{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:09:06Z","timestamp":1765343346677,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3758226","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:37:21Z","timestamp":1761377841000},"page":"12837-12843","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["AnaFig: A Human-Aligned Dataset for Scientific Figure Analysis"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5798-6304","authenticated-orcid":false,"given":"Tan","family":"Yue","sequence":"first","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5523-4563","authenticated-orcid":false,"given":"Xuzhao","family":"Shi","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1082-8755","authenticated-orcid":false,"given":"Rui","family":"Mao","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3688-5538","authenticated-orcid":false,"given":"Zilong","family":"Song","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8362-6353","authenticated-orcid":false,"given":"Zonghai","family":"Hu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0396-6703","authenticated-orcid":false,"given":"Dongyan","family":"Zhao","sequence":"additional","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China and State Key Laboratory of General Artificial Intelligence, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al., 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_2_1","unstructured":"Anthropic. 2024a. The Claude 3 Model Family: Opus Sonnet Haiku."},{"key":"e_1_3_2_1_3_1","unstructured":"Anthropic. 2024b. Model Card Addendum: Claude 3.5 Haiku and Upgraded Claude 3.5 Sonnet."},{"key":"e_1_3_2_1_4_1","volume-title":"Qwen-vl: A frontier large vision-language model with versatile abilities. 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 frontier large vision-language model with versatile abilities. arXiv preprint arXiv:2308.12966 (2023)."},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization. 65-72","author":"Banerjee Satanjeev","year":"2005","unstructured":"Satanjeev Banerjee and Alon Lavie. 2005. METEOR: An automatic metric for MT evaluation with improved correlation with human judgments. In Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization. 65-72."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093592"},{"key":"e_1_3_2_1_7_1","volume-title":"Figure captioning with reasoning and sequence-level training. arXiv preprint arXiv:1906.02850","author":"Chen Charles","year":"2019","unstructured":"Charles Chen, Ruiyi Zhang, Eunyee Koh, Sungchul Kim, Scott Cohen, Tong Yu, Ryan Rossi, and Razvan Bunescu. 2019. Figure captioning with reasoning and sequence-level training. arXiv preprint arXiv:1906.02850 (2019)."},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 24185-24198","author":"Chen Zhe","year":"2024","unstructured":"Zhe Chen, Jiannan Wu, Wenhai Wang, Weijie Su, Guo Chen, Sen Xing, Muyan Zhong, Qinglong Zhang, Xizhou Zhu, Lewei Lu, et al., 2024. Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 24185-24198."},{"key":"e_1_3_2_1_9_1","volume-title":"A closer look into automatic evaluation using large language models. arXiv preprint arXiv:2310.05657","author":"Chiang Cheng-Han","year":"2023","unstructured":"Cheng-Han Chiang and Hung-yi Lee. 2023. A closer look into automatic evaluation using large language models. arXiv preprint arXiv:2310.05657 (2023)."},{"key":"e_1_3_2_1_10_1","volume-title":"A survey on image-text multimodal models. arXiv preprint arXiv:2309.15857","author":"Guo Ruifeng","year":"2023","unstructured":"Ruifeng Guo, Jingxuan Wei, Linzhuang Sun, Bihui Yu, Guiyong Chang, Dawei Liu, Sibo Zhang, Zhengbing Yao, Mingjun Xu, and Liping Bu. 2023. A survey on image-text multimodal models. arXiv preprint arXiv:2309.15857 (2023)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.09.116"},{"key":"e_1_3_2_1_12_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] https:\/\/arxiv.org\/abs\/2311.16483"},{"key":"e_1_3_2_1_13_1","volume-title":"A Survey on Quality Metrics for Text-to-Image Generation. arXiv preprint arXiv:2403.11821","author":"Hartwig Sebastian","year":"2024","unstructured":"Sebastian Hartwig, Dominik Engel, Leon Sick, Hannah Kniesel, Tristan Payer, Poonam Poonam, Michael Gl\u00f6ckler, Alex B\u00e4uerle, and Timo Ropinski. 2024. A Survey on Quality Metrics for Text-to-Image Generation. arXiv preprint arXiv:2403.11821 (2024)."},{"key":"e_1_3_2_1_14_1","volume-title":"SciCap: Generating captions for scientific figures. arXiv preprint arXiv:2110.11624","author":"Hsu Ting-Yao","year":"2021","unstructured":"Ting-Yao Hsu, C Lee Giles, and Ting-Hao'Kenneth' Huang. 