Prof. Lap-Pui Chau, Nanyang Technological University, Singapore (IEEE Fellow)
Lap-Pui Chau received the Bachelor degree from Oxford Brookes University, and the Ph.D. degree from The Hong Kong Polytechnic University, in 1992 and 1997, respectively. He is an associate professor in School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore. His research interests include fast visual signal processing algorithms, light-field imaging, video analytics for intelligent transportation system, and human motion analysis.
He was a General Chairs for IEEE International Conference on Digital Signal Processing (DSP 2015) and International Conference on Information, Communications and Signal Processing (ICICS 2015). He was a Program Chairs for International Conference on Multimedia and Expo (ICME 2016), Visual Communications and Image Processing (VCIP 2013) and International Symposium on Intelligent Signal Processing and Communications Systems (ISPACS 2010).
He was the chair of Technical Committee on Circuits & Systems for Communications (TC-CASC) of IEEE Circuits and Systems Society from 2010 to 2012. He served as an associate editor for IEEE Transactions on Multimedia, IEEE Signal Processing Letters, IEEE Transactions on Circuits and Systems for Video Technology, and is currently serving as an associate editor for IEEE Transactions on Circuits and Systems II, IEEE Transactions on Broadcasting, and The Visual Computer (Springer Journal). Besides, he was an IEEE Distinguished Lecturer for 2009-2016, and a steering committee member of IEEE Transactions for Mobile Computing from 2011-2013. He is an IEEE Fellow.
Speech Title: Light Field Imaging: Representation, Compression and Applications
Abstract: Light field is a function which is used to describe how light rays propagates through the free space and various optical components, and finally integrates into an image. Conventional cameras record a 2D projection of the light field integration, which inevitably loses a lot of information, especially with respect to each light ray’s angular direction. Owing to the extremely large amount of information the light field contains, the light field cameras are designed to resolve the light ray integration process and capture the extra directional information, which is useful in many applications. This talk will focus on recent progress in light field imaging, which includes representation, compression and new applications.
Prof. Shahram Latifi, UNIVERSITY OF NEVADA, USA (IEEE Fellow)
Shahram Latifi received his M.S. and Ph.D. degrees in Electrical and Computer Engineering from Louisiana State University in 1986 and 1989, respectively. He is currently a Professor of Electrical and Computer Engineering and the Co-Director of Center for Information Technology and Algorithms at the University of Nevada, Las Vegas. Dr. Latifi has taught courses and performed research in various areas including Image Processing and Document Analysis, Data Compression, Remote Sensing, Biometrics, Security, Computer Networks and Machine Learning. He has authored/co-authored over 250 technical articles in reputable journals and conferences. He is the recipient of several research awards including the most recent one- Silver State Scholar research award in 2014. His research has been funded by NSF, NASA, DOE, DoD/DTRA, Boeing, Lockheed and Cray Inc. Dr. Latifi was an IEEE Distinguished Speaker ( 1997-2000), an Associate Editor of the IEEE Transactions on Computers (1999-2006) , Co-founder and General Chair of the IEEE Int'l Conf. on Information Technology (ITCC 2000-2004) and founder and General Chair of Int’l Conf. on Information Technology-New Generations (ITNG 2005-2018). He has delivered keynotes in international IEEE conferences around the world. He has also served on the editorial board of several international journals. He is an IEEE Fellow (2002) and a Registered Professional Engineer in the State of Nevada.
Speech Title: Facts and Fallacies of Machine Learning
Abstract: After being overlooked for a few decades, Machine Learning (ML) has become the center of attention once again, finding its applications in areas such as Healthcare, Education, Security, Transportation, Social media and e-Commerce, to name a few. In gaming, ML techniques have conquered complex games such as Chess, GO and Poker. ML methods, through adaptation and automation, bring about substantial savings in time and money. Factors contributing to the popularity of ML include major advancements in computing power and data storage capacity as well as the exponential growth of data in various fields. The lingering question is whether the advancements in ML can achieve Artificial General Intelligence and, if so, how soon it can be accomplished. An overview of ML, its past, present and future is presented followed by some of the main techniques employed in this area. Examples of how ML techniques benefit different applications are given and, as a specific case, a new ML approach to achieve network security is described. Hot topics of research and future trends of ML are discussed. Finally, socio-economic factors that will accelerate/impede the adoption of ML techniques are presented.
