Abstract. Learned, activity-specific motion models are useful for human pose and motion estimation. Nevertheless, while the use of activityspecific models simplifies monocular t...
Discriminative approaches for human pose estimation model the functional mapping, or conditional distribution, between image features and 3D pose. Learning such multi-modal models ...
We propose a generative statistical approach to human motion modeling and tracking that utilizes probabilistic latent semantic (PLSA) models to describe the mapping of image featu...
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...
—Detecting objects in cluttered scenes and estimating articulated human body parts from 2D images are two challenging problems in computer vision. The difficulty is particularly...