{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:46:58Z","timestamp":1765309618349,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":32,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3762056","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:54:17Z","timestamp":1761375257000},"page":"13799-13805","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Analyze-Prompt-Reason: A Collaborative Agent-Based Framework for Multi-Image Vision-Language Reasoning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-9467-6754","authenticated-orcid":false,"given":"Angelos","family":"Vlachos","sequence":"first","affiliation":[{"name":"National Technical University of Athens, School of Electrical and Computer Engineering, Artificial Intelligence and Learning Systems Laboratory, National Technical University of Athens, Athens, Attiki, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7015-7746","authenticated-orcid":false,"given":"Giorgos","family":"Filandrianos","sequence":"additional","affiliation":[{"name":"National Technical University of Athens, School of Electrical and Computer Engineering, Artificial Intelligence and Learning Systems Laboratory, National Technical University of Athens, Athens, Attiki, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9442-4186","authenticated-orcid":false,"given":"Maria","family":"Lymperaiou","sequence":"additional","affiliation":[{"name":"National Technical University of Athens, School of Electrical and Computer Engineering, Artificial Intelligence and Learning Systems Laboratory, National Technical University of Athens, Athens, Attiki, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2691-0956","authenticated-orcid":false,"given":"Nikolaos","family":"Spanos","sequence":"additional","affiliation":[{"name":"National Technical University of Athens, School of Electrical and Computer Engineering, Artificial Intelligence and Learning Systems Laboratory, National Technical University of Athens, Athens, Attiki, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3918-2616","authenticated-orcid":false,"given":"Ilias","family":"Mitsouras","sequence":"additional","affiliation":[{"name":"National Technical University of Athens, School of Electrical and Computer Engineering, Artificial Intelligence and Learning Systems Laboratory, National Technical University of Athens, Athens, Attiki, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4839-6192","authenticated-orcid":false,"given":"Vasileios","family":"Karampinis","sequence":"additional","affiliation":[{"name":"National Technical University of Athens, School of Electrical and Computer Engineering, Artificial Intelligence and Learning Systems Laboratory, National Technical University of Athens, Athens, Attiki, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0632-9769","authenticated-orcid":false,"given":"Athanasios","family":"Voulodimos","sequence":"additional","affiliation":[{"name":"National Technical University of Athens, School of Electrical and Computer Engineering, Artificial Intelligence and Learning Systems Laboratory, National Technical University of Athens, Athens, Attiki, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Oncel Tuzel, Ping Huang, Jiulong Shan, Jianjun Shi, and Meng Cao.","author":"Bai Haoping","year":"2023","unstructured":"Haoping Bai, Shancong Mou, Tatiana Likhomanenko, Ramazan Gokberk Cinbis, Oncel Tuzel, Ping Huang, Jiulong Shan, Jianjun Shi, and Meng Cao. 2023. VISION Datasets: A Benchmark for Vision-based InduStrial InspectiON. arXiv:2306.07890 [cs.CV] https:\/\/arxiv.org\/abs\/2306.07890"},{"key":"e_1_3_2_2_2_1","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems. 26898-26922","author":"Bitton Yonatan","year":"2023","unstructured":"Yonatan Bitton, Hritik Bansal, Jack Hessel, Rulin Shao, Wanrong Zhu, Anas Awadalla, Josh Gardner, Rohan Taori, and Ludwig Schimdt. 2023. VisIT-Bench: a benchmark for vision-language instruction following inspired by real-world use. In Proceedings of the 37th International Conference on Neural Information Processing Systems. 26898-26922."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"crossref","unstructured":"Rumeysa Bodur Erhan Gundogdu Binod Bhattarai Tae-Kyun Kim Michael Donoser and Loris Bazzani. 2023. iEdit: Localised Text-guided Image Editing with Weak Supervision. arXiv:2305.05947 [cs.CV] https:\/\/arxiv.org\/abs\/2305.05947","DOI":"10.1109\/CVPRW63382.2024.00738"},{"key":"e_1_3_2_2_4_1","volume-title":"Qiang Xu, Anush Krishnan, Yu Pan, Giancarlo Baldan, and Oscar Beijbom.","author":"Caesar Holger","year":"2020","unstructured":"Holger Caesar, Varun Bankiti, Alex H. Lang, Sourabh Vora, Venice Erin Liong, Qiang Xu, Anush Krishnan, Yu Pan, Giancarlo Baldan, and Oscar Beijbom. 