•  学术报告

关于举行深圳鹏城实验室陈杰博士学术报告会的通知

发布时间:2019-01-11文章来源:华南理工大学数学学院浏览次数:1891

报告题目:SRN: Side-output Residual Network for Object Symmetry Detection in the Wild

报  告  人:陈杰  博士(深圳鹏城实验室)

报告时间:2019113日(星期日)下午15:30-16:30

报告地点:4号楼318

邀  请  人:曾德炉  副教授

      欢迎广大师生前往!

数学学院

2019111

 

报告简介:

We establish a baseline for object symmetry detection in complex backgrounds by presenting a new benchmark and an end-to-end deep learning approach, opening up a promising direction for symmetry detection in the wild. The new benchmark, named Sym-PASCAL, spans challenges including object diversity, multi-objects, part-invisibility, and various complex backgrounds that are far beyond those in existing datasets. The proposed symmetry detection approach, named Side-output Residual Network (SRN), leverages output Residual Units (RUs) to fit the errors between the object symmetry ground- truth and the outputs of RUs. By stacking RUs in a deep-to-shallow manner, SRN exploits the ‘flow’ of errors among multiple scales to ease the problems of fitting complex outputs with limited layers, suppressing the complex backgrounds, and effectively matching object symmetry of different scales.

 

个人简介:

陈杰博士于2007年在哈尔滨工业大学计算机系取得博士学位。于2007.9开始供职于University of Oulu, Finland201810月至今加入深圳鹏城实验室建立了医学图像分析课题组。2012年曾于美国马里兰大学做访问学者,2015年曾于美国杜克大学做访问学者。他的研究方向包括特征提取,人脸分析,纹理分析,医学图像分析等。目前已经在相关领域内国际顶级期刊和会议发表署名作者文章70余篇,包括TPAMIIJCVTIPPRCVPR等。根据Google Scholar 统计,到20191月初为止,文献被引用次数达2,200+次,其中单篇最高引用达到850余次。他是国际期刊TVCJ Associate Editor,国际会议ACCV CVPRICCVworkshop co-chair,也是国际期刊TPAMI IJCVNeurocomputingGuest editor