{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,16]],"date-time":"2026-11-16T17:15:59Z","timestamp":1794849359216,"version":"4.9.1"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032313966","type":"print"},{"value":"9783032313973","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T00:00:00Z","timestamp":1785888000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T00:00:00Z","timestamp":1785888000000},"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":[[2027]]},"DOI":"10.1007\/978-3-032-31397-3_8","type":"book-chapter","created":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T07:07:29Z","timestamp":1785827249000},"page":"111-125","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Checkmate: Interpretable and\u00a0Explainable RSVQA is the\u00a0Endgame"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-8487-7890","authenticated-orcid":false,"given":"Lucrezia","family":"Tosato","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christel","family":"Tartini-Chappuis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Syrielle","family":"Montariol","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Flora","family":"Weissgerber","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sylvain","family":"Lobry","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Devis","family":"Tuia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,5]]},"reference":[{"key":"8_CR1","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: IEEE\/CVF ICCV, pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"8_CR2","doi-asserted-by":"crossref","unstructured":"Boussaid, H., Tosato, L., Weissgerber, F., Kurtz, C., Wendling, L., Lobry, S.: Visual question answering on multiple remote sensing image modalities. In: Proceedings of the 2025 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). IEEE, Nashville (2025)","DOI":"10.1109\/CVPRW67362.2025.00218"},{"key":"8_CR3","doi-asserted-by":"crossref","unstructured":"Chappuis, C., S\u00fcmb\u00fcl, G., Montariol, S., Lobry, S., Tuia, D.: PAN-RSVQA: vision foundation models as pseudo-annotators for remote sensing visual question answering. In: Proceedings of the 2025 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). IEEE, Nashville (2025)","DOI":"10.1109\/CVPRW67362.2025.00283"},{"key":"8_CR4","unstructured":"Chappuis, C., Walt, E., Mendez, V., Lobry, S., Le Saux, B., Tuia, D.: Evaluating language biases in remote sensing VQA.. IEEE Geosci. Remote Sens. Mag. (GRSM) (2025, accepted for publication)"},{"key":"8_CR5","doi-asserted-by":"crossref","unstructured":"Chappuis, C., Zermatten, V., Lobry, S., Le Saux, B., Tuia, D.: Prompt-RSVQA: prompting visual context to a language model for remote sensing visual question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1372\u20131381 (2022)","DOI":"10.1109\/CVPRW56347.2022.00143"},{"key":"8_CR6","doi-asserted-by":"crossref","unstructured":"Clasen, K.N., Hackel, L., Burgert, T., Sumbul, G., Demir, B., Markl, V.: reben: refined bigearthnet dataset for remote sensing image analysis. arXiv preprint arXiv:2407.03653 (2024)","DOI":"10.1109\/IGARSS55030.2025.11242834"},{"key":"8_CR7","doi-asserted-by":"publisher","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: Pre-training of deep bidirectional transformers for language understanding. In: Burstein, J., Doran, C., Solorio, T. (eds.) Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). pp. 4171\u20134186. Association for Computational Linguistics, Minneapolis, Minnesota (Jun 2019). https:\/\/doi.org\/10.18653\/v1\/N19-1423, https:\/\/aclanthology.org\/N19-1423\/","DOI":"10.18653\/v1\/N19-1423"},{"key":"8_CR8","unstructured":"Dosovitskiy, A., et al.: An image is worth $$16 \\times 16$$ words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"8_CR9","doi-asserted-by":"crossref","unstructured":"Felix, R., Repasky, B., Hodge, S., Zolfaghari, R., Abbasnejad, E., Sherrah, J.: Cross-modal visual question answering for remote sensing data. In: The International Conference on Digital Image Computing: Techniques and Applications (DICTA 2021). In: 2021 Digital Image Computing: Techniques and Applications (DICTA), pp. 1\u20139. IEEE (2021)","DOI":"10.1109\/DICTA52665.2021.9647287"},{"key":"8_CR10","doi-asserted-by":"crossref","unstructured":"Ferrario, A., Loi, M.: How explainability