报告人：冯国灿教授（中山大学数学学院教授、博士生导师）

报告题目：LEARNING ZEROTH CLASS DICTIONARY FOR HUMAN ACTION RECOGNITION

报告摘要：In this paper, a discriminative two-phase dictionary learning framework is proposed for classifying human action by sparse shape representations, in which the first-phase dictionary is learned on the selected discriminative frames and the secondphase dictionary is built for recognition using reconstruction errors of the first-phase dictionary as input features. We propose a ”zeroth class” trick for detecting undiscriminating frames of the test video and eliminating them before voting on the action categories. Experimental results on benchmarks demonstrate the effectiveness of our method.

报告时间：2018年5月22日9：30

报告地点：海韵行政楼313

联系人：谭忠教授

欢迎广大师生参加！