{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T16:34:25Z","timestamp":1784392465279,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680790","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:49Z","timestamp":1729925989000},"page":"3917-3925","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["NovaChart: A Large-scale Dataset towards Chart Understanding and Generation of Multimodal Large Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0993-8495","authenticated-orcid":false,"given":"Linmei","family":"Hu","sequence":"first","affiliation":[{"name":"SCST, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3290-7303","authenticated-orcid":false,"given":"Duokang","family":"Wang","sequence":"additional","affiliation":[{"name":"SCS, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4318-813X","authenticated-orcid":false,"given":"Yiming","family":"Pan","sequence":"additional","affiliation":[{"name":"SCST, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3430-4048","authenticated-orcid":false,"given":"Jifan","family":"Yu","sequence":"additional","affiliation":[{"name":"DCST, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8559-2628","authenticated-orcid":false,"given":"Yingxia","family":"Shao","sequence":"additional","affiliation":[{"name":"SCS, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1691-1584","authenticated-orcid":false,"given":"Chong","family":"Feng","sequence":"additional","affiliation":[{"name":"SCST, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1476-0273","authenticated-orcid":false,"given":"Liqiang","family":"Nie","sequence":"additional","affiliation":[{"name":"SCST, Harbin Institute of Technology (Shenzhen), Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00904"},{"key":"e_1_3_2_1_2_1","volume-title":"Localization, Text Reading, and Beyond. arXiv preprint arXiv:2308.12966","author":"Bai Jinze","year":"2023","unstructured":"Jinze Bai, Shuai Bai, Shusheng Yang, Shijie Wang, Sinan Tan, Peng Wang, Junyang Lin, Chang Zhou, and Jingren Zhou. 2023. Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond. arXiv preprint arXiv:2308.12966 (2023)."},{"key":"e_1_3_2_1_3_1","volume-title":"Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic. arxiv: 2306.15195 [cs.CV]","author":"Chen Keqin","year":"2023","unstructured":"Keqin Chen, Zhao Zhang, Weili Zeng, Richong Zhang, Feng Zhu, and Rui Zhao. 2023. Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic. arxiv: 2306.15195 [cs.CV]"},{"key":"e_1_3_2_1_4_1","unstructured":"Jinlan Fu See-Kiong Ng Zhengbao Jiang and Pengfei Liu. 2023. GPTScore: Evaluate as You Desire. arxiv: 2302.04166 [cs.CL]"},{"key":"e_1_3_2_1_5_1","volume-title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering. In Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Goyal Yash","year":"2017","unstructured":"Yash Goyal, Tejas Khot, Douglas Summers-Stay, Dhruv Batra, and Devi Parikh. 2017. Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering. In Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Tianrui Guan Fuxiao Liu Xiyang Wu Ruiqi Xian Zongxia Li Xiaoyu Liu Xijun Wang Lichang Chen Furong Huang Yaser Yacoob Dinesh Manocha and Tianyi Zhou. 2024. HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models. arxiv: 2310.14566 [cs.CV]","DOI":"10.1109\/CVPR52733.2024.01363"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00380"},{"key":"e_1_3_2_1_8_1","unstructured":"Yucheng Han Chi Zhang Xin Chen Xu Yang Zhibin Wang Gang Yu Bin Fu and Hanwang Zhang. 2023. ChartLlama: A Multimodal LLM for Chart Understanding and Generation. arxiv: 2311.16483 [cs.CV]"},{"key":"e_1_3_2_1_9_1","unstructured":"Wenyi Hong Weihan Wang Qingsong Lv Jiazheng Xu Wenmeng Yu Junhui Ji Yan Wang Zihan Wang Yuxiao Dong Ming Ding and Jie Tang. 2023. CogAgent: A Visual Language Model for GUI Agents. arxiv: 2312.08914 [cs.CV]"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_12_1","unstructured":"Alex Krizhevsky. 2009. Learning Multiple Layers of Features from Tiny Images. https:\/\/api.semanticscholar.org\/CorpusID:18268744"},{"key":"e_1_3_2_1_13_1","unstructured":"Vladimir I Levenshtein et al. 1966. Binary codes capable of correcting deletions insertions and reversals. In Soviet physics doklady Vol. 10. Soviet Union 707--710."