Tracking the Truth: Object-Centric Spatio-Temporal Monitoring for Video Large Language Models

[2605.08974] Tracking the Truth: Object-Centric Spatio-Temporal Monitoring for Video Large Language Models Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Computer Vision and Pattern Recognition arXiv:2605.08974 (cs) This paper has been withdrawn by Thong Nguyen [Submitted on 9 May 2026 ( v1 ), last revised 15 Aug 2026 (this version, v2)] Title: Tracking the Truth: Object-Centric Spatio-Temporal Monitoring for Video Large Language Models Authors: Tri Cao , Khoi Le , Thong Nguyen , Cong-Duy Nguyen , Quynh Vo , Anh Tuan Luu , Chunyan Miao , See-Kiong Ng , Shuicheng Yan , Bryan Hooi View a PDF of the paper titled Tracking the Truth: Object-Centric Spatio-Temporal Monitoring for Video Large Language Models, by Tri Cao and 9 other authors No PDF available, click to view other formats Abstract: While multimodal large language models (MLLMs) have advanced video understanding, they remain highly prone to hallucinations in dynamic scenes. We argue this stems from a failure in spatio-temporal monitoring, the ability to persistently track object identities, states, and relations over time. Existing benchmarks obscure this deficit by relying on single final-answer evaluations for queries that can often be resolved via local visual cues or statistical priors. To rigorously diagnose this, we introduce STEMO-Bench (Spatio-TEmporal MOnitoring), a benchmark of human-verified object-centric facts that evaluates intermediate reasoning by decomposing queries into sub-questions, distinguishing genuine temporal understanding from coincidental correctness. To address failure modes exposed by STEMO, we propose STEMO-Track, a novel object-centric framework that explicitly constructs and reasons over structured object trajectories via chunk-wise state extraction and temporal aggregation. Extensive experiments demonstrate that our object-centric framework significantly reduces hallucinated answers and improves spatio-temporal reasoning consistency over state-of-the-art MLLMs. Comments: The authors are withdrawing this manuscript due to errors identified in the experimental evaluation and result aggregation, which affect several reported quantitative results and some conclusions. These issues require substantial re-evaluation of the experiments and analysis Subjects: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI) Cite as: arXiv:2605.08974 [cs.CV] (or arXiv:2605.08974v2 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2605.08974 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Thong Nguyen [ view email ] [v1] Sat, 9 May 2026 14:32:36 UTC (31,341 KB) [v2] Sat, 15 Aug 2026 02:58:01 UTC (1 KB) (withdrawn) Full-text links: Access Paper: View a PDF of the paper titled Tracking the Truth: Object-Centric Spatio-Temporal Monitoring for Video Large Language Models, by Tri Cao and 9 other authors Withdrawn No license for this version due to withdrawn Current browse context: cs.CV < prev | next > new | recent | 2026-05 Change to browse by: cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Tracking the Truth: Object-Centric Spatio-Temporal Monitoring for Video Large Language Models#609935
• GleanVID: Complementary Token Selection for Efficient Video Large Language Models#1132243
• COMET: Contrastive Motion-Enhanced Temporal Reasoning for Video Multimodal Large Language Models#662209
• COMET: Contrastive Motion-Enhanced Temporal Reasoning for Video Multimodal Large Language Models#661159
• COMET: Contrastive Motion-Enhanced Temporal Reasoning for Video Multimodal Large Language Models#480063