A learned input-adaptive threshold gates neuron activations in event-based neural networks, delivering near-SOTA object detection and optical flow with 32-68% fewer synaptic operations.
Object detection with spiking neural networks on automotive event data,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Context-aware Sparse Spatiotemporal Learning for Event-based Vision
A learned input-adaptive threshold gates neuron activations in event-based neural networks, delivering near-SOTA object detection and optical flow with 32-68% fewer synaptic operations.