For what purpose was the dataset created? Was there a specific task in mind? Was there a specific gap that needed to be filled? As surveillance cameras become prevalent in public spaces, using them has proven effective in proactively deterring and preventing such incidents. However, the data collected by these cameras could potentially lead to breaches in privacy for those being filmed. Thus, we hope to find a way to capture scenes of violence while avoiding infringement on personal privacy. DVS cameras can naturally achieve this goal by capturing events of pixel brightness changes. Existing violence detection datasets are filmed with RGB cameras, which cannot ensure privacy preserving.

Numerous studies have demonstrated that the cognitive processes of the human brain can be modeled using the Bayesian theorem for probabilistic inference of the external world. Spiking neural networks (SNNs), capable of performing Bayesian computation with greater physiological interpretability, offer a novel approach to distributed information processing in the cortex. However, applying these models to real-world scenarios to harness the advantages of brain-like computation remains a challenge. Recently, bio-inspired sensors with high dynamic range and ultra-high temporal resolution have been widely used in extreme vision scenarios. Event streams, generated by various types of motion, represent spatiotemporal data.

In this paper, we present EV-Eye, a first-of-its-kind large-scale multimodal eye tracking dataset aimed at inspiring research on high-frequency eye/gaze tracking. EV -Eye utilizes the emerging bio-inspired event camera to capture independent pixel-level intensity changes induced by eye movements, achieving sub-microsecond latency.

Event-based cameras are attracting significant interest as they provide rich edge information, high dynamic range, and high temporal resolution.