{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:46:01Z","timestamp":1777657561950,"version":"3.51.4"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031705328","type":"print"},{"value":"9783031705335","type":"electronic"}],"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\/978-3-031-70533-5_26","type":"book-chapter","created":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T05:02:25Z","timestamp":1725685345000},"page":"453-469","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["ChartReformer: Natural Language-Driven Chart Image Editing"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1584-2350","authenticated-orcid":false,"given":"Pengyu","family":"Yan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7157-2129","authenticated-orcid":false,"given":"Mahesh","family":"Bhosale","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0515-1287","authenticated-orcid":false,"given":"Jay","family":"Lal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bikhyat","family":"Adhikari","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1639-4561","authenticated-orcid":false,"given":"David","family":"Doermann","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,8]]},"reference":[{"key":"26_CR1","doi-asserted-by":"publisher","unstructured":"Ahmed, S., Yan, P., Doermann, D., Setlur, S., Govindaraju, V.: SpaDen: sparse and dense keypoint estimation for real-world chart understanding. In: Fink, G.A., Jain, R., Kise, K., Zanibbi, R. (eds.) International Conference on Document Analysis and Recognition, vol. 14188, pp. 77\u201393. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-41679-8_5","DOI":"10.1007\/978-3-031-41679-8_5"},{"key":"26_CR2","doi-asserted-by":"crossref","unstructured":"Cheng, Z.Q., Dai, Q., Li, S., Sun, J., Mitamura, T., Hauptmann, A.G.: ChartReader: a unified framework for chart derendering and comprehension without heuristic rules. arXiv preprint arXiv:2304.02173 (2023)","DOI":"10.1109\/ICCV51070.2023.02029"},{"key":"26_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1007\/978-3-030-68793-9_27","volume-title":"Pattern Recognition. ICPR International Workshops and Challenges","author":"K Davila","year":"2021","unstructured":"Davila, K., Tensmeyer, C., Shekhar, S., Singh, H., Setlur, S., Govindaraju, V.: ICPR 2020 - competition on harvesting raw tables from infographics. In: Del Bimbo, A., et al. (eds.) ICPR 2021. LNCS, vol. 12668, pp. 361\u2013380. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-68793-9_27"},{"key":"26_CR4","doi-asserted-by":"crossref","unstructured":"Guan, T., et al.: HallusionBench: an advanced diagnostic suite for entangled language hallucination & visual illusion in large vision-language models (2023)","DOI":"10.1109\/CVPR52733.2024.01363"},{"key":"26_CR5","unstructured":"Han, Y., et al.: ChartLlama: a multimodal LLM for chart understanding and generation. arXiv preprint arXiv:2311.16483 (2023)"},{"issue":"3","key":"26_CR6","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1109\/MCSE.2007.55","volume":"9","author":"JD Hunter","year":"2007","unstructured":"Hunter, J.D.: Matplotlib: A 2D graphics environment. Comput. Sci. Eng. 9(3), 90\u201395 (2007). https:\/\/doi.org\/10.1109\/MCSE.2007.55","journal-title":"Comput. Sci. Eng."},{"key":"26_CR7","doi-asserted-by":"publisher","unstructured":"Kantharaj, S., et al.: Chart-to-text: a large-scale benchmark for chart summarization. In: Muresan, S., Nakov, P., Villavicencio, A. (eds.) Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 4005\u20134023. Association for Computational Linguistics, Dublin, Ireland (2022). https:\/\/doi.org\/10.18653\/v1\/2022.acl-long.277, https:\/\/aclanthology.org\/2022.acl-long.277","DOI":"10.18653\/v1\/2022.acl-long.277"},{"key":"26_CR8","doi-asserted-by":"publisher","unstructured":"Lal, J., Mitkari, A., Bhosale, M., Doermann, D.: LineFormer: line chart data extraction using instance segmentation. In: Fink, G.A., Jain, R., Kise, K., Zanibbi, R. (eds.) International Conference on Document Analysis and Recognition, vol. 14191, pp. 387\u2013400. