DarkShake-DVS: Event-based Human Action Recognition under Low-light andShaking Camera Conditions
Researchers have introduced DarkShake-DVS, a new benchmark dataset designed for human action recognition in challenging low-light and high-motion scenarios. The dataset includes over 18,000 real-world clips captured with synchronized IMU data to address limitations in existing event-based vision research. They also propose EIS-HAR, a novel method that combines motion compensation with a hybrid architecture for improved spatiotemporal feature extraction and action recognition. AI
IMPACT Introduces a new benchmark and method to improve AI's ability to recognize actions in challenging real-world conditions.