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

In this paper, a novel motion-information-based 3D video coding method is proposed for texture plus depth video, which addresses the issue that the traditional motion estimation methods cannot work well for all types of motion.
The global motion information is exploited to :
1. project the reference frames to the view of current-to- be-encoded frame,
2. The motion compensated virtual frame becomes more similar to the current-to-be-encoded frame.

Large scale images allow pathologists to perform reviews, using
computer workstations instead of microscopes. This trend raises
a wide range of issues related to the management of these massive
datasets. In particular, efficient solutions for data storage and processing
have to be developed in order to deliver increasingly reliable
and faster analyses. In addition, the improvement of workflows also
requires the reinforcement of visualization capabilities. In this paper,
we present a new virtual microscopy (VM) approach for interactivetime

Top-down attention plays an important role in guidance of human attention in real-world scenarios, but less efforts in computational modeling of visual attention has been put on it. Inspired by the mechanisms of top-down attention in human visual perception, we propose a multi-layer linear model of top-down attention to modulate bottom-up saliency maps actively. The first layer is a linear regression model which combines the bottom-up saliency maps on various visual features and objects.

As image tampering becomes ever more sophisticated and commonplace, the need for image forensics algorithms that can accurately and quickly detect forgeries grows. In this paper, we revisit the ideas of image querying and retrieval to provide clues to better localize forgeries. We propose a method to perform large-scale image forensics on the order of one million images using the help of an image search algorithm and database to gather contextual clues as to where tampering may have taken place.

Deriving relationships between images and tracing back their history of modifications are at the core of Multimedia Phylogeny solutions, which aim to combat misinformation through doctored visual media. Nonetheless, most recent image phylogeny solutions cannot properly address cases of forged composite images with multiple donors, an area known as multiple parenting phylogeny (MPP). This paper presents a preliminary undirected graph construction solution for MPP, without any strict assumptions.