Neuromorphic camera events are classified by constructing graphs from sampled spikes and applying residual graph CNNs, which outperform frame-based CNN baselines on six datasets.
Extraction of temporally correlated features from dynamic vision sensor s with spike-timing-dependent plasticity
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Graph-Based Object Classification for Neuromorphic Vision Sensing
Neuromorphic camera events are classified by constructing graphs from sampled spikes and applying residual graph CNNs, which outperform frame-based CNN baselines on six datasets.