Temporal Tree of Thought: Reasoning-Guided Visual Cue Search for Long-Video Understanding

[2608.27871] Temporal Tree of Thought: Reasoning-Guided Visual Cue Search for Long-Video Understanding Skip to main content Search Submit Donate Log in Computer Science > Computer Vision and Pattern Recognition arXiv:2608.27871 (cs) [Submitted on 28 Aug 2026] Title: Temporal Tree of Thought: Reasoning-Guided Visual Cue Search for Long-Video Understanding Authors: Ziling Huang , Shin'ichi Satoh View PDF Abstract: Long-video understanding remains challenging for Multimodal Large Language Models (MLLMs) due to limited context length. Uniform sampling may miss crucial moments, while agent-based frame video understanding methods often evaluate frames independently, overlooking the temporal organization of videos. Ideally, evidence selection should mimic how humans answer questions about long videos: first locating the relevant segment from the global context, then zooming into local objects and details. We propose Temporal Tree of Thought T^3, a training-free framework for adaptive coarse-to-fine long-video understanding. T^3 constructs a question-agnostic hierarchical temporal tree via recursive temporally constrained clustering, where each node represents a contiguous segment with an informative key frame. During inference, T^3 performs an answer-retrieve-explore loop: it reasons over coarse representative frames, generates a search statement when evidence is insufficient, and expands relevant branches for finer-grained evidence. This process adaptively shifts the search target from temporal regions to specific objects and visual details to help video understanding. Experiments on VideoMME, LongVideoBench, and LVBench show that T^3 improves Qwen2.5-VL-7B by 0.5%, 4.6%, and 4.4%, respectively, under the same frame budget, demonstrating the effectiveness of structured temporal reasoning. Comments: Accept by EMNLP2026 Subjects: Computer Vision and Pattern Recognition (cs.CV) Cite as: arXiv:2608.27871 [cs.CV] (or arXiv:2608.27871v1 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2608.27871 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Ziling Huang [ view email ] [v1] Fri, 28 Aug 2026 03:23:09 UTC (1,783 KB) Full-text links: Access Paper: View PDF view license Current browse context: cs.CV < prev | next > new | recent | 2026-08 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation 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

• Temporal Tree of Thought: Reasoning-Guided Visual Cue Search for Long-Video Understanding#779781
• Where to Look Matters: On-Policy Self-Distillation for Long-Video Understanding#996938
• Counterfactual Attention Policy Distillation for Temporal Video Grounding#1131666
• FocusGraph: Graph-Structured Frame Selection for Embodied Long Video Question Answering#1156298
• Evaluation of MLLM-Agnostic Plug-and-Play Keyframe Selection Methods for Long Video Understanding#1071056