My research interests include machine learning, pattern recognition, and computer vision.
Most of my recent focus is on Label Distribution Learning (LDL). Label Distribution Learning is a novel machine learning paradigm. A label distribution covers a certain number of labels, representing the degree to which each label describes the instance. LDL is a general learning framework which includes both single-label and multi-label learning as its special cases. The right is the top-100 word cloud generated from my recent published papers.