Prof. Chin-Chen Chang, Feng Chia University,Taiwan (IEEE Fellow)
Professor Chin-Chen Chang obtained his Ph.D. degree in computer engineering from National Chiao Tung University. His first degree is Bachelor of Science in Applied Mathematics and master degree is Master of Science in computer and decision sciences. Both were awarded in National Tsing Hua University. Dr. Chang served in National Chung Cheng University from 1989 to 2005. His current title is Chair Professor in Department of Information Engineering and Computer Science, Feng Chia University, from Feb. 2005. Prior to joining Feng Chia University, Professor Chang was an associate professor in Chiao Tung University, professor in National Chung Hsing University, chair professor in National Chung Cheng University. He had also been Visiting Researcher and Visiting Scientist to Tokyo University and Kyoto University, Japan. During his service in Chung Cheng, Professor Chang served as Chairman of the Institute of Computer Science and Information Engineering, Dean of College of Engineering, Provost and then Acting President of Chung Cheng University and Director of Advisory Office in Ministry of Education, Taiwan. Professor Chang's specialties include, but not limited to, data engineering, database systems, computer cryptography and information security. A researcher of acclaimed and distinguished services and contributions to his country and advancing human knowledge in the field of information science, Professor Chang has won many research awards and honorary positions by and in prestigious organizations both nationally and internationally. He is currently a Fellow of IEEE and a Fellow of IEE, UK. And since his early years of career development, he consecutively won Institute of Information & Computing Machinery Medal of Honor, Outstanding Youth Award of Taiwan, Outstanding Talent in Information Sciences of Taiwan, AceR Dragon Award of the Ten Most Outstanding Talents, Outstanding Scholar Award of Taiwan, Outstanding Engineering Professor Award of Taiwan, Chung-Shan Academic Publication Awards, Distinguished Research Awards of National Science Council of Taiwan, Outstanding Scholarly Contribution Award of the International Institute for Advanced Studies in Systems Research and Cybernetics, Top Fifteen Scholars in Systems and Software Engineering of the Journal of Systems and Software, Top Cited Paper Award of Pattern Recognition Letters, and so on. On numerous occasions, he was invited to serve as Visiting Professor, Chair Professor, Honorary Professor, Honorary Director, Honorary Chairman, Distinguished Alumnus, Distinguished Researcher, Research Fellow by universities and research institutes. He also published over serval hundred papers in Information Sciences. In the meantime, he participates actively in international academic organizations and performs advisory work to government agencies and academic organizations.
Speech Title: A Self-Reference Watermarking Scheme based on Wet Paper Coding
Abstract: Fragile watermarking is applied to protect the integrity of the digital media. Current fragile watermarking schemes mainly provide the functionality of detecting and locating the tampered regions of an authorized image. The capability to recover the tampered regions has rarely been discussed in the literature. In fact, the recovery ability is an important issue while proving and maintaining the image integrity. For achieving these purposes, we first utilize the concept of self-reference to preserve the significant information of a protected image. Then we embed the information into the protected image using the technique of wet paper coding. According to experimental results, the new scheme is highly sensitive to detect and locate the tampered area. In particular, the results show that the quality of recovery image is satisfactory.
Prof. Yi Yang, University of Technology Sydney, Australia
Yi Yang is currently a Professor with University of Technology Sydney, Australia, before which was a Post-Doctoral Research with the School of Computer Science, Carnegie Mellon University, Pittsburgh, USA. He received the Ph.D. degree in computerscience from Zhejiang University, Hangzhou, China, in 2010.His current research interest includes machine learning and its applications to multimedia content analysis and computer vision. He has published more than 100 papers in top venues. His work of multi-camera person tracking and identification was elected as one of the 13 incredible Tech innovations by the Huffington post. The system his team has developed achieved the best performance in a few international competitions, including the TRECVID LOC, the Thumos Action Recognition challenge, the MSR-Bing Image retrieval grand challenge. He is a winner of the Google Faculty Research Award, the ARC DECRA award, and the ACS gold disital disruptor.
Speech Title: Weakly Supervised Detection in Images and Videos
Abstract: Deep convolutional neural networks (CNN) achieve superior performance on many computer vision applications, e.g., detection, segmentation, and translation. Annotating a large number of images for training CNNs is tedious which costs lots of resources, especially for complex tasks, e.g., object detection and landmark detections. For example, to annotation an image for detection, one provides a bounding box for each object in images. I will talk about how to minimize the annotation cost for detection. I will first talk about how to design supervision signal, which does not require human annotating or only needs the minimum human annotations. Secondly, exemplified for object detection and facial landmark detection, I will talk how to leverage such supervision to train CNN models for different computer vision applications.