Motionlet LLC coding for discriminative human pose estimation

  title={Motionlet LLC coding for discriminative human pose estimation},
  author={Li Sun and Mingli Song and Dapeng Tao and Jiajun Bu and Chun Chen},
  journal={Multimedia Tools and Applications},
3D human pose estimation is a challenging but important research topic with abundant applications. As for discriminative human pose estimation, the main goal is to learn a nonlinear mapping from image descriptors to 3D human pose configurations, which is difficult due to the high-dimensionality of human pose space and the multimodality of the distribution. To address these problems, we propose a novel motionlet LLC coding in a discriminative framework. A motionlet consists of training examples… CONTINUE READING

Similar Papers

Loading similar papers…