报告题目:Structured Prediction in Computer Vision

报告时间：2015年3月17日星期二13：30

报告地点：健B111

报告人：王振华

报告人简介：王振华博士，2014年毕业于澳洲阿德雷德大学，获工学博士学位。主要研究方向为计算机视觉，机器学习， 图模型推理。 在国际会议和期刊上发表论文7篇，其中包括计算机视觉顶级会议cvpr，著名国际会议accv，顶级期刊tpami。获accv2014最佳论文奖。

报告内容简介：Topic: Structured Prediction in Computer Vision

Abstract: many computer vision problems, like matching, recognition, segmentation and depth estimation target at predicting structured labels like sequences and trees. Structured labels are predicted typically via minimizing an energy function over the labelling space. The presentation includes two parts. Part 1 provides key concepts of structured prediction including the motivations, the approaches of learning the parameters of the energy function from massive data, and how to find the best label given the parameters. Part 2 introduces some new ideas and results in two structured prediction problems, one is human action recognition and the other is semantic image segmentation. No prerequisites are required.