Learning representations for object and activity 面向对象和活动的学习表示.pptxVIP

Human Action Recognition by Representing 3D Skeletons as Points in a Lie Group Raviteja Vemulapalli University of Maryland, College Park. Professor Rama Chellappa Dr. Felipe Arrate Action Recognition from 3D Skeletal Data Motivation: Humans can recognize many actions directly from skeletal sequences. Tennis serve Jogging Sit down Boxing But, how do we get the 3D skeletal data? Cost Effective Depth Sensors Cost effective depth sensors like Kinect State-of-the-art depth-based skeleton estimation algorithm [Shotton 2011] Real-time skeletal sequence J. Shotton, A. Fitzgibbon, M. Cook, T. Shar