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-41734-4_24","DOI":"10.1007\/978-3-031-41734-4_24"},{"key":"26_CR9","unstructured":"Lee, K., et al.: Pix2Struct: screenshot parsing as pretraining for visual language understanding. In: Proceedings of the 40th International Conference on Machine Learning. ICML 2023, JMLR.org (2023)"},{"key":"26_CR10","doi-asserted-by":"crossref","unstructured":"Liu, F., et al.: DePlot: one-shot visual language reasoning by plot-to-table translation. arXiv preprint arXiv:2212.10505 (2022)","DOI":"10.18653\/v1\/2023.findings-acl.660"},{"key":"26_CR11","doi-asserted-by":"crossref","unstructured":"Liu, F., et al.: MatCha: enhancing visual language pretraining with math reasoning and chart derendering. arXiv preprint arXiv:2212.09662 (2022)","DOI":"10.18653\/v1\/2023.acl-long.714"},{"key":"26_CR12","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning (2023)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"26_CR13","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":"26_CR14","doi-asserted-by":"publisher","unstructured":"Masry, A., Do, X.L., Tan, J.Q., Joty, S., Hoque, E.: ChartQA: a benchmark for question answering about charts with visual and logical reasoning. In: Muresan, S., Nakov, P., Villavicencio, A. (eds.) Findings of the Association for Computational Linguistics: ACL 2022, pp. 2263\u20132279. Association for Computational Linguistics, Dublin, Ireland (2022). https:\/\/doi.org\/10.18653\/v1\/2022.findings-acl.177, https:\/\/aclanthology.org\/2022.findings-acl.177","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"26_CR15","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. arXiv preprint arXiv:2305.14761 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.906"},{"key":"26_CR16","doi-asserted-by":"publisher","unstructured":"Methani, N., Ganguly, P., Khapra, M.M., Kumar, P.: PlotQA: reasoning over scientific plots. In: 2020 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1516\u20131525 (2020). https:\/\/doi.org\/10.1109\/WACV45572.2020.9093523","DOI":"10.1109\/WACV45572.2020.9093523"},{"key":"26_CR17","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2020.3030378","author":"A Narechania","year":"2020","unstructured":"Narechania, A., Srinivasan, A., Stasko, J.: NL4DV: A toolkit for generating analytic specifications for data visualization from natural language queries. IEEE Trans. Vis. Comput. Graphics (TVCG) (2020). https:\/\/doi.org\/10.1109\/TVCG.2020.3030378","journal-title":"IEEE Trans. Vis. Comput. Graphics (TVCG)"},{"key":"26_CR18","doi-asserted-by":"publisher","unstructured":"Satyanarayan, A., Moritz, D., Wongsuphasawat, K., Heer, J.: Vega-lite: a grammar of interactive graphics. IEEE Trans. Vis. Comput. Graphics 23(1), 341\u2013350 (2017). https:\/\/doi.org\/10.1109\/TVCG.2016.2599030, https:\/\/doi.org\/10.1109\/TVCG.2016.2599030","DOI":"10.1109\/TVCG.2016.2599030"},{"key":"26_CR19","doi-asserted-by":"publisher","unstructured":"Shao, Y., Nakashole, N.: ChartDialogs: plotting from natural language instructions. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 3559\u20133574. Association for Computational Linguistics, Online (2020). https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.328, https:\/\/aclanthology.org\/2020.acl-main.328","DOI":"10.18653\/v1\/2020.acl-main.328"},{"issue":"1","key":"26_CR20","doi-asserted-by":"publisher","first-page":"511","DOI":"10.1109\/TVCG.2017.2745219","volume":"24","author":"A Srinivasan","year":"2018","unstructured":"Srinivasan, A., Stasko, J.: Orko: facilitating multimodal interaction for visual exploration and analysis of networks. IEEE Trans. Visual Comput. Graphics 24(1), 511\u2013521 (2018). https:\/\/doi.org\/10.1109\/TVCG.2017.2745219","journal-title":"IEEE Trans. Visual Comput. Graphics"},{"issue":"4","key":"26_CR21","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A., Sheikh, H., Simoncelli, E.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600\u2013612 (2004). https:\/\/doi.org\/10.1109\/TIP.2003.819861","journal-title":"IEEE Trans. Image Process."},{"key":"26_CR22","doi-asserted-by":"publisher","first-page":"218","DOI":"10.1007\/978-3-031-41676-7_13","volume-title":"Document Analysis and Recognition - ICDAR 2023","author":"P Yan","year":"2023","unstructured":"Yan, P., Ahmed, S., Doermann, D.: Context-aware chart element detection. In: Fink, G.A., Jain, R., Kise, K., Zanibbi, R. (eds.) Document Analysis and Recognition - ICDAR 2023, pp. 218\u2013233. Springer Nature Switzerland, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-41676-7_13"},{"key":"26_CR23","unstructured":"Yang, Z., et al.: The dawn of LMMs: preliminary explorations with GPT-4V(ision) (2023)"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition - ICDAR 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-70533-5_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T21:45:45Z","timestamp":1732743945000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70533-5_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031705328","9783031705335"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70533-5_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"8 September 2024","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":"Athens","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","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":"30 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icdar2024.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}