A movie captured by a wearable camera affixed to an actor’s body gives audiences the sense of “immerse in the movie”. The raw movie captured by wearable camera needs stabiliz...
Optical flow in monocular video can serve as a key for recognizing and tracking the three-dimensional pose of human subjects. In comparison with prior work using silhouettes as a ...
Recent work shows how to use local spatio-temporal features to learn models of realistic human actions from video. However, existing methods typically rely on a predefined spatial...
Reliably recovering 3D human pose from monocular video requires models that bias the estimates towards typical human poses and motions. We construct priors for people tracking usi...
Scene recognition in an unconstrained setting is an open and challenging problem with wide applications. In this paper, we study the role of scene dynamics for improved representa...