AI RESEARCH
Temporal-Aware Spiking Transformer Hashing Based on 3D-DWT
arXiv CS.CV
•
ArXi:2501.06786v2 Announce Type: replace With the rapid growth of dynamic vision sensor (DVS) data, constructing a low-energy, efficient data retrieval system has become an urgent task. Hash learning is one of the most important retrieval technologies which can keep the distance between hash codes consistent with the distance between DVS data. As spiking neural networks (SNNs) can encode information through spikes, they nstrate great potential in promoting energy efficiency.