A key problem for "face in the crowd" recognition from existing surveillance cameras in public spaces (such as mass transit centres) is the issue of pose mismatches betwe...
Face recognition using 3D information has been intensively investigated in recent years. The features selected from 3D facial surfaces are invariant to pose and lighting condition...
Abstract. This paper reviews the extensive state of the art in automated recognition of continuous signs, from different languages, based on the data sets used, features computed, ...
Barbara L. Loeding, Sudeep Sarkar, Ayush Parashar,...
In this paper we present a novel approach using a 4D (x,y,z,t) action feature model (4D-AFM) for recognizing actions from arbitrary views. The 4D-AFM elegantly encodes shape and m...
Boosted one-versus-all (OVA) classifiers are commonly used in multiclass problems, such as generic object recognition, biometrics-based identification, or gesture recognition. Join...
Alexandra Stefan (University of Texas at Arlington...