{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T22:01:45Z","timestamp":1787695305942,"version":"build-2784847793"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032360328","type":"print"},{"value":"9783032360335","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T00:00:00Z","timestamp":1787443200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T00:00:00Z","timestamp":1787443200000},"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\/978-3-032-36033-5_32","type":"book-chapter","created":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T13:21:38Z","timestamp":1787404898000},"page":"538-554","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["DeChart: A Benchmark and\u00a0Text-Enhanced Chart-to-Table Conversion Method with\u00a0Multimodal LLMs"],"prefix":"10.1007","author":[{"given":"Chen-Yu","family":"Xie","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao-Hui","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng-Lin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,23]]},"reference":[{"issue":"1","key":"32_CR1","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1109\/TVCG.2017.2744684","volume":"24","author":"E Hoque","year":"2017","unstructured":"Hoque, E., Setlur, V., Tory, M., Dykeman, I.: Applying pragmatics principles for interaction with visual analytics. IEEE Trans. Visual Comput. Graphics 24(1), 309\u2013318 (2017)","journal-title":"IEEE Trans. Visual Comput. Graphics"},{"key":"32_CR2","doi-asserted-by":"crossref","unstructured":"Hoque, E., Kavehzadeh, P., Masry, A.: Chart question answering: state of the art and future directions. In: Computer Graphics Forum. vol. 41, pp. 555\u2013572 (2022). Wiley Online Library","DOI":"10.1111\/cgf.14573"},{"key":"32_CR3","doi-asserted-by":"crossref","unstructured":"Jung, D., et al.: Chartsense: interactive data extraction from chart images. In: Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems, pp. 6706\u20136717 (2017)","DOI":"10.1145\/3025453.3025957"},{"key":"32_CR4","unstructured":"Liu, X., Klabjan, D., NBless, P.: Data extraction from charts via single deep neural network. arXiv preprint arXiv:1906.11906 (2019)"},{"key":"32_CR5","doi-asserted-by":"crossref","unstructured":"Rane, C., Subramanya, S.M., Endluri, D.S., Wu, J., Giles, C.L.: Chartreader: automatic parsing of bar-plots. In: 2021 IEEE 22nd International Conference on Information Reuse and Integration for Data Science (IRI), pp. 318\u2013325. IEEE (2021)","DOI":"10.1109\/IRI51335.2021.00050"},{"key":"32_CR6","doi-asserted-by":"crossref","unstructured":"Yan, P., Ahmed, S., Doermann, D.: Context-aware chart element detection. In: International Conference on Document Analysis and Recognition. LNCS, vol. 14187, pp. 218\u2013233. Springer (2023)","DOI":"10.1007\/978-3-031-41676-7_13"},{"key":"32_CR7","doi-asserted-by":"crossref","unstructured":"Luo, J., Li, Z., Wang, J., Lin, C.Y.: Chartocr: data extraction from charts images via a deep hybrid framework. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1917\u20131925 (2021)","DOI":"10.1109\/WACV48630.2021.00196"},{"key":"32_CR8","doi-asserted-by":"crossref","unstructured":"Cheng, Z.Q., Dai, Q., Hauptmann, A.G.: Chartreader: a unified framework for chart derendering and comprehension without heuristic rules. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 22202\u201322213 (2023)","DOI":"10.1109\/ICCV51070.2023.02029"},{"key":"32_CR9","unstructured":"Hassan, M.Y., Singh, M.: Lineex: data extraction from scientific line charts. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 6213\u20136221 (2023)"},{"key":"32_CR10","unstructured":"Xue, W., Chen, D., Yu, B., Chen, Y., Zhou, S., Peng, W.: Chartdetr: a multi-shape detection network for visual chart recognition. arXiv preprint arXiv:2308.07743 (2023)"},{"key":"32_CR11","unstructured":"Lee, K., et al.: Pix2struct: screenshot parsing as pretraining for visual language understanding. In: International Conference on Machine Learning, pp. 18893\u201318912. PMLR (2023)"},{"key":"32_CR12","doi-asserted-by":"publisher","first-page":"34892","DOI":"10.52202\/075280-1516","volume":"36","author":"H Liu","year":"2023","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. Adv. Neural. Inf. Process. Syst. 36, 34892\u201334916 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"32_CR13","doi-asserted-by":"crossref","unstructured":"Liu, F., et al.: Matcha: enhancing visual language pretraining with math reasoning and chart derendering. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 12756\u201312770. Association for Computational Linguistics, Toronto, Canada (2023)","DOI":"10.18653\/v1\/2023.acl-long.714"},{"key":"32_CR14","doi-asserted-by":"crossref","unstructured":"Liu, F., et al.: Deplot: one-shot visual language reasoning by plot-to-table translation. In: Findings of the Association for Computational Linguistics: ACL 2023, pp. 10381\u201310399. Association for Computational Linguistics, Toronto, Canada (2023)","DOI":"10.18653\/v1\/2023.findings-acl.660"},{"key":"32_CR15","unstructured":"Han, Y., et al.: Chartllama: a multimodal LLM for chart understanding and generation. arXiv preprint arXiv:2311.16483 (2023)"},{"key":"32_CR16","doi-asserted-by":"crossref","unstructured":"Kim, W., Park, S., In, Y., Han, S., Park, C.: Simplot: enhancing chart question answering by distilling essentials. In: Findings of the Association for Computational Linguistics: