AI RESEARCH
DarkShake-DVS: Event-based Human Action Recognition under Low-light andShaking Camera Conditions
arXiv CS.CV
•
ArXi:2605.20680v1 Announce Type: new Human Action Recognition (HAR) is a fundamental computer vision task with diverse real-world applications. Practical deployments often involve low-light environments and unconstrained 6-DoF camera motion, conditions that degrade visual quality, disrupt temporal coherence, and compromise reliability of existing methods. Event cameras, with high low-light sensitivity and microsecond-level temporal resolution, paired with an inertial measurement unit (IMU), present a promising solution.