contributes to trust in AI. In: Proceedings of the 2022 ACM Conference on Fairness, Accountability, and Transparency, pp. 1457\u20131466 (2022)","DOI":"10.1145\/3531146.3533202"},{"key":"8_CR11","doi-asserted-by":"crossref","unstructured":"Gilpin, L.H., Bau, D., Yuan, B.Z., Bajwa, A., Specter, M., Kagal, L.: Explaining explanations: an overview of interpretability of machine learning. In: IEEE 5th International Conference on Data Science and Advanced Analytics (DSAA), pp. 80\u201389. IEEE (2018)","DOI":"10.1109\/DSAA.2018.00018"},{"key":"8_CR12","doi-asserted-by":"crossref","unstructured":"Guo, H., Su, X., Wu, C., Du, B., Zhang, L., Li, D.: Remote sensing chatgpt: solving remote sensing tasks with chatgpt and visual models. In: IGARSS 2024-2024 IEEE International Geoscience and Remote Sensing Symposium, pp. 11474\u201311478. IEEE (2024)","DOI":"10.1109\/IGARSS53475.2024.10640736"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Hackel, L., Clasen, K.N., Ravanbakhsh, M., Demir, B.: Lit-4-RSVQA: lightweight transformer-based visual question answering in remote sensing. In: IGARSS 2023-2023 IEEE International Geoscience and Remote Sensing Symposium, pp. 2231\u20132234. IEEE (2023)","DOI":"10.1109\/IGARSS52108.2023.10281674"},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"He, J., et al.: Pers: parameter-efficient multi-modal transfer learning for remote sensing visual question answering. IEEE J. Sel. Topics Appl. Earth Obs. Remote Sens. (2024)","DOI":"10.1109\/JSTARS.2024.3447086"},{"key":"8_CR15","doi-asserted-by":"crossref","unstructured":"Hichem, B., Kwon, N., Kurtz, C., Wendling, L., Lobry, S.: LLM-driven data augmentation for visual question answering. In: 2025 Joint Urban Remote Sensing Event (JURSE), pp.\u00a01\u20134. IEEE (2025)","DOI":"10.1109\/JURSE60372.2025.11076083"},{"key":"8_CR16","doi-asserted-by":"crossref","unstructured":"Jiao, X., et al.: Tinybert: distilling BERT for natural language understanding. arXiv preprint arXiv:1909.10351 (2019)","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"8_CR17","unstructured":"Li, L.H., Yatskar, M., Yin, D., Hsieh, C.J., Chang, K.W.: Visualbert: a simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557 (2019)"},{"key":"8_CR18","doi-asserted-by":"crossref","unstructured":"Liu, B., et al.: Gemex: a large-scale, groundable, and explainable medical VQA benchmark for chest x-ray diagnosis. arXiv preprint arXiv:2411.16778 (2024)","DOI":"10.1109\/ICCV51701.2025.01979"},{"key":"8_CR19","doi-asserted-by":"crossref","unstructured":"Lobry, S., Demir, B., Tuia, D.: RSVQA meets bigearthnet: a new, large-scale, visual question answering dataset for remote sensing. In: 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS, pp. 1218\u20131221. IEEE (2021)","DOI":"10.1109\/IGARSS47720.2021.9553307"},{"key":"8_CR20","doi-asserted-by":"crossref","unstructured":"Lobry, S., Murray, J., Marcos, D., Tuia, D.: Visual question answering from remote sensing images. In: IGARSS 2019-2019 IEEE International Geoscience and Remote Sensing Symposium, pp. 4951\u20134954. IEEE (2019)","DOI":"10.1109\/IGARSS.2019.8898891"},{"key":"8_CR21","unstructured":"Marcinkevi\u010ds, R., Vogt, J.E.: Interpretability and explainability: a machine learning zoo mini-tour. arXiv preprint arXiv:2012.01805 (2020)"},{"key":"8_CR22","doi-asserted-by":"publisher","first-page":"89644","DOI":"10.1109\/ACCESS.2021.3090981","volume":"9","author":"M Rahnemoonfar","year":"2021","unstructured":"Rahnemoonfar, M., Chowdhury, T., Sarkar, A., Varshney, D., Yari, M., Murphy, R.R.: Floodnet: a high resolution aerial imagery dataset for post flood scene understanding. IEEE Access 9, 89644\u201389654 (2021)","journal-title":"IEEE Access"},{"key":"8_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"issue":"5","key":"8_CR24","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1038\/s42256-019-0048-x","volume":"1","author":"C Rudin","year":"2019","unstructured":"Rudin, C.: Stop explaining black box machine learning models for high stakes decisions and use interpretable models instead. Na. Mach. Intell. 1(5), 206\u2013215 (2019)","journal-title":"Na. Mach. Intell."