Abstract. Today, digital libraries more and more have to rely on semantic techniques during the workflows of metadata generation, search and navigational access. But, due to the st...
Traditional Markov network structure learning algorithms perform a search for globally useful features. However, these algorithms are often slow and prone to finding local optima d...
This work outlines the design process of a user centered learning object repository. A repository should foster the development and acquisition of both generic and specific informa...
We present a new paradigm for tracking objects in video in the presence of other similar objects. This branch-andtrack paradigm is also useful in the absence of motion, for the di...
Abstract. We propose a novel method to detect human poses in videos by concurrently optimizing body part matching and object segmentation. With a single exemplar image, the propose...