Scale and affine-invariant local features have shown excellent performance in image matching, object and texture recognition. This paper optimizes keypoint detection to achieve sta...
Abstract. We address the problem of comparing sets of images for object recognition, where the sets may represent arbitrary variations in an object's appearance due to changin...
Abstract. Super-resolution is a technique to restore the detailed information from the degenerated data. Lots of previous work is for 2D images while super-resolution of 3D models ...
Several state-of-the-art Generic Visual Categorization (GVC) systems are built around a vocabulary of visual terms and characterize images with one histogram of visual word counts....
Florent Perronnin, Christopher R. Dance, Gabriela ...
Recognition of complex activities from surveillance video requires detection and temporal ordering of its constituent "atomic" events. It also requires the capacity to ro...