{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T19:10:05Z","timestamp":1755889805138,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":49,"publisher":"ACM","funder":[{"name":"the Natural Science Basic Research Program of Shaanxi","award":["2023-JC-YB-593"],"award-info":[{"award-number":["2023-JC-YB-593"]}]},{"DOI":"10.13039\/501100006374","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62137002, 62293550, 62293553, 62293554, 62450005, 62437002, 62477036, 62477037, 62176209, 62192781, and 62306229"],"award-info":[{"award-number":["62137002, 62293550, 62293553, 62293554, 62450005, 62437002, 62477036, 62477037, 62176209, 62192781, and 62306229"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"name":"the Shaanxi Provincial Social Science Foundation Project","award":["2024P041"],"award-info":[{"award-number":["2024P041"]}]},{"name":"the Youth Innovation Team of Shaanxi Universities Multi-modal Data Mining and Fusion"},{"DOI":"10.13039\/501100006374","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFC3303600"],"award-info":[{"award-number":["2022YFC3303600"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"name":"LENOVO-XJTU Intelligent Industry Joint Laboratory Project"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,13]]},"DOI":"10.1145\/3726302.3729990","type":"proceedings-article","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T14:55:26Z","timestamp":1752504926000},"page":"1130-1140","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["GlFoMR: A Glance-then-Focus Multimodal Reasoning Framework for Diagram Question Answering"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3193-3658","authenticated-orcid":false,"given":"Yaxian","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Xi'an Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9732-3011","authenticated-orcid":false,"given":"Bifan","family":"Wei","sequence":"additional","affiliation":[{"name":"School of Continuing Education, Xi'an Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6004-0675","authenticated-orcid":false,"given":"Jun","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xi'an Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8136-8795","authenticated-orcid":false,"given":"Lingling","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xi'an Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1582-5684","authenticated-orcid":false,"given":"Shuting","family":"He","sequence":"additional","affiliation":[{"name":"Shanghai University of Finance and Economics, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3176-8030","authenticated-orcid":false,"given":"Jun","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Communication Content Cognition, People's Daily Online, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5650-0600","authenticated-orcid":false,"given":"Qika","family":"Lin","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,7,13]]},"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","volume-title":"Gemini: A family of highly capable multimodal models. arXiv preprint arXiv:2312.11805","author":"Anil Rohan","year":"2023","unstructured":"Rohan Anil, Sebastian Borgeaud, Yonghui Wu, Jean-Baptiste Alayrac, Jiahui Yu, Radu Soricut, Johan Schalkwyk, Andrew M Dai, Anja Hauth, Katie Millican, et al., 2023. Gemini: A family of highly capable multimodal models. arXiv preprint arXiv:2312.11805, Vol. 1 (2023)."},{"key":"e_1_3_2_1_3_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, Vol. 1, 2 (2023), 3."},{"key":"e_1_3_2_1_4_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems Vol. 33 (2020) 1877-1901."},{"key":"e_1_3_2_1_5_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_6_1","volume-title":"Openai o3 breakthrough high score on arc-agi-pub","author":"Chollet F","year":"2024","unstructured":"F Chollet. 2024. Openai o3 breakthrough high score on arc-agi-pub. ARC Prize Foundation. https:\/\/arcprize.org\/blog\/oai-o3-pubbreakthrough (2024)."},{"key":"e_1_3_2_1_7_1","unstructured":"Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Amy Yang Angela Fan et al. 2024. The llama 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)."},{"volume-title":"Computer vision and pattern recognition","author":"Farhadi Ali","key":"e_1_3_2_1_8_1","unstructured":"Ali Farhadi and Joseph Redmon. 2018. Yolov3: An incremental improvement. In Computer vision and pattern recognition, Vol. 1804. Springer Berlin\/Heidelberg, Germany, 1-6."