2021. SciCap: Generating captions for scientific figures. arXiv preprint arXiv:2110.11624 (2021)."},{"key":"e_1_3_2_1_15_1","volume-title":"A survey on evaluation of multimodal large language models. arXiv preprint arXiv:2408.15769","author":"Huang Jiaxing","year":"2024","unstructured":"Jiaxing Huang and Jingyi Zhang. 2024. A survey on evaluation of multimodal large language models. arXiv preprint arXiv:2408.15769 (2024)."},{"key":"e_1_3_2_1_16_1","volume-title":"Xiang Lin, Ahmed Masry, Megh Thakkar, Enamul Hoque, and Shafiq Joty.","author":"Kantharaj Shankar","year":"2022","unstructured":"Shankar Kantharaj, Rixie Tiffany Ko Leong, Xiang Lin, Ahmed Masry, Megh Thakkar, Enamul Hoque, and Shafiq Joty. 2022. Chart-to-text: A large-scale benchmark for chart summarization. arXiv preprint arXiv:2203.06486 (2022)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_2_1_18_1","volume-title":"International conference on machine learning. PMLR","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In International conference on machine learning. PMLR, 19730-19742."},{"key":"e_1_3_2_1_19_1","volume-title":"Exploring diverse methods in visual question answering. arXiv preprint arXiv:2404.13565","author":"Li Panfeng","year":"2024","unstructured":"Panfeng Li, Qikai Yang, Xieming Geng, Wenjing Zhou, Zhicheng Ding, and Yi Nian. 2024. Exploring diverse methods in visual question answering. arXiv preprint arXiv:2404.13565 (2024)."},{"key":"e_1_3_2_1_20_1","volume-title":"Rouge: A package for automatic evaluation of summaries. In Text summarization branches out. 74-81.","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. Rouge: A package for automatic evaluation of summaries. In Text summarization branches out. 74-81."},{"key":"e_1_3_2_1_21_1","first-page":"740","volume-title":"Zurich","author":"Lin Tsung-Yi","year":"2014","unstructured":"Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C Lawrence Zitnick. 2014. Microsoft coco: Common objects in context. In Computer Vision-ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13. Springer, 740-755."},{"key":"e_1_3_2_1_22_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Ling Zhan","year":"2024","unstructured":"Zhan Ling, Yunhao Fang, Xuanlin Li, Zhiao Huang, Mingu Lee, Roland Memisevic, and Hao Su. 2024. Deductive verification of chain-of-thought reasoning. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_23_1","volume-title":"Image Captioning in news report scenario. arXiv preprint arXiv:2403.16209","author":"Liu Tianrui","year":"2024","unstructured":"Tianrui Liu, Qi Cai, Changxin Xu, Bo Hong, Jize Xiong, Yuxin Qiao, and Tsungwei Yang. 2024. Image Captioning in news report scenario. arXiv preprint arXiv:2403.16209 (2024)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-024-10393-y"},{"key":"e_1_3_2_1_25_1","first-page":"7844","volume-title":"Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING","author":"Mao Rui","year":"2024","unstructured":"Rui Mao, Guanyi Chen, Xulang Zhang, Frank Guerin, and Erik Cambria. 2024a. GPTEval: A Survey on Assessments of ChatGPT and GPT-4. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024). ELRA and ICCL, Torino, Italia, 7844-7866."},{"key":"e_1_3_2_1_26_1","volume-title":"Qian Liu, and Erik Cambria.","author":"Mao Rui","year":"2024","unstructured":"Rui Mao, Kai He, Claudia Beth Ong, Qian Liu, and Erik Cambria. 2024b. MetaPro 2.0: Computational Metaphor Processing on the Effectiveness of Anomalous Language Modeling. In Findings of the Association for Computational Linguistics: ACL. Association for Computational Linguistics, Bangkok, Thailand, 9891-9908."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3204972"},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311-318","author":"Papineni Kishore","year":"2002","unstructured":"Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311-318."},{"key":"e_1_3_2_1_29_1","volume-title":"Md Tahmid Rahman Laskar, Md Hamjajul Ashmafee, and Abu Raihan Mostofa Kamal.","author":"Rahman Raian","year":"2023","unstructured":"Raian Rahman, Rizvi Hasan, Abdullah Al Farhad, Md Tahmid Rahman Laskar, Md Hamjajul Ashmafee, and Abu Raihan Mostofa Kamal. 2023. ChartSumm: A Comprehensive Benchmark for Automatic Chart Summarization of Long and Short Summaries.. In Canadian AI."},{"key":"e_1_3_2_1_30_1","volume-title":"Multimodal large language models for image, text, and speech data augmentation: A survey. arXiv preprint arXiv:2501.18648","author":"Sapkota RANJAN","year":"2025","unstructured":"RANJAN Sapkota, SHAINA Raza, MAGED Shoman, A Paudel, and M Karkee. 