NAACL 2025, pp. 573\u2013593. Association for Computational Linguistics, Albuquerque, New Mexico (2025)","DOI":"10.18653\/v1\/2025.findings-naacl.35"},{"key":"32_CR17","doi-asserted-by":"crossref","unstructured":"Masry, A., Shahmohammadi, M., Parvez, M.R., Hoque, E., Joty, S.: Chartinstruct: instruction tuning for chart comprehension and reasoning. In: Findings of the Association for Computational Linguistics: ACL 2024, pp. 10387\u201310409. Association for Computational Linguistics, Bangkok, Thailand (2024)","DOI":"10.18653\/v1\/2024.findings-acl.619"},{"key":"32_CR18","unstructured":"Bai, S., et\u00a0al.: Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"32_CR19","unstructured":"Chen, Z., et\u00a0al.: Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling. arXiv preprint arXiv:2412.05271 (2024)"},{"key":"32_CR20","doi-asserted-by":"crossref","unstructured":"Masry, A., Long, D.X., Tan, J.Q., Joty, S., Hoque, E.: Chartqa: a benchmark for question answering about charts with visual and logical reasoning. In: Findings of the Association for Computational Linguistics: ACL 2022, pp. 2263\u20132279. Association for Computational Linguistics, Dublin, Ireland (2022)","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"issue":"140","key":"32_CR21","first-page":"1","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(140), 1\u201367 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"32_CR22","doi-asserted-by":"crossref","unstructured":"Masry, A., Kavehzadeh, P., Do, X.L., Hoque, E., Joty, S.: Unichart: a universal vision-language pretrained model for chart comprehension and reasoning. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 14662\u201314684. Association for Computational Linguistics, Singapore (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.906"},{"key":"32_CR23","doi-asserted-by":"crossref","unstructured":"Davila, K., et al.: ICDAR 2019 competition on harvesting raw tables from infographics (chart-infographics). In: 15th International Conference on Document Analysis and Recognition (ICDAR 2019), pp. 1594\u20131599. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00203"},{"key":"32_CR24","doi-asserted-by":"crossref","unstructured":"Davila, K., Xu, F., Ahmed, S., Mendoza, D.A., Setlur, S., Govindaraju, V.: ICPR 2022: challenge on harvesting raw tables from infographics (chart-infographics). In: Proceedings of the 26th International Conference on Pattern Recognition (ICPR), pp. 4995\u20135001. IEEE (2022)","DOI":"10.1109\/ICPR56361.2022.9956289"},{"key":"32_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1007\/978-3-030-86549-8_6","volume-title":"Document Analysis and Recognition - ICDAR 2021","author":"X-H Li","year":"2021","unstructured":"Li, X.-H., Yin, F., Zhang, X.-Y., Liu, C.-L.: Adaptive scaling for archival table structure recognition. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12821, pp. 80\u201395. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86549-8_6"},{"key":"32_CR26","doi-asserted-by":"crossref","unstructured":"Zhang, L., et al.: Tinychart: efficient chart understanding with program-of-thoughts learning and visual token merging. In: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pp. 1882\u20131898. Association for Computational Linguistics, Miami, Florida, USA (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.112"},{"key":"32_CR27","unstructured":"Cui, C., et\u00a0al.: Paddleocr-vl: boosting multilingual document parsing via a 0.9 b ultra-compact vision-language model. arXiv preprint arXiv:2510.14528 (2025)"},{"key":"32_CR28","unstructured":"Cao, X., et al.: What is the visual cognition gap between humans and multimodal LLMs? arXiv preprint arXiv:2406.10424 (2024)"},{"key":"32_CR29","doi-asserted-by":"crossref","unstructured":"Yang, Y., et\u00a0al.: R1-onevision: advancing generalized multimodal reasoning through cross-modal formalization. arXiv preprint arXiv:2503.10615 (2025)","DOI":"10.1109\/ICCV51701.2025.00229"},{"key":"32_CR30","doi-asserted-by":"crossref","unstructured":"Yang, J., Yang, S., Gupta, A.W., Han, R., Fei-Fei, L., Xie, S.: Thinking in space: how multimodal large language models see, remember, and recall spaces. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10632\u201310643 (2025)","DOI":"10.1109\/CVPR52734.2025.00994"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition \u2013 ICDAR 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-36033-5_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T13:21:40Z","timestamp":1787404900000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-36033-5_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,23]]},"ISBN":["9783032360328","9783032360335"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-36033-5_32","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,23]]},"assertion":[{"value":"23 August 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICDAR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Document Analysis and Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vienna","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Austria","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":"31 August 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 September 2026","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":"icdar2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icdar2026.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}