{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T04:49:59Z","timestamp":1742964599766,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":27,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819787043"},{"type":"electronic","value":"9789819787050"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-981-97-8705-0_25","type":"book-chapter","created":{"date-parts":[[2025,2,7]],"date-time":"2025-02-07T14:37:23Z","timestamp":1738939043000},"page":"369-382","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Post-hoc XAI Method for\u00a0Visual Question Answering (VQA)"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0935-4609","authenticated-orcid":false,"given":"Satya M.","family":"Muddamsetty","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alina B.","family":"Schmidt","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7584-5209","authenticated-orcid":false,"given":"Thomas B.","family":"Moeslund","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,2,8]]},"reference":[{"key":"25_CR1","doi-asserted-by":"publisher","unstructured":"Agrawal, A., et al.: VQA: visual question answering. Int. J. Comput. Vis. 123(1) (2017). www.visualqa.org, https:\/\/doi.org\/10.1007\/s11263-016-0966-6","DOI":"10.1007\/s11263-016-0966-6"},{"key":"25_CR2","doi-asserted-by":"publisher","first-page":"502","DOI":"10.1016\/j.cag.2021.09.002","volume":"102","author":"G Alicioglu","year":"2022","unstructured":"Alicioglu, G., Sun, B.: A survey of visual analytics for explainable artificial intelligence methods. Comput. Graph. 102, 502\u2013520 (2022)","journal-title":"Comput. Graph."},{"key":"25_CR3","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":"25_CR4","doi-asserted-by":"publisher","unstructured":"Andreas, J., Rohrbach, M., Darrell, T., Klein, D.: Learning to compose neural networks for question answering. In: Association for Computational Linguistics, pp. 1545\u20131554, January 2016. https:\/\/doi.org\/10.48550\/arxiv.1601.01705, http:\/\/arxiv.org\/abs\/1601.01705","DOI":"10.48550\/arxiv.1601.01705"},{"key":"25_CR5","unstructured":"Arras, L., Osman, A., Samek, W.: Ground truth evaluation of neural network explanations with clevr-xai. arXiv preprint arXiv:2003.07258 (2020)"},{"key":"25_CR6","doi-asserted-by":"publisher","unstructured":"Arras, L., Osman, A., Samek, W.: CLEVR-XAI: a benchmark dataset for the ground truth evaluation of neural network explanations. Inf. Fusion 81 (2022). https:\/\/doi.org\/10.1016\/j.inffus.2021.11.008","DOI":"10.1016\/j.inffus.2021.11.008"},{"issue":"6","key":"25_CR7","doi-asserted-by":"publisher","first-page":"2245","DOI":"10.3390\/s22062245","volume":"22","author":"Z Boukhers","year":"2022","unstructured":"Boukhers, Z., Hartmann, T., J\u00fcrjens, J.: Coin: counterfactual image generation for visual question answering interpretation. Sensors 22(6), 2245 (2022)","journal-title":"Sensors"},{"key":"25_CR8","doi-asserted-by":"crossref","unstructured":"Das, A., Agrawal, H., Zitnick, C.L., Parikh, D., Batra, D.: Human attention in visual question answering: do humans and deep networks look at the same regions? In: Conference on Empirical Methods in Natural Language Processing (EMNLP) (2016)","DOI":"10.18653\/v1\/D16-1092"},{"key":"25_CR9","doi-asserted-by":"publisher","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 Understand. 163, 90\u2013100 (2017). https:\/\/doi.org\/10.1016\/j.cviu.2017.10.001","DOI":"10.1016\/j.cviu.2017.10.001"},{"issue":"3","key":"25_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3617592","volume":"56","author":"T Ghandi","year":"2023","unstructured":"Ghandi, T., Pourreza, H., Mahyar, H.: Deep learning approaches on image captioning: a review. ACM Comput. Surv. 56(3), 1\u201339 (2023)","journal-title":"ACM Comput. Surv."},{"key":"25_CR11","doi-asserted-by":"publisher","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 (ICCV), pp. 804\u2013813, April 2017. https:\/\/doi.org\/10.48550\/arxiv.1704.05526, http:\/\/arxiv.org\/abs\/1704.05526","DOI":"10.48550\/arxiv.1704.05526"},{"key":"25_CR12","doi-asserted-by":"publisher","unstructured":"Johnson, J., Hariharan, B., van\u00a0der Maaten, L., Fei-Fei, L., Zitnick, C.L., Girshick, R.: CLEVR: a diagnostic dataset for compositional language and elementary visual reasoning. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1988\u20131997, December 2017. https:\/\/doi.org\/10.48550\/arxiv.1612.06890, https:\/\/arxiv.org\/abs\/1612.06890","DOI":"10.48550\/arxiv.1612.06890"},{"key":"25_CR13","doi-asserted-by":"crossref","unstructured":"Johnson, J., et al.: Inferring and executing programs for visual reasoning. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.325"},{"key":"25_CR14","doi-asserted-by":"publisher","first-page":"59800","DOI":"10.1109\/ACCESS.2021.3070212","volume":"9","author":"G Joshi","year":"2021","unstructured":"Joshi, G., Walambe, R., Kotecha, K.: A review on explainability in multimodal deep neural nets. IEEE Access 9, 59800\u201359821 (2021)","journal-title":"IEEE Access"},{"key":"25_CR15","doi-asserted-by":"publisher","first-page":"114602","DOI":"10.1016\/j.eswa.2021.114602","volume":"172","author":"Y Liu","year":"2021","unstructured":"Liu, Y., Sun, P., Wergeles, N., Shang, Y.: A survey and performance evaluation of deep learning methods for small object detection. Expert Syst. Appl. 172, 114602 (2021)","journal-title":"Expert Syst. Appl."