訊息公告

【論文研討】演講公告107.4.18(三)。講題1: Effective Visualization Designs。講題2: Scene Understanding with Deep Learning and Active Learning

Effective Visualization Designs

Time2018/04/18  15:30~17:30

PlaceED117

SpeakerKwan-Liu Ma

 

Abstract

Visualization transforms data into graphical representations that exploit the high-bandwidth channel of the human visual system, leveraging the brain's remarkable ability to detect patterns and draw inferences. It has thus become an indispensable tool in many areas of study involving large, complex data. I will present visualization designs made by my group according to the data characteristics, purpose of visualization, and targeted audience.

 

Speaker Bio                                                                                         

Kwan-Liu Ma (馬匡六) is a professor of computer science and the chair of the Graduate Group in Computer Science (GGCS) at the University of California-Davis, where he directs VIDI Labs and UC Davis Center of Excellence for Visualization. His research spans the fields of visualization, computer graphics, high-performance computing, and user interface design. Professor Ma received his PhD in computer science from the University of Utah in 1993. During 1993-1999, he was with ICASE/NASA Langley Research Center as a research scientist. He joined UC Davis in 1999.

 

Professor Ma is presently leading a team of over 25 researchers pursuing research in scientific visualization, information visualization, visual analytics, visualization for storytelling, visualization interface design, and immersive visualization. For this significant research accomplishments, Professor Ma received the NSF Presidential Early-Career Research Award (PECASE) in 2000, was elected an IEEE Fellow in 2012, and received the 2013 IEEE VGTC Visualization Technical Achievement Award. Professor Ma has been actively serving the research community by playing leading roles in several professional activities including VizSec, Ultravis, EGPGV, IEEE VIS, IEEE PacificVis, and IEEE LDAV. He has served as a papers co-chair for SciVis, InfoVis, EuroVis, PacificVis, and Graph Drawing. Professor Ma was an associate editor for the IEEE Transactions on Visualization and Computer Graphics (TVCG) during 2007-2011 and the Journal of Computational Science and Discovery during 2009-2014. He presently serves on the editorial boards of the IEEE Computer Graphics and Applications (CG&A), the Journal of Visualization, the Journal of Visual Informatics, and the Journal Computational Visual Media.

 

----------------------------------------------------------------------------------------------------------------

 

Scene Understanding with Deep Learning and Active Learning

Time2018/04/18  15:30~17:30

PlaceED117

SpeakerTeng-Yok Lee

 

 

Abstract

With the availability of millions of annotated images, convolution neural networks of deep learning can learn to detect complex image features in different scales and aspects. In this talk, I will describe how we utilized these features to extract high level image semantics, which can be further applied to other applications such as image-based localization. On the other hand, the success of deep learning relies on the amount of annotated data labeled by humans, while data annotation can be slow and expensive. I will also describe how we used active learning, a machine learning strategy, to reduce the images to annotate for object detection.

 

 

Speaker Bio

Teng-Yok Lee is a research scientist of the computer vision group at Mitsubishi Electric Research Laboratories (MERL). His research interests cover 2 aspects: Visual (computer graphics, visualization, and image processing) and Computing (GPGPU, high performance and cloud computing). Before joining MERL in 2015, he worked at Amazon Web Service (AWS) to optimize HPC applications on AWS cloud computing environments. His PhD studies were about the visualization of scientific simulation result, especially time-varying and Computational Fluid Dynamics (CFD) data. He received his BS degree (2000) and MS degree (2002) from Department of Computer Science and Information Engineering at National Chiao-Tung University, Taiwan, and Ph.D. degree (2011) from Department of Computer Science and Engineering at The Ohio State University, USA, in 2011.