A simple block-based compressed-sensing reconstruction for still images is adapted to video. Incorporating reconstruction from a residual arising from motion estimation and compen...
This work investigates the use of nonlinear dependencies in natural image sequence statistics to learn higher-order structures in natural videos. We propose a two-layer model that...
—In this paper, we propose an analytic-to-holistic approach which can identify faces at different perspective variations. The database for the test consists of 40 frontal-view fa...
Background: Semantic similarity scores for protein pairs are widely applied in functional genomic researches for finding functional clusters of proteins, predicting protein functi...
Jing Wang 0004, Xianxiao Zhou, Jing Zhu, Chenggui ...
We present a novel approach to the problem of detection of visual similarity between a template image, and patches in a given image. The method is based on the computation of a lo...