Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
UDVideoQA: A Traffic Video Question Answering Dataset for Multi-Object Spatio-Temporal Reasoning in Urban Dynamics
Joseph Raj Vishal, Nagasiri Poluri, Katha Naik +7
Understanding the complex, multi-agent dynamics of urban traffic remains a fundamental challenge for video language models. This paper introduces Urban Dynamics VideoQA, a benchmar…
cs.CV2026
eSkiTB: A Synthetic Event-based Dataset for Tracking Skiers
Krishna Vinod, Joseph Raj Vishal, Kaustav Chanda +3
Tracking skiers in RGB broadcast footage is challenging due to motion blur, static overlays, and clutter that obscure the fast-moving athlete. Event cameras, with their asynchronou…