For purpose of object recognition, we learn one discriminative classifier based on one prototype, using shape context distances as the feature vector. From multiple prototypes, th...
—In this work, we address the problem of performing class-specific unsupervised object segmentation, i.e., automatic segmentation without annotated training images. Object segmen...
This paper analyses the improvements that can be gained in the generalized Hough transform method for recognizing objects through the use of imperfect perceptual grouping techniqu...
This paper introduces a robust adaptive patches sampling technique. The method does not rely on the use of keypoints to extract local information but all information contained in ...
We propose a novel probabilistic framework for learning
visual models of 3D object categories by combining appearance
information and geometric constraints. Objects are
represen...