TIME-E2V: Overcoming limitations of E2VID

In the field of action recognition, event cameras have marked a breakthrough by capturing motion dynamics be-yond the capability of traditional cameras, thanks to their high temporal sensitivity. However, the asynchronous and sparse nature of event data challenges their use with tradi-tional convolutional neural networks (CNNs). The E2VID model offers a solution by transforming event data into con-tinuous video frames, enabling the use of standard CNNs for event-based data analysis. However, it struggles with accu-rately capturing motion speed variations and pauses, limit-ing its effectiveness in scenarios where temporal dynamics are crucial. In response, we introduce TIME-E2V, which integrates spatial embeddings from E2VID with LSTM-derived temporal embeddings from frame timestamps. This combination is processed by a modified 3D convolutional network (C3D), leveraging its inherent strengths in video analysis. Our proposed approach not only overcomes E2VID’s challenges but also delivers competitive perfor-mance across a wide range of dynamic scenes with the lead-ing action recognition networks for event cameras, includ-ing those based on Spiking Neural Networks.