A spiking attention plus SNN pipeline on SpiNNaker hardware recognizes ASL fingerspelling at 83.1% accuracy, 0.565 mW power, and 3 ms latency on event-based datasets.
Introduction and analysis of an event-based sign language dataset,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Neuromorphic visual attention for Sign-language recognition on SpiNNaker
A spiking attention plus SNN pipeline on SpiNNaker hardware recognizes ASL fingerspelling at 83.1% accuracy, 0.565 mW power, and 3 ms latency on event-based datasets.