Abstract. The goal of this work is to build video cameras whose spatial and temporal resolutions can be changed post-capture depending on the scene. Building such cameras is diffic...
Abstract. We describe a clustering approach with the emphasis on detecting coherent structures in a complex dataset, and illustrate its effectiveness with computer vision applicat...
In order for recognition systems to scale to a larger number of object categories building visual class taxonomies is important to achieve running times logarithmic in the number o...
Most state-of-the-art approaches to action recognition rely on global representations either by concatenating local information in a long descriptor vector or by computing a single...
Abstract. Image segmentation techniques typically require proper weighting of competing data fidelity and regularization terms. Conventionally, the associated parameters are set t...