{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T11:27:04Z","timestamp":1786966024651,"version":"build-2736575974"},"reference-count":62,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T00:00:00Z","timestamp":1785110400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T00:00:00Z","timestamp":1785110400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Humanities and Social Sciences Youth Foundation, Ministry of Education,China","award":["24YJC740057"],"award-info":[{"award-number":["24YJC740057"]}]},{"name":"\u201c20 New Universities\u201dProject of Jinan City","award":["202333023"],"award-info":[{"award-number":["202333023"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1007\/s00530-026-02537-x","type":"journal-article","created":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T03:09:23Z","timestamp":1785121763000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Mgsc: multimodal generation and self-supervised contrast learning for mitigating language bias in visual question answering"],"prefix":"10.1007","volume":"32","author":[{"given":"Xinyu","family":"Jiang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenfang","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiang","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiangtao","family":"Qi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanhan","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dawei","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuejuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,27]]},"reference":[{"key":"2537_CR1","doi-asserted-by":"crossref","unstructured":"Ma, J., Wang, P., Kong, D., Wang, Z., Liu, J., Pei, H., Zhao, J.: Robust visual question answering: Datasets, methods, and future challenges. IEEE Transactions on Pattern Analysis and Machine Intelligence (2024)","DOI":"10.1109\/TPAMI.2024.3366154"},{"key":"2537_CR2","doi-asserted-by":"crossref","unstructured":"Schwenk, D., Khandelwal, A., Clark, C., Marino, K., Mottaghi, R.: A-okvqa: A benchmark for visual question answering using world knowledge. In: European Conference on Computer Vision, pp. 146\u2013162. Springer (2022)","DOI":"10.1007\/978-3-031-20074-8_9"},{"key":"2537_CR3","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"},{"issue":"6","key":"2537_CR4","doi-asserted-by":"publisher","first-page":"2935","DOI":"10.1109\/TCSVT.2022.3229081","volume":"33","author":"L Zhao","year":"2022","unstructured":"Zhao, L., Cai, D., Zhang, J., Sheng, L., Xu, D., Zheng, R., Zhao, Y., Wang, L., Fan, X.: Toward explainable 3d grounded visual question answering: A new benchmark and strong baseline. IEEE Trans. Circuits Syst. Video Technol. 33(6), 2935\u20132949 (2022)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"2537_CR5","doi-asserted-by":"crossref","unstructured":"Agrawal, A., Batra, D., Parikh, D.: Analyzing the behavior of visual question answering models, (2016). arXiv preprint arXiv:1606.07356","DOI":"10.18653\/v1\/D16-1203"},{"key":"2537_CR6","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":"2537_CR7","doi-asserted-by":"crossref","unstructured":"Zhang, P., Goyal, Y., Summers-Stay, D., Batra, D., Parikh, D.: Yin and yang: Balancing and answering binary visual questions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5014\u20135022. (2016)","DOI":"10.1109\/CVPR.2016.542"},{"key":"2537_CR8","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: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1574\u20131583. (2021)","DOI":"10.1109\/ICCV48922.2021.00160"},{"key":"2537_CR9","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":"2537_CR10","doi-asserted-by":"crossref","unstructured":"Anderson, P., He, X., Buehler, C., Teney, D., Johnson, M., Gould, S., Zhang, L.: 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":"2537_CR11","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, (2019). arXiv preprint arXiv:1909.03683","DOI":"10.18653\/v1\/D19-1418"},{"key":"2537_CR12","unstructured":"Kim, J.-H., Jun, J., Zhang, B.-T.: Bilinear attention networks. Advances in neural information processing systems, pp. 31. (2018)"},{"key":"2537_CR13","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1016\/j.neucom.2020.10.071","volume":"423","author":"M Lao","year":"2021","unstructured":"Lao, M., Guo, Y., Pu, N., Chen, W., Liu, Y., Lew, M.S.: Multi-stage hybrid embedding fusion network for visual question answering. Neurocomputing 423, 541\u2013550 (2021)","journal-title":"Neurocomputing"},{"issue":"6","key":"2537_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10489-025-06325-4","volume":"55","author":"AA Yusuf","year":"2025","unstructured":"Yusuf, A.A., Feng, C., Mao, X., Li, X., Haruna, Y., Duma, R.A.: Multi-scale dual-stream visual feature extraction and graph reasoning for visual question answering. Appl. Intell. 