—We present a generative model and inference algorithm for 3D nonrigid object tracking. The model, which we call G-flow, enables the joint inference of 3D position, orientation, ...
Complex human activities occurring in videos can be defined in terms of temporal configurations of primitive actions. Prior work typically hand-picks the primitives, their total...
Most codecs such as MPEG-1,2 are based on processing pixels in predetermined tiles of square blocks. The processing of each block is independent of the object-based contents that m...
A motion-based, correspondence-free technique for human gait recognition in monocular video is presented. We contend that the planar dynamics of a walking person are encoded in a ...
Real world computer vision systems highly depend on reliable, robust retrieval of motion cues to make accurate decisions about their surroundings. In this paper, we present a simp...