{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T11:42:39Z","timestamp":1783078959687,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":58,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755626","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:27:39Z","timestamp":1761377259000},"page":"4827-4836","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["MESH - Understanding Videos Like Human: Measuring Hallucinations in Large Video Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-9534-6765","authenticated-orcid":false,"given":"Garry","family":"Yang","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7032-1525","authenticated-orcid":false,"given":"Zizhe","family":"Chen","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8553-6004","authenticated-orcid":false,"given":"Man Hon","family":"Wong","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1393-2273","authenticated-orcid":false,"given":"Haoyu","family":"Lei","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2485-3529","authenticated-orcid":false,"given":"Yongqiang","family":"Chen","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8492-3069","authenticated-orcid":false,"given":"Zhenguo","family":"Li","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3088-8085","authenticated-orcid":false,"given":"Kaiwen","family":"Zhou","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6313-6288","authenticated-orcid":false,"given":"James","family":"Cheng","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01321"},{"key":"e_1_3_2_1_2_1","volume-title":"TV, and digital media","author":"Block Bruce","unstructured":"Bruce Block. 2020. The visual story: Creating the visual structure of film, TV, and digital media. Routledge."},{"key":"e_1_3_2_1_3_1","volume-title":"Film Art: An Introduction","author":"Bordwell D.","year":"2008","unstructured":"D. Bordwell and K. Thompson. 2008. Film Art: An Introduction. McGraw Hill. 2006046880 https:\/\/books.google.com.hk\/books?id=g6ZAAQAAIAAJ"},{"key":"e_1_3_2_1_4_1","volume-title":"Video-based human behavior understanding: A survey","author":"Koerich Borges Paulo Vinicius","year":"2013","unstructured":"Paulo Vinicius Koerich Borges, Nicola Conci, and Andrea Cavallaro. 2013. Video-based human behavior understanding: A survey. IEEE transactions on circuits and systems for video technology, Vol. 23, 11 (2013), 1993-2008."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01282"},{"key":"e_1_3_2_1_6_1","unstructured":"Zhe Chen Weiyun Wang Yue Cao Yangzhou Liu Zhangwei Gao Erfei Cui Jinguo Zhu Shenglong Ye Hao Tian Zhaoyang Liu et al. 2024. Expanding Performance Boundaries of Open-Source Multimodal Models with Model Data and Test-Time Scaling. arXiv preprint arXiv:2412.05271 (2024)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2411.16771"},{"key":"e_1_3_2_1_8_1","volume-title":"Barbara A Dosher, Zhong-Lin Ed Lu, and Richard M Shiffrin.","author":"Charles","year":"2013","unstructured":"Charles Ed Chubb, Barbara A Dosher, Zhong-Lin Ed Lu, and Richard M Shiffrin. 2013. Human information processing: Vision, memory, and attention., American Psychological Association."},{"key":"e_1_3_2_1_9_1","volume-title":"Asano","author":"Cores Daniel","year":"2025","unstructured":"Daniel Cores, Michael Dorkenwald, Manuel Mucientes, Cees G. M. Snoek, and Yuki M. Asano. 2025. Lost in Time: A New Temporal Benchmark for VideoLLMs. arXiv:2410.07752 [cs.CV] https:\/\/arxiv.org\/abs\/2410.07752"},{"key":"e_1_3_2_1_10_1","first-page":"886","article-title":"Histograms of oriented gradients for human detection. In 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR'05), Vol. 1","author":"Dalal Navneet","year":"2005","unstructured":"Navneet Dalal and Bill Triggs. 2005. Histograms of oriented gradients for human detection. In 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR'05), Vol. 1. Ieee, 886-893.","journal-title":"Ieee"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2405.21075"},{"key":"e_1_3_2_1_12_1","volume-title":"Mise-en-sc\u00e8ne: Film style and interpretation.","author":"Gibbs John","year":"2002","unstructured":"John Gibbs and John Edward Gibbs. 2002. Mise-en-sc\u00e8ne: Film style and interpretation. Vol. 10. Wallflower Press."