2020. nuScenes: A multimodal dataset for autonomous driving. arXiv:1903.11027 [cs.LG] https:\/\/arxiv.org\/abs\/1903.11027"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"crossref","unstructured":"Yingshan Chang Mridu Narang Hisami Suzuki Guihong Cao Jianfeng Gao and Yonatan Bisk. 2022. WebQA: Multihop and Multimodal QA. arXiv:2109.00590 [cs.CL] https:\/\/arxiv.org\/abs\/2109.00590","DOI":"10.1109\/CVPR52688.2022.01600"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"crossref","unstructured":"Lin Chen Jinsong Li Xiaoyi Dong Pan Zhang Yuhang Zang Zehui Chen Haodong Duan Jiaqi Wang Yu Qiao Dahua Lin et al. 2024. Are We on the Right Way for Evaluating Large Vision-Language Models? CoRR (2024).","DOI":"10.52202\/079017-0850"},{"key":"e_1_3_2_2_7_1","volume-title":"Neural Naturalist: Generating Fine-Grained Image Comparisons. arXiv:1909.04101 [cs.CL] https:\/\/arxiv.org\/abs\/1909.04101","author":"Forbes Maxwell","year":"2019","unstructured":"Maxwell Forbes, Christine Kaeser-Chen, Piyush Sharma, and Serge Belongie. 2019. Neural Naturalist: Generating Fine-Grained Image Comparisons. arXiv:1909.04101 [cs.CL] https:\/\/arxiv.org\/abs\/1909.04101"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.646"},{"key":"e_1_3_2_2_9_1","volume-title":"Bigham","author":"Gurari Danna","year":"2018","unstructured":"Danna Gurari, Qing Li, Abigale J. Stangl, Anhong Guo, Chi Lin, Kristen Grauman, Jiebo Luo, and Jeffrey P. Bigham. 2018. VizWiz Grand Challenge: Answering Visual Questions from Blind People. arXiv:1802.08218 [cs.CV] https:\/\/arxiv.org\/abs\/1802.08218"},{"key":"e_1_3_2_2_10_1","volume-title":"Davis","author":"Han Xintong","year":"2017","unstructured":"Xintong Han, Zuxuan Wu, Phoenix X. Huang, Xiao Zhang, Menglong Zhu, Yuan Li, Yang Zhao, and Larry S. Davis. 2017. Automatic Spatially-aware Fashion Concept Discovery. arXiv:1708.01311 [cs.CV] https:\/\/arxiv.org\/abs\/1708.01311"},{"key":"e_1_3_2_2_11_1","volume-title":"Labeled Faces in the Wild: A Database forStudying Face Recognition in Unconstrained Environments. Tech. rep. (10","author":"Huang Gary","year":"2008","unstructured":"Gary Huang, Marwan Mattar, Tamara Berg, and Eric Learned-Miller. 2008. Labeled Faces in the Wild: A Database forStudying Face Recognition in Unconstrained Environments. Tech. rep. (10 2008)."},{"volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Isola Phillip","key":"e_1_3_2_2_12_1","unstructured":"Phillip Isola, Joseph J. Lim, and Edward H. Adelson. 2015. Discovering States and Transformations in Image Collections. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_2_13_1","first-page":"60088","article-title":"2024. Remi: A dataset for reasoning with multiple images","volume":"37","author":"Kazemi Mehran","year":"2024","unstructured":"Mehran Kazemi, Nishanth Dikkala, Ankit Anand, Petar Devic, Ishita Dasgupta, Fangyu Liu, Bahare Fatemi, Pranjal Awasthi, Sreenivas Gollapudi, Dee Guo, et al., 2024. Remi: A dataset for reasoning with multiple images. Advances in Neural Information Processing Systems, Vol. 37 (2024), 60088-60109.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_14_1","unstructured":"Daesik Kim Seonhoon Kim and Nojun Kwak. 2019. Textbook Question Answering with Multi-modal Context Graph Understanding and Self-supervised Open-set Comprehension. arXiv:1811.00232 [cs.CL] https:\/\/arxiv.org\/abs\/1811.00232"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.290"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1250"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"crossref","unstructured":"Minesh Mathew Dimosthenis Karatzas and C. V. Jawahar. 2021. DocVQA: A Dataset for VQA on Document Images. arXiv:2007.00398 [cs.CV] https:\/\/arxiv.org\/abs\/2007.00398","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00156"},{"key":"e_1_3_2_2_19_1","unstructured":"Dong Huk Park Trevor Darrell and Anna Rohrbach. 2019. Robust Change Captioning. arXiv:1901.02527 [cs.CV] https:\/\/arxiv.org\/abs\/1901.02527"},{"key":"e_1_3_2_2_20_1","volume-title":"Reasoning with large language models, a survey. arXiv preprint arXiv:2407.11511","author":"Plaat Aske","year":"2024","unstructured":"Aske Plaat, Annie Wong, Suzan Verberne, Joost Broekens, Niki van Stein, and Thomas Back. 2024. Reasoning with large language models, a survey. arXiv preprint arXiv:2407.11511 (2024)."},{"key":"e_1_3_2_2_21_1","volume-title":"Tsotsos","author":"Rosenfeld Amir","year":"2018","unstructured":"Amir Rosenfeld, Markus D. Solbach, and John K. Tsotsos. 