(1) Stereoscopic 3D Video Processing

Perceptual stereoscopic video coding using depth-of-focus blur effects

Example-based video stereolization (EBVS) for 2D-to-3D conversion

Joint geodesic depth propagation and depth up-sampling

Visual comfort assessment and enhancement based on saliency and DIBR

Reliability-based discontinuity-preserving stereo matching

(2) Multimedia Annotation and Retrieval

Semantic annotation based on semi-supervised learning and constraint propagation

Kernel sparse representation-based classification using multi-objective optimization

Content-based summarization and retrieval for news and sports videos

Interactive image retrieval by active learning from relevance feedback

Videotext detection, segmentation, and recognition

(3) Image Super-resolution

Novel Bayesian deringing method using spatial-gradient-local-inhomogeniety prior

Face super-resolution based on convex optimization (l1-norm)

Parallelization of super-resolution reconstruction on GPU and multi-core platforms

Curvature-preserving super-resolution with gradient-consistency-anisotropic-regularization prior

Dictionary-based super-resolution with nonlocal total variation regularization

(4) Computational Photography

High dynamic range imaging by tone mapping and multi-exposure fusion

Specularity removal in color images

Interactive image segmentation by user interactions such as makers and touch

Power-constrained contrast enhancement for low power LCD displays

(5) Perceptual Video Coding and H.265

Perceptual image/video coding using human color perception

Perceptual rate distortion optimization using free energy principles and structural similarity

Blocking artifact reduction using sparse representation

Perceptual block merging for quad-tree based partitioning in H.265

Motion compensated prediction and interpolation in H.265