时间：2017年12月01日（周五）中午12点30分
When: 12:30 p.m., Friday, Dec. 01, 2017
地点：卫津路校区教职工文化活动中心多功能厅
Where: Multifunctional Hall, Cultural Activity Center for Faculty and Staff, Weijin Road Campus
报告题目：一叶知秋：稀疏/低秩先验下图像信号的部分观测重建
Lecture: Ex pede Herculem: Image Reconstruction From Partial Measurements Based on Sparse/Low-rank Priors
主讲人：杨敬钰
Lecturer: Jingyu Yang
主讲人简介：杨敬钰，男，天津大学自动化学院研究员，博士生导师。2003年毕业于北京邮电大学自动化学院，获学士学位；2009年毕业于清华大学自动化系，获博士学位。2009年9月入职天津大学。2011年在微软亚洲研究院进行访问研究，2012年/2014年到瑞士联邦洛桑理工学院（EPFL）进行学术访问。主要研究方向包括图像与视频稀疏表示，计算机视觉以及立体视频处理。研究受到国家自然科学基金、天津市应用基础与前沿技术研究计划、航天科技集团等机构的资助。在IEEE TIP/CSVT/TMM、CVPR、ECCV、ICME等国际期刊与会议上发表论文70余篇，在国际会议VCIP2016与ICME2017获两项论文奖。
作为主要科研人员，获授权国家发明专利15项，获天津市技术发明一等奖（2016，排名3）、国家技术发明奖二等奖（2008，排名4）等多项省部级科技奖励。入选教育部“新世纪优秀人才支持计划”（2011）、“北洋学者-青年骨干教师计划”（2012）、“北洋青年学者计划”（2014）、天津市创新人才推进计划（青年科技优秀人才，2015）、天津市“131”创新型人才培养工程第二层次人选（2016）。入选IEEE高级会员，担任ICME、VCIP、ICIP等国际会议程序委员会成员20余次，担任VCIP2016专场主席（深度数据分析与处理）和ICIP2017领域主席。
Lecturer: Jingyu Yang received the B.E. degree from the Beijing University of Posts and Telecommunications, Beijing, China, in 2003, and the Ph.D. degree (Hons.) from Tsinghua University, Beijing, in 2009. He was with Microsoft Research Asia (MSRA), Beijing, in 2011, within the MSRA’s Young Scholar Supporting Program, and the Signal Processing Laboratory, EPFL, Lausanne, Switzerland,in 2012, and from 2014 to 2015. He has been a Faculty Member of Tianjin University, Tianjin, China, since 2009, where he is currently a Research Professor with the School of Electrical and Information Engineering. His current research interests include image/video processing, 3D imaging, and computer vision. As a Co-Author, he received the Best 10% Paper Award in the IEEE VCIP 2016 and the Platinum Best Paper Award in the IEEE ICME 2017. He was selected into the Program for New Century Excellent Talents in University from the Ministry of Education, China, in 2011, the Elite Peiyang Scholar Program and the Reserved Peiyang Scholar Program of Tianjin University, in 2012 and 2014, respectively, and the Innovation Talent Promotion Program from Tianjin Municipal Commission of Science and Technology in 2015.
报告内容简介：由于采样欠缺、压缩传感、噪声干扰、传输丢失等原因，许多视觉计算任务中仅获得信号的部分（降质）观测样本。从部分观测样本重建高质量图像信号，不仅可以获得舒适的视觉观感，而且信息的完整化对视觉处理链上后续环节得以稳健地展开具有重要作用。所幸视觉信号在高维空间具有低维结构，从而使得由部分表达整体，从一隅窥见全局成为可能。讲者近五年来围绕信号稀疏/低秩表示理论，面向噪声消除、干扰抑制、运动恢复、结构重建等欠定视觉计算问题进行持续研究。本次报告将梗概梳理这些研究工作，探讨优劣，分享得失，并求教于各位方家。
About the Lecture: In many computer vision tasks, only partial (degraded) measurements of signals are available. Reconstructing the complete version of high-quality visual signals not only provides more comfortable visual reception, but also facilitates robust processing in higher-level vision tasks. Fortunately, visual signals have low dimensional structures in the ambient signal space, which makes it possible to reconstruct the high quality complete signals from partial observations. This talks will summarize our research works in this area, and related ill-posed vision tasks include noise removal, interference suppression, motion recovery, and structure reconstruction.
相关学科：计算机视觉、图像与视频处理
Relevant Discipline: Computer vision, image and video processing
主办单位：校工会、图书馆、科研院、校青年教师联谊会、学生创新实践协会
Organizers: Trade Unions, Library, Office of Science and Technology, Young Teachers Association, Student Association of Innovation and Practicums
