时间：2016年5月5日（周四）16:00-17:30 地点：东校区数据科学与jbo竞博电竞官方网站院楼A101
Title:A Brief Overview of RGB-D Object Recognition
Speaker: Richard Cai, Lead Researcher, MSRA
Abstract:
RGB-D object recognition has now become an active research area with the rapid development of commodity depth cameras. These depth cameras, such as Kinect, are capable of recording synchronized color and depth data, which together provide rich multimodal information to depict an object. A noticeable t-rend is that depth camera has been integrated into mobile devices like Google Tango and Microsoft Hololens, which offer an even appealing platform for RGB-D object recognition. Although the captured RGB-D data provides rich multimodal information to depict an object, such as color, texture, appearance (RGB modality) as well as shape and geometry information (depth modality), how to effectively represent each modality and combine the both to improve object recognition remains an open problem.This talk provides a brief overview to recent research efforts in this area,introduces both state-of-the-art algorithms and existing challenges.
Bio:
Dr. RuiCai is a Lead Researcher at Microsoft Research Asia. He received the B.E. and Ph.D. degrees in computer science from Tsinghua University, Beijing, China, in 2001 and 2006, respectively. His research interests include computer vision, multimediaanalysis and retrieval, web search and data mining. He has published more than 50 quality papers in referred international conferences and journals, including CVPR, ICCV, ECCV, WWW, SIGIR, KDD, CIKM, IJCAI, ACM Multimedia, IEEE Multimedia, etc. He also holds 20 granted US / international patents.
Title: Serving big graphs in real-time using distributed in-memory graph engine
Speaker: Bin Shao, Lead Researcher, MSRA
Abstract:
Big data become increasingly connected along with the rapid growth in data volume. Connected data are naturally represented as graphs and they play an indispensable role in a wide range of application domains. Graph processing at scale, however, is facing challenges at all levels, ranging from system architectures to programming models. In this talk, we will review the challenges of building large graph processing systems, overview the design philosophy of Trinity Graph Engine, and introduce a few real-life large graph serving applications.
Bio:
Bin Shao is a lead researcher at Microsoft Research (Beijing, China). He joined Microsoft after receiving his Ph.D. degree from Fudan University in July 2010. Bin Shao is the architect and a core developer of Microsoft Graph Engine, which is a distributed, in-memory, large graph processing engine. His research interests include in-memory databases,
distributed systems, graph query processing, and concurrency control algorithms. The results of his research have appeared in top conferences and leading journals such as SIGMOD, VLDB, ICDE, TPDS, CSCW, and ICDCS