Most approaches to learn classifiers for structured objects (e.g., images) use generative models in a classical Bayesian framework. However, state-of-the-art classifiers for vecto...
We present a method to simultaneously estimate 3d body pose and action categories from monocular video sequences. Our approach learns a lowdimensional embedding of the pose manifol...
Tobias Jaeggli, Esther Koller-Meier, Luc J. Van Go...
Many applications in image analysis are concerned with the temporal evolution of shapes in video sequences. In situations involving low-contrast, low-quality images, human aid is o...
Shantanu H. Joshi, Anuj Srivastava, Washington Mio
We develop nonparametric Bayesian models for multiscale representations of images depicting natural scene categories. Individual features or wavelet coefficients are marginally de...
Jyri J. Kivinen, Erik B. Sudderth, Michael I. Jord...
We describe how to create with machine learning techniques a generative, videorealistic, speech animation module. A human subject is first recorded using a videocamera as he/she u...