We propose a framework to learn statistical shape models for faces as piecewise linear models. Specifically, our methodology builds upon primitive active shape models(ASM) to hand...
Parameterized Appearance Models (PAMs) (e.g. eigentracking, active appearance models, morphable models) use Principal Component Analysis (PCA) to model the shape and appearance of...
Face recognition in video has gained wide attention due to its role in designing surveillance systems. One of the main advantages of video over still frames is that evidence accumu...
In this paper, we present a novel approach for human activities recognition in the video. We analyze human activities in the sequential frames because human activities can be cons...
We present a method to analyze daily activities, such as meal preparation, using video from an egocentric camera. Our method performs inference about activities, actions, hands, a...