SOURCE-LINKED INTELLIGENCE

Event-based Selective Attention for Multi-resolution Fast Region of Interest (ROI) Detection

arXiv · AI, language, vision and robotics · article · Sep 15, 2026 · UTC

Neuromorphic vision systems operate under strict constraints on bandwidth, memory, and energy, particularly at the edge, motivating early mechanisms for data reduction and selective processing. In this work, we investigate a multi-scale training-free, saliency-based, bottom-up visual attention model that operates directly on low-resolution event-based input and selects Regions of Interest (ROI) from the visual scene. The model is evaluated across multiple downscaling factors applied to the incoming event stream, with input resolutions reduced by up to 256x relative to full resolution. Performa

Read original source ↗ Open in workspace

recordType

paper

region

Global