The fact that the eyes are constantly in motion, even during ‘fixation’, implies that retinal ganglion cells' spike times carry information about the visual scene even when the scene is static. Moreover, this motion implies that fine details of the visual scene could not be decoded from pure spatial retinal representations due to smearing. Understanding the interplay of temporal and spatial information in visual processing is thus pivotal for both biological research and bio-inspired computer-vision applications. In this study, we consider data from an event-based camera that was designed to emulate a biological retina in hardware. Similarly to the biological eye, and in contrast to standard frame-based cameras, this camera outputs an event when a change in local illumination intensity is detected. We used this camera to convert datasets of tiny images to datasets of event streams. Using these datasets we demonstrate the contribution of spatio-temporal information to image recognition by artificial neural networks (ANNs). The present work illustrates, for the first time, an advantage for using sparse event-based visual data over the equivalent frame-based data, in a standard computer vision task conducted on tiny images, utilizing precise temporal information. We also demonstrate the benefits of continuous event sequences for unsupervised learning. Interestingly, Vernier hyperacuity emerged in ANNs following training on tiny images, resembling the natural hyperacuity observed in humans. Our findings underscore the essential role of temporal information in visual processing, offering insights for advancing both biological understanding and bio-inspired engineering of visual perception.