","volume":"34","author":"Y Bi","year":"2024","unstructured":"Bi, Y., Jiang, H., Hu, Y., Sun, Y., Yin, B.: See and learn more: dense caption-aware representation for visual question answering. IEEE Trans. Circuits Syst. Video Technol. 34(2), 1135\u20131146 (2024)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"22_CR13","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: IJCAI, pp. 1083\u20131089 (2020)","DOI":"10.24963\/ijcai.2020\/151"},{"key":"22_CR14","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1016\/j.patrec.2023.11.024","volume":"177","author":"Y Bi","year":"2024","unstructured":"Bi, Y., Jiang, H., Zhang, H., Hu, Y., Yin, B.: Self-supervised knowledge distillation in counterfactual learning for VQA. Pattern Recogn. Lett. 177, 33\u201339 (2024)","journal-title":"Pattern Recogn. Lett."},{"key":"22_CR15","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1109\/TIP.2021.3128322","volume":"31","author":"Y Guo","year":"2021","unstructured":"Guo, Y., Nie, L., Cheng, Z., Tian, Q., Zhang, M.: Loss re-scaling VQA: revisiting the language prior problem from a class-imbalance view. IEEE Trans. Image Process. 31, 227\u2013238 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"22_CR16","doi-asserted-by":"crossref","unstructured":"Dancette, C., Cadene, R., Teney, D., Cord, M.: Beyond question based biases: Assessing multimodal shortcut learning in visual question answering. In: IEEE International Conference on Computer Vision (ICCV), pp. 1574\u20131583 (2021)","DOI":"10.1109\/ICCV48922.2021.00160"},{"key":"22_CR17","unstructured":"Nam, J., Cha, H., Ahn, S., Lee, J., Shin, J.: Learning from failure: de-biasing classifier from biased classifier. In: NeurIPS, vol. 33, pp. 20673\u201320684 (2020)"},{"key":"22_CR18","doi-asserted-by":"crossref","unstructured":"Shrestha, R., Kafle, K., Kanan, C.: A negative case analysis of visual grounding methods for VQA. In: ACL, pp. 8172\u20138181 (2020)","DOI":"10.18653\/v1\/2020.acl-main.727"},{"key":"22_CR19","doi-asserted-by":"crossref","unstructured":"Cho, J.W., Kim, D.-J., Ryu, H., Kweon, I.S.: Generative bias for robust visual question answering. In: CVPR, pp. 11681\u201311690 (2023)","DOI":"10.1109\/CVPR52729.2023.01124"},{"key":"22_CR20","doi-asserted-by":"publisher","first-page":"56","DOI":"10.3390\/jimaging10030056","volume":"10","author":"Q Lu","year":"2024","unstructured":"Lu, Q., Chen, S., Zhu, X.: Collaborative modality fusion for mitigating language bias in visual question answering. J. Imaging 10, 56 (2024)","journal-title":"J. Imaging"},{"key":"22_CR21","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: Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 3285\u20133292 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.265"},{"key":"22_CR22","doi-asserted-by":"publisher","unstructured":"Chen, L., Yuhang, Z., Jun, X.: Rethinking data augmentation for robust visual question answering. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13696, pp. 95\u2013112. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20059-5_6","DOI":"10.1007\/978-3-031-20059-5_6"},{"key":"22_CR23","unstructured":"Teney, D., Abbasnejad, E., Kafle, K., Shrestha, R., Kanan, C., VanDen Hengel, A.: On the value of out-of-distribution testing: an example of Goodhart\u2019s law. In: Advances in Neural Information Processing Systems (NeurIPS), vol. 33, pp. 407\u2013417 (2020)"},{"key":"22_CR24","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 (CVPR), pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"22_CR25","doi-asserted-by":"crossref","unstructured":"Yang, Z., He, X., Gao, J., Deng, L., Smola, A.: Stacked attention networks for image question answering. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 21\u201329 (2016)","DOI":"10.1109\/CVPR.2016.10"},{"key":"22_CR26","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems (NeurIPS), vol. 28, pp. 91\u201399 (2015)"},{"key":"22_CR27","doi-asserted-by":"crossref","unstructured":"Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: EMNLP, pp. 1724\u20131734 (2014)","DOI":"10.3115\/v1\/D14-1179"},{"key":"22_CR28","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: GloVe: global vectors for word representation. In: EMNLP, pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-5615-5_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,9]],"date-time":"2024-11-09T11:05:31Z","timestamp":1731150331000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-5615-5_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819756148","9789819756155"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-5615-5_22","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":"3 August 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tianjin","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 August 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2024\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}