We present an approach for online learning of discriminative appearance models for robust multi-target tracking in a crowded scene from a single camera. Although much progress has...
Learning to program is a unique experience for each student, and it is not fully understood why one person in an introductory programming course learns to program better and more ...
Vennila Ramalingam, Deborah LaBelle, Susan Wiedenb...
We develop a semi-supervised learning method that constrains the posterior distribution of latent variables under a generative model to satisfy a rich set of feature expectation c...
Most real-world data is heterogeneous and richly interconnected. Examples include the Web, hypertext, bibliometric data and social networks. In contrast, most statistical learning...
Lise Getoor, Nir Friedman, Daphne Koller, Benjamin...
We present an active learning framework to simultaneously learn appearance and contextual models for scene understanding tasks (multi-class classification). Existing multi-class a...