},{"key":"e_1_3_2_1_14_1","unstructured":"Bo Li Yuanhan Zhang Liangyu Chen Jinghao Wang Fanyi Pu Jingkang Yang Chunyuan Li and Ziwei Liu. 2023. MIMIC-IT: Multi-Modal In-Context Instruction Tuning. (2023). arxiv: 2306.05425 [cs.CV]"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--3--319--10602--1_48"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.660"},{"key":"e_1_3_2_1_17_1","volume-title":"2023 d. MMC: Advancing Multimodal Chart Understanding with Large-scale Instruction Tuning. arXiv preprint arXiv:2311.10774","author":"Liu Fuxiao","year":"2023","unstructured":"Fuxiao Liu, Xiaoyang Wang, Wenlin Yao, Jianshu Chen, Kaiqiang Song, Sangwoo Cho, Yaser Yacoob, and Dong Yu. 2023 d. MMC: Advancing Multimodal Chart Understanding with Large-scale Instruction Tuning. arXiv preprint arXiv:2311.10774 (2023)."},{"key":"e_1_3_2_1_18_1","unstructured":"Haotian Liu Chunyuan Li Yuheng Li and Yong Jae Lee. 2023. Improved Baselines with Visual Instruction Tuning."},{"key":"e_1_3_2_1_19_1","unstructured":"Haotian Liu Chunyuan Li Qingyang Wu and Yong Jae Lee. 2023. Visual Instruction Tuning. In NeurIPS."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/22949.22950"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.906"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093523"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3615120"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-019-00588-3"},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings, Part II 16","author":"Sidorov Oleksii","year":"2020","unstructured":"Oleksii Sidorov, Ronghang Hu, Marcus Rohrbach, and Amanpreet Singh. 2020. Textcaps: a dataset for image captioning with reading comprehension. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part II 16. Springer, 742--758."},{"key":"e_1_3_2_1_29_1","unstructured":"Weihan Wang Qingsong Lv Wenmeng Yu Wenyi Hong Ji Qi Yan Wang Junhui Ji Zhuoyi Yang Lei Zhao Xixuan Song Jiazheng Xu Bin Xu Juanzi Li Yuxiao Dong Ming Ding and Jie Tang. 2023. CogVLM: Visual Expert for Pretrained Language Models. arxiv: 2311.03079 [cs.CV]"},{"key":"e_1_3_2_1_30_1","unstructured":"Renqiu Xia Bo Zhang Haoyang Peng Hancheng Ye Xiangchao Yan Peng Ye Botian Shi Yu Qiao and Junchi Yan. 2024. StructChart: Perception Structuring Reasoning for Visual Chart Understanding. arxiv: 2309.11268 [cs.CV]"},{"key":"e_1_3_2_1_31_1","unstructured":"Renqiu Xia Bo Zhang Hancheng Ye Xiangchao Yan Qi Liu Hongbin Zhou Zijun Chen Min Dou Botian Shi Junchi Yan and Yu Qiao. 2024. ChartX & ChartVLM: A Versatile Benchmark and Foundation Model for Complicated Chart Reasoning. arxiv: 2402.12185 [cs.CV]"},{"key":"e_1_3_2_1_32_1","unstructured":"Zhengzhuo Xu Sinan Du Yiyan Qi Chengjin Xu Chun Yuan and Jian Guo. 2024. ChartBench: A Benchmark for Complex Visual Reasoning in Charts. arxiv: 2312.15915 [cs.CV]"},{"key":"e_1_3_2_1_33_1","unstructured":"Zhengyuan Yang Linjie Li Kevin Lin Jianfeng Wang Chung-Ching Lin Zicheng Liu and Lijuan Wang. 2023. The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision). arxiv: 2309.17421 [cs.CV]"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_35_1","volume-title":"Kola: Carefully benchmarking world knowledge of large language models. arXiv preprint arXiv:2306.09296","author":"Yu Jifan","year":"2023","unstructured":"Jifan Yu, Xiaozhi Wang, Shangqing Tu, Shulin Cao, Daniel Zhang-Li, Xin Lv, Hao Peng, Zijun Yao, Xiaohan Zhang, Hanming Li, et al. 2023. Kola: Carefully benchmarking world knowledge of large language models. arXiv preprint arXiv:2306.09296 (2023)."},{"key":"e_1_3_2_1_36_1","volume-title":"Proceedings, Part II 14","author":"Yu Licheng","year":"2016","unstructured":"Licheng Yu, Patrick Poirson, Shan Yang, Alexander C Berg, and Tamara L Berg. 2016. Modeling context in referring expressions. In Computer Vision--ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11--14, 2016, Proceedings, Part II 14. Springer, 69--85."},{"key":"e_1_3_2_1_37_1","volume-title":"InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Composition. arXiv preprint arXiv:2309.15112","author":"Zhang Pan","year":"2023","unstructured":"Pan Zhang, Xiaoyi Dong, Bin Wang, Yuhang Cao, Chao Xu, Linke Ouyang, Zhiyuan Zhao, Shuangrui Ding, Songyang Zhang, Haodong Duan, Wenwei Zhang, Hang Yan, Xinyue Zhang, Wei Li, Jingwen Li, Kai Chen, Conghui He, Xingcheng Zhang, Yu Qiao, Dahua Lin, and Jiaqi Wang. 2023. InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Composition. arXiv preprint arXiv:2309.15112 (2023)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.540"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680790","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680790","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:07Z","timestamp":1750295887000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680790"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":37,"alternative-id":["10.1145\/3664647.3680790","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680790","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}