报告题目：Salient object detection from images and videos
报 告  人：邹文斌 (深圳大学)
报告时间：10月28日 16:00
报告地点：屏峰校区A1区块计算机大楼B315

报告摘要：Salient object detection, which aims at highlighting those objects that mostly draw human attention in an image or video, has become an active research topic in computer vision because of a rising tide of applications to object segmentation, object tracking, and action recognition. This top, on one hand, presents an approach to salient object detection in images, which was originally published as “HARF: Hierarchy-associated Rich Features for Salient Object Detection” in ICCV’2015. On the other hand, this top also introduce recently proposed approach to salient object detection in videos, which formulates spatial and temporal cues as well as a local constraint into a unified framework to achieve a global saliency optimization.

报告人介绍：：
Wenbin Zou received the M.E. degree in software engineering with a specialization in multimedia technology from Peking University, China, in 2010, and the Ph.D. degree from the National Institute of Applied Sciences, Rennes, France, in 2014. From 2014 to 2015, he was a Researcher with the Ecole des PontsParisTech, France. Since then, he has been with the faculty of the College of Information Engineering, Shenzhen University, China. His current research interests include saliency detection, object segmentation, and object tracking. He has authored more than 40 papers in the most prestigious journals and conferences including IEEE Transaction on Image Processing, IEEE international conference on computer vision. He has held grants as PI totaling more than 5 million RMB since 2015, including two projects supported by the National Natural Science Foundation of China and several industrial grants.