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01331"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29776"},{"key":"e_1_3_2_1_11_1","unstructured":"Aaron Hurst Adam Lerer Adam P Goucher Adam Perelman Aditya Ramesh Aidan Clark AJ Ostrow Akila Welihinda Alan Hayes Alec Radford et al. 2024. Gpt-4o system card. arXiv preprint arXiv:2410.21276 (2024)."},{"key":"e_1_3_2_1_12_1","unstructured":"Aaron Jaech Adam Kalai Adam Lerer Adam Richardson Ahmed El-Kishky Aiden Low Alec Helyar Aleksander Madry Alex Beutel Alex Carney et al. 2024. Openai o1 system card. arXiv preprint arXiv:2412.16720 (2024)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_15"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.571"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.579"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"e_1_3_2_1_18_1","volume-title":"Visual instruction tuning. Advances in neural information processing systems","author":"Liu Haotian","year":"2024","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2024b. Visual instruction tuning. Advances in neural information processing systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_19_1","first-page":"2507","article-title":"Learn to explain: Multimodal reasoning via thought chains for science question answering","volume":"35","author":"Lu Pan","year":"2022","unstructured":"Pan Lu, Swaroop Mishra, Tanglin Xia, Liang Qiu, Kai-Wei Chang, Song-Chun Zhu, Oyvind Tafjord, Peter Clark, and Ashwin Kalyan. 2022. Learn to explain: Multimodal reasoning via thought chains for science question answering. Advances in Neural Information Processing Systems, Vol. 35 (2022), 2507-2521.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3180563"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01954-z"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01367"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29844"},{"key":"e_1_3_2_1_24_1","unstructured":"OpenAI. 2023. ChatGPT. https:\/\/chat.openai.com. (2023)."},{"key":"e_1_3_2_1_25_1","volume-title":"International conference on machine learning. PMLR, 8748-8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al., 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748-8763."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00559"},{"key":"e_1_3_2_1_27_1","unstructured":"Robert L Solso M Kimberly MacLin and Otto H MacLin. 2005. Cognitive psychology. Pearson Education New Zealand."},{"volume-title":"Human reasoning and cognitive science","author":"Stenning Keith","key":"e_1_3_2_1_28_1","unstructured":"Keith Stenning and Michiel Van Lambalgen. 2012. Human reasoning and cognitive science. MIT Press."},{"key":"e_1_3_2_1_29_1","volume-title":"Trends in cognitive sciences","author":"Summerfield Christopher","year":"2009","unstructured":"Christopher Summerfield and Tobias Egner. 2009. Expectation (and attention) in visual cognition. Trends in cognitive sciences, Vol. 13, 9 (2009), 403-409."},{"key":"e_1_3_2_1_30_1","volume-title":"Ryan Burnell, Libin Bai, Anmol Gulati, Garrett Tanzer, Damien Vincent, Zhufeng Pan, Shibo Wang, et al.","author":"Team Gemini","year":"2024","unstructured":"Gemini Team, Petko Georgiev, Ving Ian Lei, Ryan Burnell, Libin Bai, Anmol Gulati, Garrett Tanzer, Damien Vincent, Zhufeng Pan, Shibo Wang, et al., 2024. Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context. arXiv preprint arXiv:2403.05530 (2024)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29884"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.147"},{"key":"e_1_3_2_1_33_1","volume-title":"Computer science diagram understanding with topology parsing. ACM Transactions on Knowledge Discovery from Data (TKDD)","author":"Wang Shaowei","year":"2022","unstructured":"Shaowei Wang, Lingling Zhang, Xuan Luo, Yi Yang, Xin Hu, Tao Qin, and Jun Liu. 2022. Computer science diagram understanding with topology parsing. ACM Transactions on Knowledge Discovery from Data (TKDD), Vol. 16, 6 (2022), 1-20."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01325"},{"key":"e_1_3_2_1_35_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Wang Wenhai","year":"2024","unstructured":"Wenhai Wang, Zhe Chen, Xiaokang Chen, Jiannan Wu, Xizhou Zhu, Gang Zeng, Ping Luo, Tong Lu, Jie Zhou, Yu Qiao, et al., 2024a. Visionllm: Large language model is also an open-ended decoder for vision-centric tasks. