Home
Call for Papers
Paper Submission
Workshop Program
Accommodation
Travel
Workshop Venue
Social Events
Registration
Organizing Committee
 
KEYNOTE SPEECHES
 
 9:00-10:00, Wednesday, January 22, 2014

On Sparse Representation and Its Application to Image Colorization

Oscar Au, Professor, IEEE Fellow
Hong Kong University of Science and Technology (HKUST)


Sparse representation is a powerful tool to model real-world signals, which suggests that signals of interest live in a low-dimensional linear sub-space spanned by the combinations of atoms from the learned dictionary. Although finding the sparsest representation and the dictionary is generally intractable, recent progresses show approximation algorithms perform well in practice. In this paper, we review the mechanisms of sparse representation and dictionary learning. Moreover, we highlight several representative applications of using sparse representation to solve image processing problems. After that, we demonstrate the usage of sparse representation onto the problem of image colorization. Experimental results show that our colorization algorithm leads to high-quality colorizations with small amount of user inputs.


Oscar C. Au received his B.A.Sc. from Univ. of Toronto in 1986, his M.A. and Ph.D. from Princeton Univ. in 1988 and 1991 respectively. After being a postdoc in Princeton for 1 year, he joined Hong Kong Univ. of Science and Technology (HKUST) as an Assistant Professor in 1992. He is/was a Professor of Dept. of Electronic and Computer Engineering, Director of Multimedia Technology Research Center, and Director of Computer Engineering in HKUST.

His main research contributions are on video/image coding and processing, watermarking/light weight encryption, speech/audio processing. Research topics include fast motion estimation for H.261/3/4/5, MPEG-1/2/4,  and AVS, optimal and fast sub-optimal rate control, mode decision, transcoding, denoising, deinterlacing, post-processing, multi-view coding, view interpolation, depth estimation, 3DTV, scalable video coding, distributed video coding, subpixel rendering, JPEG/JPEG2000, HDR imaging, compressive sensing, halftone image data hiding, GPU-processing, software-hardware co-design, etc. He has published 60+ technical journal papers, 350+ conference papers, 3 book chapters, and 70+ contributions to international standards. His fast motion estimation algorithms were accepted into the ISO/IEC 14496-7 MPEG-4 international video coding standard and the China AVS-M standard. His light-weight encryption and error resilience algorithms are accepted into the China AVS standard. He was Chair of Screen Content Coding AdHoc Group in JCTVC for HEVC. He has 20+ granted US patents and is applying for 70+ more on his signal processing techniques. He has performed forensic investigation and stood as an expert witness in Hong Kong courts many times.

Dr. Au is a Fellow of IEEE and HKIE. He is/was Associate Editors of 8 journals: TCSVT, TIP, TCAS1, JVCIR, JSPS, TSIP, JMM, and JFI. He is guest editor of some special issues in JSTSP and TCSVT. He is/was BoG member and Vice President – Technical Activity of APSIPA. He is/was Chair of 3 technical committees: IEEE CAS MSA TC, IEEE SPS MMSP TC, and APSIPA IVM TC. He is a member of 5 other TCs: IEEE CAS VSPC TC, DSP TC, IEEE SPS IVMSP TC, IFS TC, and IEEE ComSoc MMC TC. He served on 2 steering committees: IEEE TMM, and IEEE ICME. He also served on organizing committee of many conferences including ISCAS 1997, ICASSP 2003, ISO/IEC 71st MPEG in Jan 2005, ICIP 2010, etc. He was/will be General Chair of several conferences: PCM 2007, ICME 2010, PV 2010, MMSP 2015, APSIPA ASC 2015, and ICME 2017. He won 5 best paper awards: SiPS 2007, PCM 2007, MMSP 2012, ICIP 2013, and MMSP 2013. He was IEEE Distinguished Lecturer (DL) in 2009 and 2010, APSIPA DL in 2013 and 2014, and has been keynote speaker multiple times.

 
 
 13:30-14:30, Wednesday, January 22, 2014

3D Video Coding and 3D-HEVC: A Research Perspective

Nam Ling, Ph.D., IEEE Fellow, IET Fellow
Sanfilippo Family Chair Professor

Chair, Department of Computer Engineering
Santa Clara University, U.S.A


In this presentation, we will address the art of 3D video coding and focus on the latest state-of-the-art 3D-High Efficiency Video Coding (3D-HEVC) technology and related research challenges. Following the success of HEVC jointly developed by the Joint Collaborative Team on Video Coding (JCT-VC) of ISO/IEC Motion Picture Experts Group (MPEG) and ITU-T Video Coding Experts Group (VCEG), a second team known as the Joint Collaborative Team on 3D Video (JCT-3V) focuses on developing its 3D extension. This technology goes beyond the traditional stereoscopic and multi-view representations of video and extends to include the use of depth maps and view synthesis. More powerful 3D capabilities coupled with much higher resolution and perceptual quality target toward future devices and content that can be expected for theater, home, and mobile applications. In 3D-HEVC, coding of dependent views, coding of depth maps, synthesizing intermediate views, and optimizing its encoder, pose new challenges in achieving high coding efficiency while maintaining a reasonable computational complexity. In the talk, we will briefly explain 3D video coding principles and concentrate to focus on the coding tools in 3D-HEVC and its future research challenges; we will also briefly highlight some of our current related research.


