This paper presents a new method for 2-D and 3-D shape retrieval based on geodesic signatures. These signatures are high dimensional statistical distributions computed by extractin...
Abstract. This paper introduces a new framework for image classification using local visual descriptors. The pipeline first performs a nonlinear feature transformation on descripto...
Many methods for object recognition, segmentation, etc., rely on tessellation of an image into "superpixels". A superpixel is an image patch which is better aligned with ...
Abstract. In this paper we introduce a new salient object segmentation method, which is based on combining a saliency measure with a conditional random field (CRF) model. The propo...
Esa Rahtu, Juho Kannala, Mikko Salo, Janne Heikkil...
Abstract. We propose a new generative model, and a new image similarity kernel based on a linked hierarchy of probabilistic segmentations. The model is used to efficiently segment ...
Abstract. Multiple-instance learning (MIL) allows for training classifiers from ambiguously labeled data. In computer vision, this learning paradigm has been recently used in many ...
Sparse representation of signals has been the focus of much research in the recent years. A vast majority of existing algorithms deal with vectors, and higher
Ravishankar Sivalingam, Daniel Boley, Vassilios Mo...
Tracking multiple objects is important in many application domains. We propose a novel algorithm for multi-object tracking that is capable of working under very challenging conditi...
This paper introduces a new procedure to handle color in single image super resolution (SR). Most existing SR techniques focus primarily on enforcing image priors or synthesizing i...
Shuaicheng Liu, Michael S. Brown, Seon Joo Kim, Yu...
We introduce a novel nonrigid 2D image registration method that establishes dense and accurate correspondences across images without the need of any manual intervention. Our key in...