—We propose a general methodology (PURE-LET) to design and optimize a wide class of transform-domain thresholding algorithms for denoising images corrupted by mixed Poisson–Gau...
Abstract--This paper presents a new region-based unified tensor level set model for image segmentation. This model introduces a three-order tensor to comprehensively depict feature...
One of the principal bottlenecks in applying learning techniques to classification problems is the large amount of labeled training data required. Especially for images and video, ...
Ajay J. Joshi, Fatih Porikli, Nikolaos Papanikolop...
Fast retrieval methods are critical for large-scale and
data-driven vision applications. Recent work has explored
ways to embed high-dimensional features or complex distance
fun...
It is widely conjectured that the excellent ROC performance of biological vision systems is due in large part to the exploitation of context at each of many levels in a part/whole...