Introduces the first large-scale event-based HAR benchmark under low-light and 6-DoF shaking conditions with IMU data, and an EIS-HAR pipeline using non-linear warping for motion compensation plus a four-stage hybrid network that outperforms prior methods on three datasets.
Spiking deep convolutional neural networks for energy-efficient ob- ject recognition.International Journal of Computer Vision, 113:54–66
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DarkShake-DVS: Event-based Human Action Recognition under Low-light andShaking Camera Conditions
Introduces the first large-scale event-based HAR benchmark under low-light and 6-DoF shaking conditions with IMU data, and an EIS-HAR pipeline using non-linear warping for motion compensation plus a four-stage hybrid network that outperforms prior methods on three datasets.