},{"key":"25_CR16","doi-asserted-by":"publisher","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 (2016). https:\/\/doi.org\/10.48550\/arXiv.1606.00061","DOI":"10.48550\/arXiv.1606.00061"},{"key":"25_CR17","doi-asserted-by":"publisher","unstructured":"Muddamsetty, S.M., Jahromi, M.N., Ciontos, A.E., Fenoy, L.M., Moeslund, T.B.: Visual explanation of black-box model: Similarity Difference and Uniqueness (SIDU) method. Pattern Recogn. 127, 108604 (2022). https:\/\/doi.org\/10.1016\/j.patcog.2022.108604","DOI":"10.1016\/j.patcog.2022.108604"},{"issue":"11","key":"25_CR18","first-page":"75","volume":"4","author":"KB Obaid","year":"2020","unstructured":"Obaid, K.B., Zeebaree, S., Ahmed, O.M., et al.: Deep learning models based on image classification: a review. Int. J. Sci. Bus. 4(11), 75\u201381 (2020)","journal-title":"Int. J. Sci. Bus."},{"key":"25_CR19","doi-asserted-by":"publisher","unstructured":"Petsiuk, V., Das, A., Saenko, K.: RISE: Randomized input sampling for explanation of black-box models. In: Proceedings of the British Machine Vision Conference (BMVC), June 2018. https:\/\/doi.org\/10.48550\/arxiv.1806.07421, http:\/\/arxiv.org\/abs\/1806.07421","DOI":"10.48550\/arxiv.1806.07421"},{"issue":"11","key":"25_CR20","doi-asserted-by":"publisher","first-page":"2660","DOI":"10.1109\/TNNLS.2016.2599820","volume":"28","author":"W Samek","year":"2016","unstructured":"Samek, W., Binder, A., Montavon, G., Lapuschkin, S., M\u00fcller, K.R.: Evaluating the visualization of what a deep neural network has learned. IEEE Trans. Neural Netw. Learn. Syst. 28(11), 2660\u20132673 (2016)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"25_CR21","doi-asserted-by":"publisher","unstructured":"Samek, W., Montavon, G., Lapuschkin, S., Anders, C.J., M\u00fcller, K.R.: Explaining deep neural networks and beyond: a review of methods and applications. Proc. IEEE 109(3), 247\u2013278 (2021). https:\/\/doi.org\/10.1109\/JPROC.2021.3060483","DOI":"10.1109\/JPROC.2021.3060483"},{"key":"25_CR22","doi-asserted-by":"publisher","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: Visual explanations from deep networks via gradient-based localization. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 618\u2013626, October 2017. https:\/\/doi.org\/10.1007\/s11263-019-01228-7, http:\/\/arxiv.org\/abs\/1610.02391, http:\/\/dx.doi.org\/10.1007\/s11263-019-01228-7","DOI":"10.1007\/s11263-019-01228-7"},{"key":"25_CR23","doi-asserted-by":"crossref","unstructured":"Srivastava, Y., Murali, V., Dubey, S.R., Mukherjee, S.: Visual question answering using deep learning: a survey and performance analysis. In: Computer Vision and Image Processing, August 2021. http:\/\/arxiv.org\/abs\/1909.01860","DOI":"10.1007\/978-981-16-1092-9_7"},{"key":"25_CR24","doi-asserted-by":"crossref","unstructured":"Wang, H., et al.: Score-cam: score-weighted visual explanations for convolutional neural networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 24\u201325 (2020)","DOI":"10.1109\/CVPRW50498.2020.00020"},{"key":"25_CR25","doi-asserted-by":"publisher","unstructured":"Wu, Q., Teney, D., Wang, P., Shen, C., Dick, A., van\u00a0den Hengel, A.: Visual question answering: a survey of methods and datasets. Comput. Vis. Image Understand. 163 (2017). https:\/\/doi.org\/10.1016\/j.cviu.2017.05.001","DOI":"10.1016\/j.cviu.2017.05.001"},{"key":"25_CR26","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1016\/j.cviu.2017.05.001","volume":"163","author":"Q Wu","year":"2017","unstructured":"Wu, Q., Teney, D., Wang, P., Shen, C., Dick, A., Van Den Hengel, A.: Visual question answering: a survey of methods and datasets. Comput. Vis. Image Underst. 163, 21\u201340 (2017)","journal-title":"Comput. Vis. Image Underst."},{"key":"25_CR27","doi-asserted-by":"publisher","unstructured":"Yang, Z., He, X., Gao, J., Deng, L., Smola, A.: Stacked attention networks for image question answering. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 21\u201329, November 2015. https:\/\/doi.org\/10.48550\/arxiv.1511.02274, http:\/\/arxiv.org\/abs\/1511.02274","DOI":"10.48550\/arxiv.1511.02274"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-8705-0_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,7]],"date-time":"2025-02-07T14:37:33Z","timestamp":1738939053000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8705-0_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819787043","9789819787050"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8705-0_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"8 February 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPRAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition and Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Jeju Island","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","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":"18 June 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 June 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icprai2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/brain.korea.ac.kr\/icprai2024\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}