In this paper, we propose a novel supervised hierarchical sparse coding model based on local image descriptors for classification tasks. The supervised dictionary training is perf...
Abstract. This paper introduces a new framework for image classification using local visual descriptors. The pipeline first performs a nonlinear feature transformation on descripto...
Sparse representation theory has been increasingly used in the fields of signal processing and machine learning. The standard sparse models are not invariant to spatial transform...
This paper introduces a novel way to leverage the implicit geometry of sparse local features (e.g. SIFT operator) for the purposes of object detection and segmentation. A two-clas...
We propose an online algorithm based on local sparse representation for robust object tracking. Local image patches of a target object are represented by their sparse codes with a...