We describe a simple model for parsing pedestrians based on shape. Our model assembles candidate parts from an oversegmentation of the image and matches them to a library of exemp...
A commonly considered image manipulation is to conceal undesirable objects or people in the scene with a region of pixels copied from the same image. Forensic mechanisms aimed at ...
Our goal is to segment a video sequence into moving objects and the world scene. In recent work, spectral embedding of point trajectories based on 2D motion cues accumulated from ...
Automatic video browsing requires algorithms for detecting a variety of events, including production effects (e.g., scene breaks and captions) and moving objects. We present new m...
We consider the problem of segmenting an image into foreground and background, with foreground containing solely objects of interest known a priori. We propose an integration mode...