Nam Ling received the B.Eng. degree from Singapore and the M.S. and Ph.D. degrees from the U.S.A. He is currently the Sanfilippo Family Chair Professor (University Endowed Chair) of Santa Clara University (U.S.A) and the Chair of its Department of Computer Engineering. From 2002 to 2010, he was an Associate Dean for its School of Engineering. Currently, he is also a Consulting Professor for the National University of Singapore, a Guest Professor for Shanghai Jiao Tong University (China), and a Tsuiying Chair Professor for Lanzhou University (China). He has more than 170 publications (including a book) in the fields of video coding and systolic arrays. He also has several adopted standard contributions (normative and informative) and has filed and been granted many U.S. patents. He is an IEEE Fellow due to his contributions to video coding algorithms and architectures. He is also an IET Fellow. He was named IEEE Distinguished Lecturer twice and received the IEEE ICCE Best Paper Award (First Place). He received six awards from the University, four at the University level (Outstanding Achievement, Recent Achievement in Scholarship, President’s Recognition, and Sustained Excellence in Scholarship) and two at the School/College level (Researcher of the Year and Teaching Excellence). He has served as Keynote Speakers for IEEE APCCAS, VCVP, JCPC, IEEE ICAST, IEEE ICIEA, and IET FC & U-Media, as well as a Distinguished Speaker for IEEE ICIEA. He has served as General Chairs/Co Chairs for IEEE Hot Chips, VCVP (twice), IEEE ICME, and IET U-Media. He has also served as Technical Program Co Chairs for IEEE ISCAS, APSIPA ASC, IEEE APCCAS, IEEE SiPS (twice), DCV, and IEEE VCIP. He was Technical Committee Chairs for IEEE CASCOM TC and IEEE TCMM, and has served as Guest Editors/Associate Editors for IEEE TCAS I, IEEE J-STSP, Springer JSPS, and Springer MSSP journals. He has delivered more than 110 invited colloquia worldwide and has served as a Visiting Professor/Consultant/Scientist/ Scholar for many institutions and companies.
 
 
 8:30-9:30, Thursday, January 23, 2014

Perception Inspired Video Processing: From Digital Camera to Ubiquitous Projection

Homer H. Chen, Professor, IEEE Fellow
Department of Electrical Engineering

National Taiwan University

My research team at the Multimedia Processing and Communications (MPAC) Laboratory, National Taiwan University, has been engaged in a variety of research projects related to the processing and communication of multimedia signals, with applications to digital video camera, P2P IPTV, digital home, and music information retrieval. In this talk, I will first briefly introduce our research in the area of music emotion recognition through a series of demos. Then I will zoom in on our recent work on digital autofocus and perception inspired video processing. The former, which is fundamental to digital video cameras, is by no means an easy problem. It drove us to an intermediate solution using light field theory before we eventually came to our present solution with a new look at how to represent focus profile. The latter explores perceptual and cognitive findings of the factors that affect user experience in viewing video. I will show how the new perceptually optimized computational paradigms can drive, for example, video coding and image projection to an unprecedented performance level.


Homer H. Chen received the Ph.D. degree in Electrical and Computer Engineering from University of Illinois at Urbana-Champaign.

Dr. Chen is a renowned expert in multimedia signal processing and communications. His professional career has spanned across academia and industry. Since August 2003, he has been with the College of Electrical Engineering and Computer Science, National Taiwan University, where he is Irving T. Ho Chair Professor. Prior to that, he held various R&D management and engineering positions with U.S. companies over a period of 17 years, including AT&T Bell Labs, Rockwell Science Center, iVast, and Digital Island (acquired by Cable & Wireless). He was a U.S. delegate for ISO and ITU standards committees and contributed to the development of many new interactive multimedia technologies that are now part of the MPEG-4 and JPEG-2000 standards. His professional interests lie in the broad area of multimedia signal processing and communications.

Dr. Chen is an IEEE Fellow. As a Technical Program Co-Chair, he helped revamp the IEEE International Conference on Multimedia and Expo in 2010. He was an Associate Editor of IEEE Transactions on Circuits and Systems for Video Technology from 2004 to 2010, IEEE Transactions on Image Processing from 1992 to 1994, and Pattern Recognition from 1989 to 1999. He served as a Guest Editor for IEEE Transactions on Circuits and Systems for Video Technology in 1999 and for IEEE Transactions on Multimedia in 2011. He is a guest editor of the upcoming Special Issue on Perception-Inspired Video Processing for IEEE Journal of Selected Topics in Signal Processing in 2014.