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

arXiv: https://arxiv.org/abs/2609.17134 · HTML: https://mlsanity.com/paper/2609.17134/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 44 references that are in the map.
- First posted on arXiv 15 Sep 2026.

## Builds on (most cited first, 10 of 10)

- [Event-based Vision: A Survey](https://mlsanity.com/paper/1904.08405/) (2019)
- [Recurrent Models of Visual Attention](https://mlsanity.com/paper/1406.6247/) (2014)
- [Learning to Detect Objects with a 1 Megapixel Event Camera](https://mlsanity.com/paper/2009.13436/) (2020)
- [Motion Guided Attention for Video Salient Object Detection](https://mlsanity.com/paper/1909.07061/) (2019)
- [Event-Based Angular Velocity Regression with Spiking Networks](https://mlsanity.com/paper/2003.02790/) (2020)
- [Event-assisted Low-Light Video Object Segmentation](https://mlsanity.com/paper/2404.01945/) (2024)
- [Real-Time Cortical Simulation on Neuromorphic Hardware](https://mlsanity.com/paper/1909.08665/) (2019)
- [Wandering around: A bioinspired approach to visual attention through object motion sensitivity](https://mlsanity.com/paper/2502.06747/) (2025)
- [Enabling Depth-driven Visual Attention on the iCub Humanoid Robot: Instructions for Use and New Perspectives](https://mlsanity.com/paper/1509.06939/) (2015)
- [An event-based implementation of saliency-based visual attention for rapid scene analysis](https://mlsanity.com/paper/2401.05030/) (2024)

## Abstract (arXiv)

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. Performance is assessed on the Prophesee Automotive dataset, the largest publicly available event-based dataset, demonstrating robust ROI selection across different scales on a real-world use-case. The proposed approach is capable of detecting ROIs belonging to multiple object classes, including various vehicle types, pedestrians, traffic lights, and traffic signs, with accuracy up to 70.8%, while operating at millisecond temporal resolution, 16x finer than the temporal resolution provided by the dataset ground truth. These results highlight the potential of combining early event downscaling with saliency-based attention as an effective front-end for efficient edge neuromorphic vision systems.