Contextual reasoning through graphical models such as Markov Random Fields often show superior performance against local classifiers in many domains. Unfortunately, this performanc...
We present a background subtraction algorithm aimed at efciency and robustness to common sources of disturbance such as illumination changes, camera gain and exposure variations, ...
Alessandro Lanza, Federico Tombari, Luigi di Stefa...
We study the challenging problem of localizing and classifying category-specific object contours in real world images. For this purpose, we present a simple yet effective method ...
Bharath Hariharan, Pablo Arbelaez, Lubomir Bourdev...
Abstract. Figure/ground assignment is a key step in perceptual organization which assigns contours to one of the two abutting regions, providing information about occlusion and all...
To bridge the semantic gap in content-based image retrieval, detecting meaningful visual entities (e.g. faces, sky, foliage, buildings etc) in image content and classifying images...