Recently, models based on conditional random fields (CRF) have produced promising results on labeling sequential data in several scientific fields. However, in the vision task of c...
Huazhong Ning, Wei Xu, Yihong Gong, Thomas S. Huan...
We consider the problem of recognizing human actions from still images. We propose a novel approach that treats the pose of the person in the image as latent variables that will h...
Current approaches to pose estimation and tracking can be classified into two categories: generative and discriminative. While generative approaches can accurately determine human...
Abhinav Gupta, Trista Chen, Francine Chen, Don Kim...
3D human pose estimation in multi-view settings benefits from embeddings of human actions in low-dimensional manifolds, but the complexity of the embeddings increases with the num...