{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,11]],"date-time":"2026-01-11T12:06:31Z","timestamp":1768133191290,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":26,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819786190","type":"print"},{"value":"9789819786206","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T00:00:00Z","timestamp":1729382400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T00:00:00Z","timestamp":1729382400000},"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\/978-981-97-8620-6_2","type":"book-chapter","created":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T21:02:10Z","timestamp":1729371730000},"page":"18-33","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Charting the Uncharted: Building and Analyzing a Multifaceted Chart Question Answering Dataset for Complex Logical Reasoning Process"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2843-898X","authenticated-orcid":false,"given":"Anran","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuwen","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yujia","family":"Xia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9146-051X","authenticated-orcid":false,"given":"Xingjiao","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianlong","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,20]]},"reference":[{"key":"2_CR1","unstructured":"Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F.L., Almeida, D., Altenschmidt, J., Altman, S., Anadkat, S., et\u00a0al.: Gpt-4 technical report. arXiv:2303.08774 (2023)"},{"key":"2_CR2","unstructured":"Bai, J., Bai, S., Yang, S., Wang, S., Tan, S., Wang, P., Lin, J., Zhou, C., Zhou, J.: Qwen-vl: A frontier large vision-language model with versatile abilities. arXiv:2308.12966 (2023)"},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Chaudhry, R., Shekhar, S., Gupta, U., Maneriker, P., Bansal, P., Joshi, A.: Leaf-qa: Locate, encode & attend for figure question answering. In: IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 3512\u20133521 (2020)","DOI":"10.1109\/WACV45572.2020.9093269"},{"issue":"11","key":"2_CR4","doi-asserted-by":"publisher","first-page":"3799","DOI":"10.1109\/TPAMI.2020.2992028","volume":"43","author":"K Davila","year":"2020","unstructured":"Davila, K., Setlur, S., Doermann, D., Kota, B.U., Govindaraju, V.: Chart mining: a survey of methods for automated chart analysis. IEEE Trans. Pattern Anal. Mach. Intell. 43(11), 3799\u20133819 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2_CR5","unstructured":"Dong, X., Zhang, P., Zang, Y., Cao, Y., Wang, B., Ouyang, L., Wei, X., Zhang, S., Duan, H., Cao, M., et\u00a0al.: Internlm-xcomposer2: mastering free-form text-image composition and comprehension in vision-language large model. arXiv:2401.16420 (2024)"},{"key":"2_CR6","unstructured":"Hu, J., Yao, Y., Wang, C., Wang, S., Pan, Y., Chen, Q., Yu, T., Wu, H., Zhao, Y., Zhang, H., et\u00a0al.: Large multilingual models pivot zero-shot multimodal learning across languages. arXiv:2308.12038 (2023)"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Kafle, K., Price, B., Cohen, S., Kanan, C.: Dvqa: Understanding data visualizations via question answering. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5648\u20135656 (2018)","DOI":"10.1109\/CVPR.2018.00592"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Kafle, K., Shrestha, R., Cohen, S., Price, B., Kanan, C.: Answering questions about data visualizations using efficient bimodal fusion. In: IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1498\u20131507 (2020)","DOI":"10.1109\/WACV45572.2020.9093494"},{"key":"2_CR9","unstructured":"Kahou, S.E., Michalski, V., Atkinson, A., K\u00e1d\u00e1r, \u00c1., Trischler, A., Bengio, Y.: Figureqa: an annotated figure dataset for visual reasoning (2017)"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Kim, D.H., Hoque, E., Agrawala, M.: Answering questions about charts and generating visual explanations. In: Proceedings of the CHI Conference on Human Factors in Computing Systems (CHI), pp. 1\u201313 (2020)","DOI":"10.1145\/3313831.3376467"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Kim, G., Hong, T., Yim, M., Nam, J., Park, J., Yim, J., Hwang, W., Yun, S., Han, D., Park, S.: Ocr-free document understanding transformer. In: European Conference on Computer Vision (ECCV), pp. 498\u2013517. Springer (2022)","DOI":"10.1007\/978-3-031-19815-1_29"},{"key":"2_CR12","unstructured":"Lee, K., Joshi, M., Turc, I.R., Hu, H., Liu, F., Eisenschlos, J.M., Khandelwal, U., Shaw, P., Chang, M.W., Toutanova, K.: Pix2struct: Screenshot parsing as pretraining