55(6), 1\u201318 (2025)","journal-title":"Appl. Intell."},{"key":"2537_CR15","first-page":"528","volume":"32","author":"R Cadene","year":"2019","unstructured":"Cadene, R., Dancette, C., Cord, M., Parikh, D.: Rubi: Reducing unimodal biases for visual question answering. Adv. Neural. Inf. Process. Syst. 32, 528 (2019)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2537_CR16","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 the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10800\u201310809. (2020)","DOI":"10.1109\/CVPR42600.2020.01081"},{"issue":"10","key":"2537_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3673902","volume":"20","author":"D Hao","year":"2024","unstructured":"Hao, D., Wang, Q., Zhu, X., Liu, J.: Hccl: Hierarchical counterfactual contrastive learning for robust visual question answering. ACM Trans. Multimed. Comput. Commun. Appl. 20(10), 1\u201321 (2024)","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"key":"2537_CR18","doi-asserted-by":"crossref","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12700\u201312710. (2021)","DOI":"10.1109\/CVPR46437.2021.01251"},{"issue":"11","key":"2537_CR19","doi-asserted-by":"publisher","first-page":"3027","DOI":"10.1007\/s11263-021-01514-3","volume":"129","author":"TM Le","year":"2021","unstructured":"Le, T.M., Le, V., Venkatesh, S., Tran, T.: Hierarchical conditional relation networks for multimodal video question answering. Int. J. Comput. Vision 129(11), 3027\u20133050 (2021)","journal-title":"Int. J. Comput. Vision"},{"key":"2537_CR20","doi-asserted-by":"crossref","unstructured":"Qiao, T., Dong, J., Xu, D.: Exploring human-like attention supervision in visual question answering. In: Proceedings of the AAAI Conference on Artificial Intelligence, 32, (2018)","DOI":"10.1609\/aaai.v32i1.12272"},{"key":"2537_CR21","unstructured":"Wu, J., Mooney, R.: Self-critical reasoning for robust visual question answering. Adv. Neural. Inf. Process. Syst. 32, (2019)"},{"key":"2537_CR22","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. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9690\u20139698. (2020)","DOI":"10.1109\/CVPR42600.2020.00971"},{"key":"2537_CR23","doi-asserted-by":"crossref","unstructured":"Bi, Y., Jiang, H., Hu, Y., Sun, Y., Yin, B.: Fair attention network for robust visual question answering. In: IEEE Transactions on Circuits and Systems for Video Technology, (2024)","DOI":"10.1109\/TCSVT.2024.3382684"},{"key":"2537_CR24","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.113993","volume":"164","author":"D Gupta","year":"2021","unstructured":"Gupta, D., Suman, S., Ekbal, A.: Hierarchical deep multi-modal network for medical visual question answering. Expert Syst. Appl. 164, 113993 (2021)","journal-title":"Expert Syst. Appl."},{"key":"2537_CR25","doi-asserted-by":"crossref","unstructured":"Han, X., Wang, S., Su, C., Huang, Q., Tian, Q.: Greedy gradient ensemble for robust visual question answering. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1584\u20131593. (2021)","DOI":"10.1109\/ICCV48922.2021.00161"},{"issue":"2","key":"2537_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2024.103988","volume":"62","author":"Y Sun","year":"2025","unstructured":"Sun, Y., Qi, J., Zhu, Z., Li, K., Zhao, L., Lv, L.: Bias-guided margin loss for robust visual question answering. Inf. Proc. Manag. 62(2), 103988 (2025)","journal-title":"Inf. Proc. Manag."},{"issue":"1","key":"2537_CR27","doi-asserted-by":"publisher","first-page":"549","DOI":"10.1007\/s00371-024-03346-x","volume":"41","author":"L Xue","year":"2025","unstructured":"Xue, L., Wang, W., Wang, R., Yang, J.: Modular dual-stream visual fusion network for visual question answering. Vis. Comput. 41(1), 549\u2013562 (2025)","journal-title":"Vis. Comput."},{"key":"2537_CR28","first-page":"3784","volume":"34","author":"Z Wen","year":"2021","unstructured":"Wen, Z., Xu, G., Tan, M., Wu, Q., Wu, Q.: Debiased visual question answering from feature and sample perspectives. Adv. Neural. Inf. Process. Syst. 34, 3784\u20133796 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"11","key":"2537_CR29","doi-asserted-by":"crossref","first-page":"13218","DOI":"10.1109\/TPAMI.2023.3289667","volume":"45","author":"L Chen","year":"2023","unstructured":"Chen, L., Zheng, Y., Niu, Y., Zhang, H., Xiao, J.: Counterfactual samples synthesizing and training for robust visual question answering. IEEE Trans. Pattern Anal. Mach. Intell. 