2018. Totally Looks Like - How Humans Compare, Compared to Machines. arXiv:1803.01485 [cs.CV] https:\/\/arxiv.org\/abs\/1803.01485"},{"key":"e_1_3_2_2_22_1","volume-title":"ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks. arXiv:1912.01734 [cs.CV] https:\/\/arxiv.org\/abs\/1912.01734","author":"Shridhar Mohit","year":"2020","unstructured":"Mohit Shridhar, Jesse Thomason, Daniel Gordon, Yonatan Bisk, Winson Han, Roozbeh Mottaghi, Luke Zettlemoyer, and Dieter Fox. 2020. ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks. arXiv:1912.01734 [cs.CV] https:\/\/arxiv.org\/abs\/1912.01734"},{"key":"e_1_3_2_2_23_1","unstructured":"Alane Suhr and Yoav Artzi. 2019. NLVR2 Visual Bias Analysis. arXiv:1909.10411 [cs.CL] https:\/\/arxiv.org\/abs\/1909.10411"},{"key":"e_1_3_2_2_24_1","volume-title":"Resampling Benchmark for Efficient Comprehensive Evaluation of Large Vision-Language Models. arXiv preprint arXiv:2504.09979","author":"Suzuki Teppei","year":"2025","unstructured":"Teppei Suzuki and Keisuke Ozawa. 2025. Resampling Benchmark for Efficient Comprehensive Evaluation of Large Vision-Language Models. arXiv preprint arXiv:2504.09979 (2025)."},{"key":"e_1_3_2_2_25_1","unstructured":"Alon Talmor Ori Yoran Amnon Catav Dan Lahav Yizhong Wang Akari Asai Gabriel Ilharco Hannaneh Hajishirzi and Jonathan Berant. 2021. MultiModalQA: Complex Question Answering over Text Tables and Images. arXiv:2104.06039 [cs.CL] https:\/\/arxiv.org\/abs\/2104.06039"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"crossref","unstructured":"Ryota Tanaka Kyosuke Nishida Kosuke Nishida Taku Hasegawa Itsumi Saito and Kuniko Saito. 2023. SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images. arXiv:2301.04883 [cs.CL] https:\/\/arxiv.org\/abs\/2301.04883","DOI":"10.1609\/aaai.v37i11.26598"},{"key":"e_1_3_2_2_27_1","volume-title":"Xinzhuo Li, Xiaona Zhou, Vedant Shah, Tianjiao Yu, Pinar Yanardag, and Ismini Lourentzou.","author":"Wahed Muntasir","year":"2024","unstructured":"Muntasir Wahed, Kiet A Nguyen, Adheesh Sunil Juvekar, Xinzhuo Li, Xiaona Zhou, Vedant Shah, Tianjiao Yu, Pinar Yanardag, and Ismini Lourentzou. 2024. PRIMA: Multi-Image Vision-Language Models for Reasoning Segmentation. arXiv preprint arXiv:2412.15209 (2024)."},{"key":"e_1_3_2_2_28_1","volume-title":"Lvlm-ehub: A comprehensive evaluation benchmark for large vision-language models","author":"Xu Peng","year":"2024","unstructured":"Peng Xu, Wenqi Shao, Kaipeng Zhang, Peng Gao, Shuo Liu, Meng Lei, Fanqing Meng, Siyuan Huang, Yu Qiao, and Ping Luo. 2024. Lvlm-ehub: A comprehensive evaluation benchmark for large vision-language models. IEEE Transactions on Pattern Analysis and Machine Intelligence (2024)."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"crossref","unstructured":"Semih Yagcioglu Aykut Erdem Erkut Erdem and Nazli Ikizler-Cinbis. 2018. RecipeQA: A Challenge Dataset for Multimodal Comprehension of Cooking Recipes. arXiv:1809.00812 [cs.CL] https:\/\/arxiv.org\/abs\/1809.00812","DOI":"10.18653\/v1\/D18-1166"},{"volume-title":"The Twelfth International Conference on Learning Representations.","author":"Yang Chengrun","key":"e_1_3_2_2_30_1","unstructured":"Chengrun Yang, Xuezhi Wang, Yifeng Lu, Hanxiao Liu, Quoc V Le, Denny Zhou, and Xinyun Chen. [n.d.]. Large Language Models as Optimizers. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_2_31_1","volume-title":"Benchmarking multi-image understanding in vision and language models: Perception, knowledge, reasoning, and multi-hop reasoning. arXiv preprint arXiv:2406.12742","author":"Zhao Bingchen","year":"2024","unstructured":"Bingchen Zhao, Yongshuo Zong, Letian Zhang, and Timothy Hospedales. 2024. Benchmarking multi-image understanding in vision and language models: Perception, knowledge, reasoning, and multi-hop reasoning. arXiv preprint arXiv:2406.12742 (2024)."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"crossref","unstructured":"Yang Zou Jongheon Jeong Latha Pemula Dongqing Zhang and Onkar Dabeer. 2022. SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentation. arXiv:2207.14315 [cs.CV] https:\/\/arxiv.org\/abs\/2207.14315","DOI":"10.1007\/978-3-031-20056-4_23"}],"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\/3746027.3762056","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:44:12Z","timestamp":1765309452000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3762056"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":32,"alternative-id":["10.1145\/3746027.3762056","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3762056","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"}}]}}