Datasets > Modality > Images > VIVA (Vision for Intelligent Vehicles and Applications)

VIVA (Vision for Intelligent Vehicles and Applications)


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

Samples

License

  • Unknown

Modalities

Languages

Tasks