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_36_1","volume-title":"InstructTA: Instruction-tuned targeted attack for large vision-language models. arXiv preprint arXiv:2312.01886","author":"Wang Xunguang","year":"2023","unstructured":"Xunguang Wang, Zhenlan Ji, Pingchuan Ma, Zongjie Li, and Shuai Wang. 2023a. InstructTA: Instruction-tuned targeted attack for large vision-language models. arXiv preprint arXiv:2312.01886 (2023)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109441"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3231463"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3306910"},{"key":"e_1_3_2_1_40_1","unstructured":"Jason Wei Yi Tay Rishi Bommasani Colin Raffel Barret Zoph Sebastian Borgeaud Dani Yogatama Maarten Bosma Denny Zhou Donald Metzler et al. 2022. Emergent Abilities of Large Language Models. Transactions on Machine Learning Research (2022)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.111766"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.755"},{"key":"e_1_3_2_1_43_1","volume-title":"International Journal of Computer Vision","author":"Zang Yuhang","year":"2024","unstructured":"Yuhang Zang, Wei Li, Jun Han, Kaiyang Zhou, and Chen Change Loy. 2024. Contextual object detection with multimodal large language models. International Journal of Computer Vision (2024), 1-19."},{"key":"e_1_3_2_1_44_1","volume-title":"CoCoT: Contrastive chain-of-thought prompting for large multimodal models with multiple image inputs. arXiv preprint arXiv:2401.02582","author":"Zhang Daoan","year":"2024","unstructured":"Daoan Zhang, Junming Yang, Hanjia Lyu, Zijian Jin, Yuan Yao, Mingkai Chen, and Jiebo Luo. 2024a. CoCoT: Contrastive chain-of-thought prompting for large multimodal models with multiple image inputs. arXiv preprint arXiv:2401.02582 (2024)."},{"key":"e_1_3_2_1_45_1","volume-title":"LFSRM: Few-Shot Diagram-Sentence Matching via Local-Feedback Self-Regulating Memory","author":"Zhang Lingling","year":"2025","unstructured":"Lingling Zhang, Wenjun Wu, Jun Liu, Xiaojun Chang, Xin Hu, Yuhui Zheng, Yaqiang Wu, and Qinghua Zheng. 2025. LFSRM: Few-Shot Diagram-Sentence Matching via Local-Feedback Self-Regulating Memory. IEEE Transactions on Pattern Analysis and Machine Intelligence (2025)."},{"key":"e_1_3_2_1_46_1","article-title":"Multimodal Chain-of-Thought Reasoning in Language","volume":"2024","author":"Zhang Zhuosheng","year":"2024","unstructured":"Zhuosheng Zhang, Aston Zhang, Mu Li, Hai Zhao, George Karypis, and Alex Smola. 2024b. Multimodal Chain-of-Thought Reasoning in Language Models. Trans. Mach. Learn. Res., Vol. 2024 (2024).","journal-title":"Models. Trans. Mach. Learn. Res."},{"key":"e_1_3_2_1_47_1","volume-title":"An open and comprehensive pipeline for unified object grounding and detection. arXiv preprint arXiv:2401.02361","author":"Zhao Xiangyu","year":"2024","unstructured":"Xiangyu Zhao, Yicheng Chen, Shilin Xu, Xiangtai Li, Xinjiang Wang, Yining Li, and Haian Huang. 2024. An open and comprehensive pipeline for unified object grounding and detection. arXiv preprint arXiv:2401.02361 (2024)."},{"key":"e_1_3_2_1_48_1","first-page":"5168","article-title":"DDcot: Duty-distinct chain-of-thought prompting for multimodal reasoning in language models","volume":"36","author":"Zheng Ge","year":"2023","unstructured":"Ge Zheng, Bin Yang, Jiajin Tang, Hong-Yu Zhou, and Sibei Yang. 2023. DDcot: Duty-distinct chain-of-thought prompting for multimodal reasoning in language models. Advances in Neural Information Processing Systems, Vol. 36 (2023), 5168-5191.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_49_1","volume-title":"Image-of-Thought Prompting for Visual Reasoning Refinement in Multimodal Large Language Models. arXiv preprint arXiv:2405.13872","author":"Zhou Qiji","year":"2024","unstructured":"Qiji Zhou, Ruochen Zhou, Zike Hu, Panzhong Lu, Siyang Gao, and Yue Zhang. 2024. Image-of-Thought Prompting for Visual Reasoning Refinement in Multimodal Large Language Models. arXiv preprint arXiv:2405.13872 (2024)."}],"event":{"name":"SIGIR '25: The 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Padua Italy","acronym":"SIGIR '25"},"container-title":["Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3726302.3729990","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T18:31:06Z","timestamp":1755887466000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3726302.3729990"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,13]]},"references-count":49,"alternative-id":["10.1145\/3726302.3729990","10.1145\/3726302"],"URL":"https:\/\/doi.org\/10.1145\/3726302.3729990","relation":{},"subject":[],"published":{"date-parts":[[2025,7,13]]},"assertion":[{"value":"2025-07-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}