We present a new framework to represent and analyze dynamic facial motions using a decomposable generative model. In this paper, we consider facial expressions which lie on a one d...
Conventional contour tracking algorithms with level set often use generative models to construct the energy function. For tracking through cluttered and noisy background, however,...
Activity Recognition has gained a lot of interest in recent years due to its potential and usefulness for context-aware wearable computing. However, most approaches for activity r...
The synthesis of facial expression with control of intensity and personal styles is important in intelligent and affective human-computer interaction, especially in face-to-face i...
Chan-Su Lee, Ahmed M. Elgammal, Dimitris N. Metaxa...
We present an algorithm for jointly learning a consistent bidirectional generative-recognition model that combines top-down and bottom-up processing for monocular 3d human motion ...
Cristian Sminchisescu, Atul Kanaujia, Dimitris N. ...
In this paper, the problem of face authentication using salient facial features together with statistical generative models is adressed. Actually, classical generative models, and ...
Generative models of pattern individuality attempt to represent the distribution of observed quantitative features, e.g., by learning parameters from a database, and then use such...
We present a two-layer generative model for sport video mining that is composed of a two-layer observation model. The first layer is the Gaussian mixture model (GMM) using framew...
We present a new generative model for relational data in which relations between objects can have either a binding or a separating effect. For example, in a group of students sep...
Generative model learning is one of the key problems in machine learning and computer vision. Currently the use of generative models is limited due to the difficulty in effective...