Codebook-based representations are widely employed in the classification of complex objects such as images and documents. Most previous codebook-based methods construct a single c...
Wei Zhang, Akshat Surve, Xiaoli Fern, Thomas G. Di...
Human visual recognition is based largely on shape, yet effectively using shapes in natural image retrieval is a challenging task. Most existing methods are based on the geometric...
The LiveSync interaction metaphor allows an efficient and nonintrusive integration of 2D and 3D visualizations in medical workstations. This is achieved by synchronizing the 2D sl...
Peter Kohlmann, Stefan Bruckner, Armin Kanitsar, E...
The bottleneck in interactive visual classification is the exchange of information between human and machine. We introduce the concept of the visible model, which is an ion of an ...
We investigate the challenging issue of joint audio-visual analysis of generic videos targeting at semantic concept detection. We propose to extract a novel representation, the Sh...
Wei Jiang, Courtenay V. Cotton, Shih-Fu Chang, Dan...