The HMDB dataset consists of 6766 videos from 51 different action categories. The videos are generally of low quality, with strong camera motion, and non-centered people.
Video classification is a fundamental problem in many video-based tasks. Applications such as autonomous driving technology, controlling drones and robots are driving the demand...
RGB-D action and gesture recognition remains an interesting topic in human-centered scene understanding, primarily due to the multiple granularities and large variation in human...
Motion has shown to be useful for video understanding, where motion is typically represented by optical flow. However, computing flow from video frames is very time-consuming....
Video classification is a fundamental problem in many video-based tasks. Applications such as autonomous driving technology, controlling drones and robots are driving the demand...