Training-Free Temporal Abstraction for General Video Understanding

[2608.27929] Training-Free Temporal Abstraction for General Video Understanding Skip to main content Search Submit Donate Log in Computer Science > Computer Vision and Pattern Recognition arXiv:2608.27929 (cs) [Submitted on 28 Aug 2026] Title: Training-Free Temporal Abstraction for General Video Understanding Authors: Etienne Casanova , Sevan Brodjian , Pietro Perona View PDF HTML (experimental) Abstract: Videos are expensive to analyze frame by frame, yet many video understanding tasks depend on knowing where relevant moments occur. A system may need to find when an action changes, locate the segment described by a sentence, or choose a few frames for a vision-language model. Existing methods often solve these problems separately, using task-specific training data or specialized architectures. We study whether a pretrained video-text model can provide enough temporal structure to support several of these tasks at once. We present STITCH, a training-free method that divides a video into semantically meaningful temporal chunks. STITCH embeds short video windows with a frozen video-text backbone and detects changes in the resulting embedding sequence. These chunks are computed once per video and reused across tasks. We evaluate STITCH on generic event boundary detection, language-based moment retrieval, and frame selection for long-video VLM reasoning. Across all three settings, STITCH remains competitive with more specialized methods while requiring no task-specific training, with especially clear gains when only a small number of frames or tokens can be processed. These results suggest that reusable temporal abstraction is a promising direction for general video understanding, allowing dense video streams to be converted once into semantic units that can be localized, retrieved, sampled, or reasoned over by downstream systems. Comments: Submitted to NeurIPS 2026 Subjects: Computer Vision and Pattern Recognition (cs.CV) Cite as: arXiv:2608.27929 [cs.CV] (or arXiv:2608.27929v1 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2608.27929 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Etienne Casanova [ view email ] [v1] Fri, 28 Aug 2026 05:10:54 UTC (1,599 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.CV < prev | next > new | recent | 2026-08 Change to browse by: cs References & Citations SciX 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)

Related documents

• Training-Free Temporal Abstraction for General Video Understanding#779832
• StreamOPD: A Post-Training Recipe with Spatio-Temporal Cue Gating for Streaming Video Understanding#620720
• StreamOPD: A Post-Training Recipe with Spatio-Temporal Cue Gating for Streaming Video Understanding#619041
• CoFiE: Coarse-to-Fine Evidence Selection for Efficient Streaming Video Understanding#926570
• What Should a Streaming Video Model Remember?#1117469