We study the task of object part extraction and labeling, which seeks to understand objects beyond simply identifiying their bounding boxes. We start from bottom-up segmentation of...
Real-time recognition may be limited by scarce memory and computing resources for performing classification. Although, prior research has addressed the problem of training classif...
Ashish Kapoor, Simon Baker, Sumit Basu, Eric Horvi...
Most pose robust face verification algorithms, which employ 2D appearance, rely heavily on statistics gathered from offline databases containing ample facial appearance variation ...
This paper proposes a novel method for robust and automatic realtime head tracking by fusing face and head cues within a multi-state particle filter. Due to large appearance vari...
ct expressions, and different head orientations. In this paper, we introduce a new approach for realtime 3D face pose discrimination based on active IR illumination from a monocula...