45(11), 13218\u201313234 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2537_CR30","doi-asserted-by":"crossref","unstructured":"Li, M., Zhu, Z., Li, K., Pei, H.: Diversity and balance: multimodal sentiment analysis using multimodal-prefixed and cross-modal attention. IEEE Transactions on Affective Computing (2024)","DOI":"10.1109\/TAFFC.2024.3430045"},{"key":"2537_CR31","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Wu, H., Wang, J., Lv, L., Bardou, D., Yu, G.: Vlca: Vision-language feature enhancement with cross-attention learning for facial expression recognition. Expert Syst. Appl., 130292 (2025)","DOI":"10.1016\/j.eswa.2025.130292"},{"issue":"2","key":"2537_CR32","doi-asserted-by":"publisher","first-page":"1135","DOI":"10.1109\/TCSVT.2023.3291379","volume":"34","author":"Y Bi","year":"2023","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 (2023)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"2537_CR33","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Zhu, Y., Wu, H., Lv, L., Niu, S., Yu, G.: Sge: Semantic-guided generalization enhancement for few-shot learning. Knowledge-Based Systems, pp. 113761. (2025)","DOI":"10.1016\/j.knosys.2025.113761"},{"key":"2537_CR34","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. 31. (2018)"},{"issue":"2","key":"2537_CR35","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2022.103223","volume":"60","author":"Z Zhu","year":"2023","unstructured":"Zhu, Z., Zhang, D., Li, L., Li, K., Qi, J., Wang, W., Zhang, G., Liu, P.: Knowledge-guided multi-granularity gcn for absa. Info. Proc. Manag. 60(2), 103223 (2023)","journal-title":"Info. Proc. Manag."},{"key":"2537_CR36","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Wu, H., Lv, L., Zhang, C., Guo, H., Niu, S., Yu, G.: Multi-branch semantic alignment for few-shot image classification. Inf. Sci., 122676 (2025)","DOI":"10.1016\/j.ins.2025.122676"},{"key":"2537_CR37","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, (2020). arXiv preprint arXiv:2009.08566","DOI":"10.18653\/v1\/2020.emnlp-main.63"},{"key":"2537_CR38","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2024.103976","volume":"241","author":"S Yang","year":"2024","unstructured":"Yang, S., Xiao, L., Wu, X., Xu, J., Wang, L., He, L.: Simple contrastive learning in a self-supervised manner for robust visual question answering. Comput. Vis. Image Underst. 241, 103976 (2024)","journal-title":"Comput. Vis. Image Underst."},{"key":"2537_CR39","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. Patt. Recogn. Lett. 177, 33\u201339 (2024)","journal-title":"Patt. Recogn. Lett."},{"key":"2537_CR40","doi-asserted-by":"crossref","unstructured":"Huai, T., Yang, S., Zhang, J., Wang, G., Yu, X., Ma, T., He, L.: Sqt: Debiased visual question answering via shuffling question types. In: 2023 IEEE International Conference on Multimedia and Expo (ICME), pp. 600\u2013605. IEEE (2023)","DOI":"10.1109\/ICME55011.2023.00109"},{"key":"2537_CR41","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106560","volume":"179","author":"D Peng","year":"2024","unstructured":"Peng, D., Li, Z.: Robust visual question answering via polarity enhancement and contrast. Neural Netw. 179, 106560 (2024)","journal-title":"Neural Netw."},{"key":"2537_CR42","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.110412","volume":"266","author":"Z Zheng","year":"2023","unstructured":"Zheng, Z., Wu, H., Lv, L., Ye, H., Zhang, C., Yu, G.: Iccl: Independent and correlative correspondence learning for few-shot image classification. Knowl.-Based Syst. 266, 110412 (2023)","journal-title":"Knowl.-Based Syst."},{"key":"2537_CR43","doi-asserted-by":"crossref","unstructured":"Cho, J.W., Kim, D.-J., Ryu, H., Kweon, I.S.: Generative bias for robust visual question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11681\u201311690. (2023)","DOI":"10.1109\/CVPR52729.2023.01124"},{"key":"2537_CR44","unstructured":"Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y.: Generative adversarial nets. In: Advances in neural information processing systems, pp. 27. (2014)"},{"key":"2537_CR45","doi-asserted-by":"crossref","unstructured":"Grand, G., Belinkov, Y.: Adversarial regularization for visual question answering: Strengths, shortcomings, and side effects, (2019). arXiv preprint arXiv:1906.08430","DOI":"10.18653\/v1\/W19-1801"},{"key":"2537_CR46","doi-asserted-by":"crossref","unstructured":"Belinkov, Y., Poliak, A., Shieber, S.M., Van Durme, B., Rush, A.M.: Don\u2019t take the premise for granted: Mitigating artifacts in natural language inference, (2019). arXiv preprint arXiv:1907.04380","DOI":"10.18653\/v1\/P19-1084"},{"key":"2537_CR47","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.neucom.2022.11.073","volume":"520","author":"H Wu","year":"2023","unstructured":"Wu, H., Zhao, Y., Li, J.: Invariant and consistent: Unsupervised representation learning for few-shot visual recognition. Neurocomputing 520, 1\u201314 (2023)","journal-title":"Neurocomputing"},{"key":"2537_CR48","doi-asserted-by":"crossref","unstructured":"Antol, S., Agrawal, A., Lu, J., Mitchell, M., Batra, D., Zitnick, C.L., Parikh, D.: 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":"2537_CR49","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, pp. 28. (2015)"},{"key":"2537_CR50","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":"2537_CR51","doi-asserted-by":"crossref","unstructured":"Cho, K., Van Merri\u00ebnboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., Bengio, Y.: Learning phrase representations using rnn encoder-decoder for statistical machine translation, (2014). arXiv preprint arXiv:1406.1078","DOI":"10.3115\/v1\/D14-1179"},{"key":"2537_CR52","doi-asserted-by":"publisher","first-page":"6648","DOI":"10.1109\/TMM.2024.3355640","volume":"26","author":"Y Pan","year":"2024","unstructured":"Pan, Y., Liu, J., Jin, L., Li, Z.: Unbiased visual question answering by leveraging instrumental variable. IEEE Trans. Multimedia 26, 6648\u20136662 (2024)","journal-title":"IEEE Trans. Multimedia"},{"key":"2537_CR53","doi-asserted-by":"crossref","unstructured":"Abbasnejad, E., Teney, D., Parvaneh, A., Shi, J., Hengel, A.: Counterfactual vision and language learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10044\u201310054 (2020)","DOI":"10.1109\/CVPR42600.2020.01006"},{"key":"2537_CR54","doi-asserted-by":"crossref","unstructured":"Teney, D., Abbasnejad, E., Hengel, A.: Unshuffling data for improved generalization in visual question answering. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1417\u20131427. (2021)","DOI":"10.1109\/ICCV48922.2021.00145"},{"key":"2537_CR55","first-page":"407","volume":"33","author":"D Teney","year":"2020","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. Adv. Neural. Inf. Process. Syst. 33, 407\u2013417 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2537_CR56","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. arXiv preprint arXiv:2012.11528 (2020)","DOI":"10.24963\/ijcai.2020\/151"},{"key":"2537_CR57","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 the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 3285\u20133292. (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.265"},{"key":"2537_CR58","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Lee, S., Shen, Y., Jin, H., Ghosh, S., Heck, L., Batra, D., Parikh, D.: Taking a hint: Leveraging explanations to make vision and language models more grounded. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2591\u20132600. (2019)","DOI":"10.1109\/ICCV.2019.00268"},{"key":"2537_CR59","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.112629","volume":"305","author":"L Zhao","year":"2024","unstructured":"Zhao, L., Li, K., Qi, J., Sun, Y., Zhu, Z.: Robust visual question answering utilizing bias instances and label imbalance. Knowl.-Based Syst. 305, 112629 (2024)","journal-title":"Knowl.-Based Syst."},{"key":"2537_CR60","doi-asserted-by":"publisher","first-page":"8609","DOI":"10.1109\/TMM.2024.3380259","volume":"26","author":"A Vosoughi","year":"2024","unstructured":"Vosoughi, A., Deng, S., Zhang, S., Tian, Y., Xu, C., Luo, J.: Cross modality bias in visual question answering: A causal view with possible worlds vqa. IEEE Trans. Multimedia 26, 8609\u20138624 (2024)","journal-title":"IEEE Trans. Multimedia"},{"key":"2537_CR61","doi-asserted-by":"crossref","unstructured":"Basu, A., Addepalli, S., Babu, R.V.: Rmlvqa: A margin loss approach for visual question answering with language biases. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11671\u201311680. (2023)","DOI":"10.1109\/CVPR52729.2023.01123"},{"key":"2537_CR62","first-page":"20673","volume":"33","author":"J Nam","year":"2020","unstructured":"Nam, J., Cha, H., Ahn, S., Lee, J., Shin, J.: Learning from failure: De-biasing classifier from biased classifier. Adv. Neural. Inf. Process. Syst. 33, 20673\u201320684 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02537-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-026-02537-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02537-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T11:01:51Z","timestamp":1786964511000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-026-02537-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,27]]},"references-count":62,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026,8]]}},"alternative-id":["2537"],"URL":"https:\/\/doi.org\/10.1007\/s00530-026-02537-x","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,27]]},"assertion":[{"value":"25 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 June 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 July 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no conflict of interest.","order":1,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"472"}}