We are pleased to announce the following Invited Speakers at ICVISP 2017

Keynote Speaker I


Prof. King Ngi Ngan

Chair Professor, Department of Electronic Engineering, 

The Chinese University of Hong Kong

Title: 3D Morphable Model and its Applications


In this talk, the research work on 3D morphable model and its applications conducted in the Image and Visual Processing (IVP) Laboratory of the Chinese University of Hong Kong (CUHK) is discussed. The 3D morphable model is introduced with respect to the works carried out for face modeling and reconstruction. Its applications to head pose tracking, facial expression tracking, and face reconstruction using a single color image are explored. Demonstrations showing the results obtained are displayed in video. Lastly some future directions will be outlined.


King N. Ngan (F’00) received the Ph.D. degree in Electrical Engineering from the Loughborough University in U.K.  He is currently a chair professor at the Department of Electronic Engineering, Chinese University of Hong Kong. He was previously a full professor at the Nanyang Technological University, Singapore, and the University of Western Australia, Australia. He has been appointed Chair Professor at the University of Electronic Science and Technology, Chengdu, China, under the National ThousandTalents Program(千人计划) since 2012. He holds honorary and visiting professorships of numerous universities in China, Australia and South East Asia.

Prof. Ngan served as associate editor of IEEE Transactions on Circuits and Systems for Video Technology, Journal on Visual Communications and Image Representation, EURASIP Journal of Signal Processing: Image Communication, and Journal of Applied Signal Processing.  He chaired and co-chaired a number of prestigious international conferences on image and video processing including the 2010 IEEE International Conference on Image Processing, and served on the advisory and technical committees of numerous professional organizations.  He has published extensively including 3 authored books, 7 edited volumes, over400 refereed technical papers, and edited 9 special issues in journals. In addition, he holds 15 patents in the areas of imageideo coding and communications. 

Prof. Ngan is a Fellow of IEEE (U.S.A.), IET (U.K.), and IEAust (Australia), and an IEEE Distinguished Lecturer in 2006-2007.

Plenary Speaker I

Photo of Dr Gerald Schaefer

Dr Gerald Schaefer

Loughborough University,UK

Title: Fast compressed domain image retrieval


Content-based image retrieval (CBIR) has been an active research area for many years. However, almost all images are stored in compressed form, the vast majority of CBIR algorithms operate in the (uncompressed) pixel domain. This not only leads to a computational overhead for feature calculation, it can also be shown that image compression affects retrieval accuracy, especially at extreme compression rates.

In my talk, I will discuss efficient and effective CBIR techniques that operate directly in the compressed domain. In particular, I will focus on JPEG compressed images since most images are stored in this format. Our compressed domain retrieval techniques eliminate the need of full decompression for feature extraction while matching common pixel domain methods in terms of retrieval performance. Last not least I will show how retrieval can be achieved without any decompression at all, by exploiting adapted information stored in the header of JPEG files.

Prof. Carlos Ramos


Institute of Engineering – Polytechnic of Porto (ISEP/IPP),Portugal

Speech Title: Computer Vision in the Artificial Intelligence boom era

Abstract:Computer Vision deals with how to automatically obtain high-level understanding from digital images. On one hand, recent advances in Artificial Intelligence (AI), namely in fields like Machine Learning, particularly in Neural Networks, together with the evolution of the hardware processing capabilities, are allowing advances in the Computer Vision field. On the other hand, in the AI era, at the same time that methods and techniques evolve, the requests imposed to Computer Vision integrated in AI systems become more demanding. If we look at the main evolutions expected for the next decades, from intelligent robots and autonomous vehicles to the ambient assisted living, the ability to obtain information using a different range of sensing channels is essential. As the richest sensing channel, Computer Vision plays a unique role for this purpose. During many years the “singularity” was seen as a hypothetical moment in time when artificial intelligence will have progressed to the point of a greater-than-human intelligence. With the boom in AI, defined today as strategic for most important companies, we are taking large steps in the direction of the singularity moment. However, as we can easily understand, we are still far from obtaining the kind of human ability to join sensorial capabilities, namely vision, with knowledge and reasoning performances, in order to be comparable with the human being at this level. In spite of achieving Computer Vision systems able to perform better than the human being, we are in a phase in which it is much more credible to think in the cooperation human-computer vision. As an example, we can select the case of medical image, as tomography, that due the dimension of the problem is a huge effort for the analysis of the human being. Image processing plays an important role to identify better to which set of images one expert should focus the attention. In which tasks we will achieve computer vision systems able to replace the better of the experts, and in which tasks this is not still possible is something that we will understand with the evolution of the research fields of Computer Vision and Artificial Intelligence.


