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...
We describe a novel variational segmentation algorithm designed to split an image in two regions based on their intensity distributions. A functional is proposed to integrate the ...
We report on a system for automatically obtaining high-resolution images of surveillance targets. The system, beginning from a framed target, uses the presence of faces as a cue t...
Alberto Del Bimbo, Andrew D. Bagdanov, Walter Nunz...
Active Appearance Model (AAM) represents the shape and appearance of an object via two low-dimensional subspaces, one for shape and one for appearance. AAM for facial images is cu...
We propose a nonparametric framework based on the beta process for discovering temporal patterns within a heterogenous video collection. Starting from quantized local motion descr...