},{"key":"8_CR25","unstructured":"Sanh, V., Debut, L., Chaumond, J., Wolf, T.: Distilbert, a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108 (2019)"},{"key":"8_CR26","doi-asserted-by":"crossref","unstructured":"Siebert, T., Clasen, K.N., Ravanbakhsh, M., Demir, B.: Multi-modal fusion transformer for visual question answering in remote sensing. In: Image and Signal Processing for Remote Sensing XXVIII, vol. 12267, pp. 162\u2013170. SPIE (2022)","DOI":"10.1117\/12.2636276"},{"key":"8_CR27","unstructured":"Su, W., et al.: VL-BERT: pre-training of generic visual-linguistic representations. arXiv preprint arXiv:1908.08530 (2019)"},{"key":"8_CR28","doi-asserted-by":"crossref","unstructured":"Sumbul, G., Charfuelan, M., Demir, B., Markl, V.: Bigearthnet: a large-scale benchmark archive for remote sensing image understanding. In: IGARSS 2019-2019 IEEE International Geoscience and Remote Sensing Symposium, pp. 5901\u20135904. IEEE (2019)","DOI":"10.1109\/IGARSS.2019.8900532"},{"key":"8_CR29","doi-asserted-by":"crossref","unstructured":"Tosato, L., Boussaid, H., Weissgerber, F., Kurtz, C., Wendling, L., Lobry, S.: Segmentation-guided attention for visual question answering from remote sensing images. In: IGARSS 2024-2024 IEEE International Geoscience and Remote Sensing Symposium, pp. 2750\u20132754. IEEE (2024)","DOI":"10.1109\/IGARSS53475.2024.10642082"},{"key":"#cr-split#-8_CR30.1","unstructured":"Tosato, L., Lobry, S., Weissgerber, F., Wendling, L.: Can SAR improve RSVQA performance? In: EUSAR 2024"},{"key":"#cr-split#-8_CR30.2","unstructured":"15th European Conference on Synthetic Aperture Radar, VDE Verlag (2024)"},{"key":"8_CR31","doi-asserted-by":"crossref","unstructured":"Wang, Y., Ghamisi, P.: RSAdapter: adapting multimodal models for remote sensing visual question answering. IEEE Trans. Geosci. Remote Sens. (2024)","DOI":"10.1109\/TGRS.2024.3413174"},{"key":"8_CR32","doi-asserted-by":"crossref","unstructured":"Xia, J., Chen, H., Broni-Bediako, C., Wei, Y., Song, J., Yokoya, N.: Openearthmap-SAR: a benchmark synthetic aperture radar dataset for global high-resolution land cover mapping. arXiv preprint arXiv:2501.10891 (2025)","DOI":"10.1109\/MGRS.2025.3599512"},{"key":"8_CR33","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., Luo, P.: Segformer: simple and efficient design for semantic segmentation with transformers. In: Advances in Neural Information Processing Systems, vol. 34, pp. 12077\u201312090 (2021)"},{"key":"8_CR34","unstructured":"Xiong, Z., et al.: Neural plasticity-inspired foundation model for observing the earth crossing modalities. arXiv e-prints, pp. arXiv\u20132403 (2024)"},{"key":"8_CR35","doi-asserted-by":"crossref","unstructured":"Yuan, Z., Mou, L., Zhu, X.X.: Multilingual augmentation for robust visual question answering in remote sensing images. In: 2023 Joint Urban Remote Sensing Event (JURSE), pp.\u00a01\u20134. IEEE (2023)","DOI":"10.1109\/JURSE57346.2023.10144189"},{"key":"8_CR36","doi-asserted-by":"crossref","unstructured":"Zhang, H., Wang, K., Zhang, L., Wang, B., Li, X.: Hierarchical multi-modality graph reasoning for remote sensing visual question answering. IEEE Trans. Geosci. Remote Sensing (2024)","DOI":"10.1109\/TGRS.2024.3502800"},{"key":"8_CR37","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2020.3040221","volume":"60","author":"X Zheng","year":"2021","unstructured":"Zheng, X., Wang, B., Du, X., Lu, X.: Mutual attention inception network for remote sensing visual question answering. IEEE Trans. Geosci. Remote Sens. 60, 1\u201314 (2021)","journal-title":"IEEE Trans. Geosci. Remote Sens."}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-31397-3_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T07:07:45Z","timestamp":1785827265000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-31397-3_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,5]]},"ISBN":["9783032313966","9783032313973"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-31397-3_8","relation":{"is-part-of":[{"id-type":"doi","id":"https:\/\/doi.org\/10.1007\/978-3-032-31397-3","asserted-by":"object"}]},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,5]]},"assertion":[{"value":"5 August 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lyon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 August 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 August 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2026.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}