Neural events compress event camera streams into fewer informative tokens via discrete asynchronous autoencoders, achieving on-par or better performance on detection and classification with 2x lower event rate.
A 128× 128 120 db 15 µs latency asynchronous temporal contrast vision sensor.IEEE Journal of Solid-State Circuits 2008; 43(2): 566–576
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
verdicts
UNVERDICTED 6representative citing papers
TIDES simulates realistic event camera streams in continuous time via dynamic Gaussian splatting with adaptive occlusion handling and sensor artifact modeling, claiming SOTA fidelity and better downstream transfer than prior methods.
Presents the ev-CIVIL dataset and benchmark showing that event-based cameras can support real-time detection of cracks and spalling in civil infrastructure under challenging lighting.
GeoIMO uses a yaw-compensated focus of expansion model on event streams to classify independent object motion via scale-invariant residuals without training or labels.
Multi-stage silicon retina on SCAMP-5 achieves 13% lower saliency prediction loss and 47% fewer events than standard DVS using a ~100k-parameter network.
A coarse-to-fine autoregressive framework with multi-scale tokenization and scale-aware control reconstructs human motion from sparse observations and reports SOTA accuracy on AMASS.
citing papers explorer
-
Programmable Silicon Retina on Pixel Processor Array
Multi-stage silicon retina on SCAMP-5 achieves 13% lower saliency prediction loss and 47% fewer events than standard DVS using a ~100k-parameter network.