for visual language understanding. In: Proceedings of International Conference on Machine Learning (ICML), pp. 18893\u201318912. PMLR (2023)"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Levy, M., Ben-Ari, R., Lischinski, D.: Classification-regression for chart comprehension. In: European Conference on Computer Vision (ECCV), pp. 469\u2013484. Springer (2022)","DOI":"10.1007\/978-3-031-20059-5_27"},{"issue":"2","key":"2_CR14","first-page":"136","volume":"2","author":"D Li","year":"2018","unstructured":"Li, D., Mei, H., Shen, Y., Su, S., Zhang, W., Wang, J., Zu, M., Chen, W.: Echarts: a declarative framework for rapid construction of web-based visualization. Vis. Inf. 2(2), 136\u2013146 (2018)","journal-title":"Vis. Inf."},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"Liu, F., Piccinno, F., Krichene, S., Pang, C., Lee, K., Joshi, M., Altun, Y., Collier, N., Eisenschlos, J.M.: Matcha: enhancing visual language pretraining with math reasoning and chart derendering (2022)","DOI":"10.18653\/v1\/2023.acl-long.714"},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. arXiv:2310.03744 (2023)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"Ma, W., Zhang, H., Yan, S., Yao, G., Huang, Y., Li, H., Wu, Y., Jin, L.: Towards an efficient framework for data extraction from chart images. In: International Conference on Document Analysis and Recognition (ICDAR), pp. 583\u2013597. Springer (2021)","DOI":"10.1007\/978-3-030-86549-8_37"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Masry, A., Long, D., Tan, J.Q., Joty, S., Hoque, E.: Chartqa: a benchmark for question answering about charts with visual and logical reasoning. In: ACL Findings, pp. 2263\u20132279 (2022)","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"2_CR19","doi-asserted-by":"crossref","unstructured":"Methani, N., Ganguly, P., Khapra, M.M., Kumar, P.: Plotqa: Reasoning over scientific plots. In: IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1527\u20131536 (2020)","DOI":"10.1109\/WACV45572.2020.9093523"},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"Reddy, R., Ramesh, R., Deshpande, A., Khapra, M.M.: Figurenet: a deep learning model for question-answering on scientific plots. In: International Joint Conference on Neural Networks (IJCNN), pp.\u00a01\u20138 (2019)","DOI":"10.1109\/IJCNN.2019.8851830"},{"key":"2_CR21","unstructured":"Santoro, A., Raposo, D., Barrett, D.G., Malinowski, M., Pascanu, R., Battaglia, P., Lillicrap, T.: A simple neural network module for relational reasoning. In: Advances in Neural Information Processing Systems (NeurIPS), 30 (2017)"},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"Singh, H., Shekhar, S.: Stl-cqa: structure-based transformers with localization and encoding for chart question answering. In: Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 3275\u20133284 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.264"},{"key":"2_CR23","unstructured":"Wei, J., Wang, X., Schuurmans, D., Bosma, M., Xia, F., Chi, E., Le, Q.V., Zhou, D., et al.: Chain-of-thought prompting elicits reasoning in large language models, vol. 35, pp. 24824\u201324837 (2022)"},{"key":"2_CR24","unstructured":"Xia, R., Zhang, B., Ye, H., Yan, X., Liu, Q., Zhou, H., Chen, Z., Dou, M., Shi, B., Yan, J., et\u00a0al.: Chartx & chartvlm: a versatile benchmark and foundation model for complicated chart reasoning. arXiv:2402.12185 (2024)"},{"key":"2_CR25","doi-asserted-by":"crossref","unstructured":"Ye, Q., Xu, H., Ye, J., Yan, M., Liu, H., Qian, Q., Zhang, J., Huang, F., Zhou, J.: mplug-owl2: revolutionizing multi-modal large language model with modality collaboration. arXiv:2311.04257 (2023)","DOI":"10.1109\/CVPR52733.2024.01239"},{"key":"2_CR26","doi-asserted-by":"crossref","unstructured":"Zou, J., Wu, G., Xue, T., Wu, Q.: An affinity-driven relation network for figure question answering. In: IEEE International Conference on Multimedia & Expo (ICME), pp.\u00a01\u20136 (2020)","DOI":"10.1109\/ICME46284.2020.9102911"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-8620-6_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T21:09:35Z","timestamp":1729372175000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8620-6_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,20]]},"ISBN":["9789819786190","9789819786206"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8620-6_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,20]]},"assertion":[{"value":"20 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Urumqi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2024.prcv.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}