We present a hierarchical generative model for object recognition that is constructed by weakly-supervised learning. A key component is a novel, adaptive patch feature whose width...
Recent works in object recognition often use visual words, i.e. vector quantized local descriptors extracted from the images. In this paper we present a novel method to build such ...
Structure from motion (SFM) aims at jointly recovering the structure of a scene as a collection of 3D points and estimating the camera poses from a number of input images. In this...
In this paper we propose an approach capable of simultaneous recognition and localization of multiple object classes using a generative model. A novel hierarchical representation ...
Shock graphs have emerged as a powerful generic 2-D shape representation. However, most approaches typically assume that the silhouette has been correctly segmented. In this paper,...