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2309.03905"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(81)90024-2"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01353"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2311.05232"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","unstructured":"Aaron Hurst Adam Lerer Adam P. Goucher Adam Perelman Aditya Ramesh Aidan Clark AJ Ostrow Akila Welihinda Alan Hayes Alec Radford Aleksander Madry Alex Baker-Whitcomb Alex Beutel Alex Borzunov Alex Carney Alex Chow Alex Kirillov Alex Nichol Alex Paino Alex Renzin Alex Tachard Passos Alexander Kirillov Alexi Christakis Alexis Conneau Ali Kamali Allan Jabri Allison Moyer Allison Tam Amadou Crookes Amin Tootoonchian Ananya Kumar Andrea Vallone Andrej Karpathy Andrew Braunstein Andrew Cann Andrew Codispoti Andrew Galu Andrew Kondrich Andrew Tulloch Andrey Mishchenko Angela Baek Angela Jiang Antoine Pelisse Antonia Woodford Anuj Gosalia Arka Dhar Ashley Pantuliano Avi Nayak Avital Oliver Barret Zoph Behrooz Ghorbani Ben Leimberger Ben Rossen Ben Sokolowsky Ben Wang Benjamin Zweig Beth Hoover Blake Samic Bob McGrew Bobby Spero Bogo Giertler Bowen Cheng Brad Lightcap Brandon Walkin Brendan Quinn Brian Guarraci Brian Hsu Bright Kellogg Brydon Eastman Camillo Lugaresi Carroll L. Wainwright Cary Bassin Cary Hudson Casey Chu Chad Nelson Chak Li Chan Jun Shern Channing Conger Charlotte Barette Chelsea Voss Chen Ding Cheng Lu Chong Zhang Chris Beaumont Chris Hallacy Chris Koch Christian Gibson Christina Kim Christine Choi Christine McLeavey Christopher Hesse Claudia Fischer Clemens Winter Coley Czarnecki Colin Jarvis Colin Wei Constantin Koumouzelis and Dane Sherburn. 2024. GPT-4o System Card. CoRR Vol. abs\/2410.21276 (2024). arXiv:2410.21276 doi:10.48550\/ARXIV.2410.21276","DOI":"10.48550\/ARXIV.2410.21276"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3571730"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2411.11150"},{"key":"e_1_3_2_1_20_1","first-page":"16","article-title":"Analysis of the Difficulty and Discrimination Indices of Multiple-Choice Questions According to Cognitive Levels in an Open and Distance Learning Context","volume":"15","author":"Kocdar Serpil","year":"2016","unstructured":"Serpil Kocdar, Nejdet Karadag, and Murat Dogan Sahin. 2016. Analysis of the Difficulty and Discrimination Indices of Multiple-Choice Questions According to Cognitive Levels in an Open and Distance Learning Context. Turkish Online Journal of Educational Technology-TOJET, Vol. 15, 4 (2016), 16-24.","journal-title":"Turkish Online Journal of Educational Technology-TOJET"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2020.ACL-MAIN.730"},{"key":"e_1_3_2_1_22_1","volume-title":"Eun Woo Im, and Pooyan Fazli","author":"Li Chaoyu","year":"2024","unstructured":"Chaoyu Li, Eun Woo Im, and Pooyan Fazli. 2024a. VidHalluc: Evaluating Temporal Hallucinations in Multimodal Large Language Models for Video Understanding. arXiv:2412.03735 [cs.CV] https:\/\/arxiv.org\/abs\/2412.03735"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2023.EMNLP-MAIN.20"},{"key":"e_1_3_2_1_25_1","volume-title":"Making long-context language models better multi-hop reasoners. arXiv preprint arXiv:2408.03246","author":"Li Yanyang","year":"2024","unstructured":"Yanyang Li, Shuo Liang, Michael R Lyu, and Liwei Wang. 2024b. Making long-context language models better multi-hop reasoners. arXiv preprint arXiv:2408.03246 (2024)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2310.19773"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00813"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2310.14566"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2403.11116"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2024.FINDINGS-ACL.517"},{"key":"e_1_3_2_1_31_1","volume-title":"Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution. arXiv preprint arXiv:2409.12961","author":"Liu Zuyan","year":"2024","unstructured":"Zuyan Liu, Yuhao Dong, Ziwei Liu, Winston Hu, Jiwen Lu, and Yongming Rao. 2024a. Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution. arXiv preprint arXiv:2409.12961 (2024)."},{"key":"e_1_3_2_1_32_1","article-title":"Calibrating and Improving Graph Contrastive","volume":"2023","author":"Ma Kaili","year":"2023","unstructured":"Kaili Ma, Garry Yang, Han Yang, Yongqiang Chen, and James Cheng. 2023. Calibrating and Improving Graph Contrastive Learning. Trans. Mach. Learn. Res., Vol. 2023 (2023). https:\/\/openreview.net\/forum?id=LdSP6cvTS4","journal-title":"Learning. Trans. Mach. Learn. Res."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2405.03770"},{"key":"e_1_3_2_1_34_1","volume-title":"From Human Attention to Computational Attention","author":"Mancas Matei","unstructured":"Matei Mancas, Vincent P Ferrera, Nicolas Riche, and John G Taylor. 2016. From Human Attention to Computational Attention. Vol. 2. Springer."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01359"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2402.06196"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2024.FINDINGS-ACL.217"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2311.16103"},{"key":"e_1_3_2_1_39_1","unstructured":"OpenAI. 2023. GPT-4 Technical Report. CoRR Vol. abs\/2303.08774 (2023). arXiv:2303.08774 doi:10.48550\/ARXIV.2303.08774"},{"key":"e_1_3_2_1_40_1","volume-title":"Perception Test: A Diagnostic Benchmark for Multimodal Video Models. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023","author":"Patraucean Viorica","year":"2023","unstructured":"Viorica Patraucean, Lucas Smaira, Ankush Gupta, Adri\u00e0 Recasens, Larisa Markeeva, Dylan Banarse, Skanda Koppula, Joseph Heyward, Mateusz Malinowski, Yi Yang, Carl Doersch, Tatiana Matejovicova, Yury Sulsky, Antoine Miech, Alexandre Fr\u00e9chette, Hanna Klimczak, Raphael Koster, Junlin Zhang, Stephanie Winkler, Yusuf Aytar, Simon Osindero, Dima Damen, Andrew Zisserman, and Jo\u00e3o Carreira. 2023. Perception Test: A Diagnostic Benchmark for Multimodal Video Models. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023, Alice Oh, Tristan Naumann, Amir Globerson, Kate Saenko, Moritz Hardt, and Sergey Levine (Eds.). http:\/\/papers.nips.cc\/paper_files\/paper\/2023\/hash\/8540fba4abdc7f9f7a7b1cc6cd60e409-Abstract-Datasets_and_Benchmarks.html"},{"key":"e_1_3_2_1_41_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021","volume":"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, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, 8748-8763. http:\/\/proceedings.mlr.press\/v139\/radford21a.html"},{"key":"e_1_3_2_1_42_1","volume-title":"Visual Methodologies: An Introduction to the Interpretation of Visual Materials","author":"Rose G.","year":"2007","unstructured":"G. Rose. 2007. Visual Methodologies: An Introduction to the Interpretation of Visual Materials. SAGE Publications. 2006927695 https:\/\/books.google.com.hk\/books?id=gnUPNcnYjcIC"},{"key":"e_1_3_2_1_43_1","volume-title":"Video and Audio Foundation Models. In Findings of the Association for Computational Linguistics: EMNLP 2024","author":"Sahoo Pranab","year":"2024","unstructured":"Pranab Sahoo, Prabhash Meharia, Akash Ghosh, Sriparna Saha, Vinija Jain, and Aman Chadha. 2024a. A Comprehensive Survey of Hallucination in Large Language, Image, Video and Audio Foundation Models. In Findings of the Association for Computational Linguistics: EMNLP 2024, Miami, Florida, USA, November 12-16, 2024, Yaser Al-Onaizan, Mohit Bansal, and Yun-Nung Chen (Eds.). Association for Computational Linguistics, 11709-11724. https:\/\/aclanthology.org\/2024.findings-emnlp.685"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2405.09589"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2406.10889"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3148210"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2312.17432"},{"key":"e_1_3_2_1_48_1","volume-title":"Multimodal Signal Processing: Theory and applications for human-computer interaction","author":"Thiran Jean-Philippe","unstructured":"Jean-Philippe Thiran, Ferran Marques, and Herv\u00e9 Bourlard. 2009. Multimodal Signal Processing: Theory and applications for human-computer interaction. Academic Press."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2302.13971"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2406.16338"},{"key":"e_1_3_2_1_51_1","volume-title":"PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models. arXiv:2412.09613 [cs.CV] https:\/\/arxiv.org\/abs\/2412.09613","author":"Yang Chenyu","year":"2024","unstructured":"Chenyu Yang, Xuan Dong, Xizhou Zhu, Weijie Su, Jiahao Wang, Hao Tian, Zhe Chen, Wenhai Wang, Lewei Lu, and Jifeng Dai. 2024a. PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models. arXiv:2412.09613 [cs.CV] https:\/\/arxiv.org\/abs\/2412.09613"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2406.06040"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2306.13549"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2409.16597"},{"key":"e_1_3_2_1_56_1","unstructured":"Yuanhan Zhang Jinming Wu Wei Li Bo Li Zejun Ma Ziwei Liu and Chunyuan Li. 2024c. Video Instruction Tuning With Synthetic Data. arXiv:2410.02713 [cs.CV] https:\/\/arxiv.org\/abs\/2410.02713"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2411.18659"},{"key":"e_1_3_2_1_58_1","volume-title":"MLVU: Benchmarking Multi-task Long Video Understanding. arXiv:2406.04264 [cs.CV] https:\/\/arxiv.org\/abs\/2406.04264","author":"Zhou Junjie","year":"2025","unstructured":"Junjie Zhou, Yan Shu, Bo Zhao, Boya Wu, Zhengyang Liang, Shitao Xiao, Minghao Qin, Xi Yang, Yongping Xiong, Bo Zhang, Tiejun Huang, and Zheng Liu. 2025. MLVU: Benchmarking Multi-task Long Video Understanding. arXiv:2406.04264 [cs.CV] https:\/\/arxiv.org\/abs\/2406.04264"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755626","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:58:04Z","timestamp":1765342684000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755626"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":58,"alternative-id":["10.1145\/3746027.3755626","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755626","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"}}]}}