Carlos Ramos was born in São Paulo, Brazil, in 1963. He got his 5-years graduation from the University of Porto, Portugal, in 1986 and the PhD degree from the same university in 1993. In 2001 he got the “agregação” (academic career maturity top level).

 Between 1986 and 1995 Carlos Ramos was Assistant and Professor at the University of Porto and worked in the areas of Artificial Intelligence, Robotics, and Computer Vision. In 1993, after his PhD, Carlos Ramos joined the Institute of Engineering – Polytechnic of Porto (ISEP-IPP), as Coordinator Professor, where we created GECAD, a Research Centre oriented for Intelligent Systems areas. He was responsible for more than 20 national and international R&D projects. He published more than 300 papers in scientific conferences and more than 60 in international scientific journals. Currently his main interests of activity are centered in Ambient Intelligence field. His publication “Ambient Intelligence: the next step for AI” is one of the 3 most cited publications of Ambient Intelligence field on the last 10 years.

In March 2010 Carlos Ramos was appointed as Vice-President of the Polytechnic Institute of Porto. He assumes the responsibility for the R&D, Innovation and Internationalization areas. 


Prof. Goreti Marreiros

Polytechnic Institute of Porto (ISEP),Portugal

Speech title:Social Signal Processing: Computer Vision and Affective Computing


We are living in a world increasingly affected by new technologies and more sophisticated devices, and Computer Vision will make it possible for computer systems to perceive, learn and adapt to the environment. These new smart environments must be ready to capture and understand human behaviours, usually displayed in a social context, so that they can improve the quality of life by anticipating each users needs. In my presentation I will address  Social Signal Processing, a new technological domain which relies on Computer Vision features to process human social signals and behaviours and make computer systems more intelligent.


Goreti Marreiros is graduated in Computer Science since 1995, have a master in Information Management (2002) both from the Porto University, and a PhD in Informatics-Artificial Intelligence from Minho University (2008). Since 1997 she is a professor in the Department of Computer Engineering at the School of Engineering of the Polytechnic Institute of Porto (ISEP). Goreti Marreiros is also researcher and sub-director of GECAD – Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development, having participating in over 25 research projects, and actually she is coordinating 4 research projects. In the last years she has taught and been responsible for a number of courses on Decision Support Systems, Multiagent Systems and on Artificial Intelligence at the graduate and postgraduate level. 

She is currently working in applying Artificial intelligence techniques (e.g. multi-agent systems, knowledge based systems, knowledge discovery techniques) to the creation of smart environments. Since 2002 she authored more than 100 scientific publications, 50 of which in international journals and books. Along these years she has been participating in renowned international conferences as member of the Program Committee, as Program Chair or reviewer. She has been also keynote speaker in several conferences and guest editor and/or member of editorial board of scientific international journals. She is also vice-president of APPIA – Portuguese Association of Artificial Intelligence.

Quick Links

Best Paper Awards 

Several best paper Awards SELECTED from different sessions  will be given at the dinner banquet of ICVISP 2017. 

Media Partner




Japan is a stratovolcanic archipelago of 6,852 islands. The four largest are Honshu, Hokkaido, Kyushu and Shikoku, which make up about ninety-seven percent of Japan's land area. The country is divided into 47 prefectures in eight regions. The population of 126 million is the world's tenth largest. Japanese people make up 98.5% of Japan's total population.  


Ms. Anna H. M. Wong

Email: icvisp@iased.org

Tel:+852-30696823 (English)

Monday-Friday, 9:30am-12:00pm and 1:30pm-6:00pm