Sorry, you need to enable JavaScript to visit this website.

A novel scheme for infrared small target detection in compressive domain is presented. First, the original image is separated into two components, i.e., the target and the background. Next, we compress them individually. Finally, the compressed target image is utilized to construct the corresponding compressive detector to perform detection in compressive domain.

In this paper, we propose a method to estimate statistical divergence between probability distributions by a DNN-based discriminative approach and its use for language identification tasks. Since statistical divergence is generally defined as a functional of two probability density functions, these density functions are usually represented in a parametric form. Then, if a mismatch exists between the assumed distribution and its true one, the obtained divergence becomes erroneous.

This paper presents a new method for solving linear inverse problems where the observations are corrupted with a mixed Poisson-Gaussian noise.

Previous works on actor identification mainly focused on static
features based on face identification and costume detection,
without considering the abundant dynamic information contained
in videos. In this paper, we propose a novel method
to mine representative actions of each actor, and show the remarkable
power of such actions for actor identification task.
Videos are firstly divided into shots and represented by BoW
based on spatial-temporal features. Then we integrate the prototype