Visit ShanghaiTech University | 中文
HOME > News and Events > Seminars
Saliency Object Detection Via Learning Saliency
Date: 2015/11/27             Browse: 422

Speaker: Huchuan Lu

Time: Nov 27, 10:30am - 11:50am.

Location: Lecture hall, Administration building, Zhangjiang Campus

Abstract:

Saliency object detection, which aims to identify the most important and conspicuous object regions in an image, has received increasingly more interest in recent years. Salient object detection methods can be categorized as bottom-up stimuli-driven and top-down task-driven approaches. Bottom-up methods are usually based on low-level visual information and are more effective in detecting fine details. In contrast, top-down saliency models are able to detect objects of certain sizes and categories based on more representative features from training samples. In this talk, I would like to introduce Bootstrap Learning saliency and Deep Learning Saliency which are from the Top-down perspective.

Bio:

卢湖川,大连理工大学教授,星海学者,信息与通信工程学院副院长,研究方向:计算机视觉、模式识别。在国际顶级会议CVPR、ICCV和顶级期刊IEEE TIP上发表论文20余篇,担任国际期刊IEEE Transaction on Cybernetics Associate Editor.  获得多项国际学术论文奖,包括 ICCV2011 Most Remembered Poster , ICIP2012 Best Student Paper Award Finalist  和 IET Image Processing 2014年 Best Paper . 并有7篇顶级会议论文进入CVPR,ICCV当年会议论文集引用前15位

                                                                                                                        SIST-Seminar 15050