We extend the "Sparse LDA" algorithm of [7] with new sparsity bounds on 2-class separability and efficient partitioned matrix inverse techniques leading to 1000-fold spe...
We propose a novel approach for shape-based segmentation based on a specially designed level set function format. This format permits us to better control the process of object re...
Abstract. We present a comparative study on how to use discriminative learning methods such as classification, regression, and ranking to address deformable shape segmentation. Tra...
Jingdan Zhang, Shaohua Kevin Zhou, Dorin Comaniciu...
We describe a new projectively invariant representation of disjoint contour groups which is suitable for shape-based retrieval from an image database. It consists of simultaneous ...
The MPEG-7 dominant color descriptor (DCD) is an effective, compact, and intuitive representation of salient colors in an image region and is very useful for contentbased image re...