{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:38Z","timestamp":1777865378216,"version":"3.51.4"},"reference-count":68,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000153","name":"DBI","doi-asserted-by":"publisher","award":["s2405416"],"award-info":[{"award-number":["s2405416"]}],"id":[{"id":"10.13039\/100000153","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000143","name":"CCF","doi-asserted-by":"publisher","award":["2348306"],"award-info":[{"award-number":["2348306"]}],"id":[{"id":"10.13039\/100000143","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000144","name":"CNS","doi-asserted-by":"publisher","award":["2347617"],"award-info":[{"award-number":["2347617"]}],"id":[{"id":"10.13039\/100000144","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01886","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"20280-20290","source":"Crossref","is-referenced-by-count":0,"title":["ARGUS: Hallucination and Omission Evaluation in Video-LLMs"],"prefix":"10.1109","author":[{"given":"Ruchit","family":"Rawal","sequence":"first","affiliation":[{"name":"University of Maryland,College Park,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Reza","family":"Shirkavand","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heng","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gowthami","family":"Somepalli","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tom","family":"Goldstein","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"SmolVLM2: Bringing Video Understanding to Every Device - huggingface.co","year":"2025"},{"key":"ref2","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref3","volume-title":"Are language models better at generating answers or validating solutions?","year":"2025"},{"key":"ref4","volume-title":"The snli corpus","author":"Bowman","year":"2015"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref6","article-title":"e-snli: Natural language inference with natural language explanations","volume":"31","author":"Camburu","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref7","article-title":"Auroracap: Efficient, performant video detailed captioning and a new benchmark","author":"Chai","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01265"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.starsem-1.7"},{"key":"ref10","article-title":"Expanding performance boundaries of open-source multimodal models with model, data, and testtime scaling","author":"Chen","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref12","article-title":"Vidhal: Benchmarking temporal hallucinations in vision 11 ms","author":"Choong","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref13","article-title":"Transforming question answering datasets into natural language inference datasets","author":"Demszky","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00030"},{"key":"ref15","volume-title":"diffusers\/shot-categorizer-v0","year":"2025"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"ref17","article-title":"Tc-bench: Benchmarking temporal compositionality in text-to-video and image-tovideo generation","author":"Feng","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref18","article-title":"Video-mme: The first-ever comprehensive evaluation benchmark of multi-modal 11 ms in video analysis","author":"Fu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.127"},{"key":"ref20","article-title":"The llama 3 herd of models","author":"Grattafiori","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01363"},{"key":"ref23","article-title":"Deepseek-r1: Incentivizing reasoning capability in 11 ms via reinforcement learning","author":"Guo","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref24","article-title":"Ciem: Contrastive instruction evaluation method for better instruction tuning","author":"Hu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.5244\/C.34.29"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00487"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.290"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02571"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01318"},{"key":"ref30","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"CoRR"},{"key":"ref31","article-title":"Llms-as-judges: a comprehensive survey on 11 m -based evaluation methods","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00782"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref34","article-title":"Revisiting the role of language priors in vision-language models","author":"Lin","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref35","article-title":"Deepseek-v3 technical report","author":"Liu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref36","article-title":"Mitigating hallucination in large multi-modal models via robust instruction tuning","author":"Liu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref37","article-title":"A survey on hallucination in large vision-language models","author":"Liu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref38","article-title":"Logical reasoning in large language models: A survey","author":"Liu","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2004"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00675"},{"key":"ref41","article-title":"Neptune: The long orbit to benchmarking long video understanding","author":"Nagrani","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02222"},{"key":"ref43","volume-title":"Gpt-4o","year":"2024"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1852"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3712059"},{"key":"ref46","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref47","article-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref48","article-title":"Cinepile: A long video question answering dataset and benchmark","author":"Rawal","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1437"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.841"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.775"},{"key":"ref52","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref53","article-title":"A linear estimator on top of CLIP to predict the aesthetic quality of images","volume-title":"Laion-aesthetics_predictor v1","year":"2022"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0732"},{"key":"ref55","article-title":"Amber: An llm -free multi-dimensional benchmark for mllms hallucination evaluation","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00677"},{"key":"ref57","article-title":"Lvbench: An extreme long video understanding benchmark","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref58","article-title":"Videohallucer: Evaluating intrinsic and extrinsic hallucinations in large video-language models","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n18-1101"},{"key":"ref60","article-title":"Anlizing the adversarial natural language inference dataset","author":"Williams","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00048"},{"key":"ref62","article-title":"Qwen2. 5 technical report","author":"Yang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref63","article-title":"mplugowl3: Towards long image-sequence understanding in multimodal large language models","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Ye","year":"2024"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref65","article-title":"Eventhallusion: Diagnosing event hallucinations in video llms","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2020"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01727"},{"key":"ref68","article-title":"Apollo: An exploration of video understanding in large multimodal models","author":"Zohar","year":"2024","journal-title":"arXiv preprint arXiv"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11443430.pdf?arnumber=11443430","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:21:02Z","timestamp":1777530062000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443430\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01886","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}