题目： Label Distribution Learning and its Applications
报告人： 耿新 教授 东南大学
摘要： Label Distribution Learning (LDL) is a new machine learning paradigm where each instance is associated with a label distribution rather than a single label or a set of labels. The label distribution covers a certain number of labels, representing the degree to which each label describes the instance. This talk will report our recent progresses on label distribution learning and introduce several successful applications of LDL, such as age estimation, pose estimation, multi-label ranking, expression recognition, crowd counting, crowd opinion prediction, etc.