SOURCE-LINKED INTELLIGENCE

Efficient Multi-Timescale Event Representations for Feed-Forward Object Detection

arXiv · AI, language, vision and robotics · article · Sep 4, 2026 · UTC

Autonomous systems require robust low-latency perception under rapidly changing scene dynamics and challenging illumination. In event cameras object detection commonly relies on recurrent architectures to accumulate sparse temporal information over time. This work investigates how temporal information can be encoded directly within the event representation. We propose a confidence-normalized continuous multi-timescale representation based on logarithmic B-spline temporal encoding together with a geometry-aware local confidence mechanism that exploits the spatial structure of event generation.

Read original source ↗ Open in workspace

recordType

paper

region

Global