VIVA

The VIVA challenge’s dataset is a multimodal dynamic hand gesture dataset specifically designed with difficult settings of cluttered background, volatile illumination, and frequent occlusion for studying natural human activities in real-world driving settings. This dataset was captured using a Microsoft Kinect device, and contains 885 intensity and depth video sequences of 19 different dynamic hand gestures performed by 8 subjects inside a vehicle.

Source: Short-Term Temporal Convolutional Networks for Dynamic Hand Gesture Recognition Image Source: http://www.site.uottawa.ca/research/viva/projects/hand_detection/index.html