arXiv · 2611.16452
Can an LVLM Perceive Event Boundaries Like a Human?
Abstract
Large Vision-Language Models (LVLMs) reason effectively about video content, but whether they perceive its event boundaries in a manner consistent with humans remains unclear. We first investigate this through Generic Event Boundary Detection (GEBD), which identifies event boundaries naturally perceived by humans in continuous video, without relying on predefined event categories. On Kinetics-GEBD dataset, LVLMs miss many boundaries when predicting directly from frames, but effectively refine candidates proposed by an unsupervised discovery method, achieving state-of-the-art unsupervised GEBD performance. We extend this discovery-refinement approach to hour-long egocentric video, where boundary discovery requires a broader semantic scale and whole-video LVLM refinement becomes impractical. We address these challenges through coarse-to-fine temporal discovery and localized LVLM accept/reject judgments. Human evaluation shows that the LVLM's agreement with group consensus falls within the range observed among human annotators, with disagreements concentrated on low-consensus cases. Using this pipeline, we construct EgoBoundary, a benchmark for event boundary detection in hour-scale egocentric video. Representative supervised and unsupervised methods degrade substantially on EgoBoundary, highlighting the challenge of long-horizon event boundary detection.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Hyolim Kang, Jungsoo Lee, Yeji Song, Whie Jung, Janghoon Cho, Juntae Lee. 2026-11-12. Can an LVLM Perceive Event Boundaries Like a Human?. https://searcharxiv.com/abs/2611.16452
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.