2025. Multimodal large language models for image, text, and speech data augmentation: A survey. arXiv preprint arXiv:2501.18648 (2025)."},{"key":"e_1_3_2_1_31_1","volume-title":"Ryan Burnell, Libin Bai, Anmol Gulati, et al.","author":"Team Gemini","year":"2024","unstructured":"Gemini Team, Petko Georgiev, Ving Ian Lei, Ryan Burnell, Libin Bai, Anmol Gulati, et al., 2024. Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context. arXiv:2403.05530 [cs.CL] https:\/\/arxiv.org\/abs\/2403.05530"},{"key":"e_1_3_2_1_32_1","unstructured":"Qwen Team. 2025. Qwen2.5 Technical Report. arXiv:2412.15115 [cs.CL] https:\/\/arxiv.org\/abs\/2412.15115"},{"key":"e_1_3_2_1_33_1","volume-title":"The Eleventh International Conference on Learning Representations.","author":"Wang Heng","year":"2022","unstructured":"Heng Wang, Tan Yue, Xiang Ye, Zihang He, Bohan Li, and Yong Li. 2022. Revisit finetuning strategy for few-shot learning to transfer the emdeddings. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3514228"},{"key":"e_1_3_2_1_35_1","volume-title":"Forty-first International Conference on Machine Learning.","author":"Wu Shengqiong","year":"2024","unstructured":"Shengqiong Wu, Hao Fei, Leigang Qu, Wei Ji, and Tat-Seng Chua. 2024. Next-gpt: Any-to-any multimodal llm. In Forty-first International Conference on Machine Learning."},{"key":"e_1_3_2_1_36_1","volume-title":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL). Association for Computational Linguistics","author":"Wu Xiaobao","year":"2025","unstructured":"Xiaobao Wu, Liangming Pan, Yuxi Xie, Ruiwen Zhou, Shuai Zhao, Yubo Ma, Mingzhe Du, Rui Mao, Anh Tuan Luu, and William Yang Wang. 2025. AntiLeak-Bench: Preventing Data Contamination by Automatically Constructing Benchmarks with Updated Real-World Knowledge. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL). Association for Computational Linguistics, Vienna, Austria."},{"key":"e_1_3_2_1_37_1","unstructured":"Renqiu Xia Bo Zhang Hancheng Ye Xiangchao Yan Qi Liu Hongbin Zhou Zijun Chen Min Dou Botian Shi Junchi Yan et al. 2024. Chartx & chartvlm: A versatile benchmark and foundation model for complicated chart reasoning. arXiv preprint arXiv:2402.12185 (2024)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126287"},{"key":"e_1_3_2_1_39_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Yang Xu","year":"2024","unstructured":"Xu Yang, Yongliang Wu, Mingzhuo Yang, Haokun Chen, and Xin Geng. 2024. Exploring diverse in-context configurations for image captioning. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_40_1","unstructured":"Yuan Yao Tianyu Yu Ao Zhang Chongyi Wang Junbo Cui Hongji Zhu Tianchi Cai Haoyu Li Weilin Zhao Zhihui He et al. 2024. MiniCPM-V: A GPT-4V Level MLLM on Your Phone. arXiv preprint arXiv:2408.01800 (2024)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.3233\/JIFS-213022"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10192443"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.3390\/app12094554"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.716"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101921"},{"key":"e_1_3_2_1_46_1","first-page":"14325","volume-title":"Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING","author":"Yue Tan","year":"2024","unstructured":"Tan Yue, Xuzhao Shi, Rui Mao, Zonghai Hu, and Erik Cambria. 2024. SarcNet: a multilingual multimodal sarcasm detection dataset. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024). 14325-14335."},{"key":"e_1_3_2_1_47_1","volume-title":"Mm-llms: Recent advances in multimodal large language models. arXiv preprint arXiv:2401.13601","author":"Zhang Duzhen","year":"2024","unstructured":"Duzhen Zhang, Yahan Yu, Jiahua Dong, Chenxing Li, Dan Su, Chenhui Chu, and Dong Yu. 2024. Mm-llms: Recent advances in multimodal large language models. arXiv preprint arXiv:2401.13601 (2024)."},{"key":"e_1_3_2_1_48_1","volume-title":"Bertscore: Evaluating text generation with bert. arXiv preprint arXiv:1904.09675","author":"Zhang Tianyi","year":"2019","unstructured":"Tianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q Weinberger, and Yoav Artzi. 2019. Bertscore: Evaluating text generation with bert. arXiv preprint arXiv:1904.09675 (2019)."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3758226","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:04:19Z","timestamp":1765343059000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3758226"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":48,"alternative-id":["10.1145\/3746027.3758226","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3758226","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}