• Tieniu TAN, PhD, Fellow of CAS, TWAS (The World Academy of Sciences for the advancement of science in developing countries), IEEE and IAPR (the International Association of Pattern Recognition), and an International Fellow of the UK Royal Academy of Engineering. 

Keynote Title: Biologically-inspired Pattern Recognition: the State of the Art

Abstract: 

Pattern recognition has made significant progress in the past decades, both in fundamental theories and in practical applications. However, even the most advanced existing pattern recognition systems still have no comparison with biological systems such as the human visual recognition system, especially in terms of adaptiveness, robustness and usability. It is necessary to seek biological mechanisms and develop biologically inspired pattern recognition to achieve breakthroughs in both theories and applications.

In this talk, I will first review the concept and history of pattern recognition, and outline the biological mechanisms which are expected to be useful in pattern recognition. I will then introduce the state-of-the-art methods in this direction including some of our recent work. Finally, I will discuss some possible directions for future research on biologically-inspired pattern recognition.

• David Feng, PhD, Fellow of ACS, ATSE, HKIE, IEE, and IEEE. Special Area Editor of IEEE Transactions on Information Technology in Biomedicine, and is the current Chairman of IFAC-TC-BIOMED.

Keynote Title: Data Processing and AI for Future Medical Research and Healthcare Delivery

Abstract: 

The repaid growth of various types of data from innumerable diverse sources, such as microwave new sensors, images, and other devices (related to genes, proteins, metabolism, pathology, organs, systems, individuals and population) has created an incredible opportunity for new information findings, knowledge development and services improvements. The large volume of data sets has also created a huge opportunity for artificial intelligence applications in biomedicine. Until very recently, most of biomedical research and healthcare delivery are still based on their traditional ways and their directly related information, such as diagnosis images, blood test results, etc. However, such practices have started to have a revolutionary change, due to much previously ignored information is becoming so relevant, and can possibly be integrated into the biomedical research and healthcare delivery equations, such as precision medicine and disease management. In this talk, we will discuss the impact of big data processing and artificial intelligence in biomedicine and how they will reshape the future medical research and healthcare delivery.

• Jianmin Jiang, PhD, Fellow of IET, UK, Fellow of RSA, UK, Distinguished Professor and Director, Research Institute for Future Media Computing, Shenzhen University

Keynote Title: Context-supported deep learning for EEG-based classification of image-evoked brain activities

Abstract: 

While artificial intelligence becomes hot in computer science, how to bridge the gap between artificial intelligence and human brain intelligence remains a challenge. On one hand, understanding EEGs evoked by visual objects has been active in exploring human brain intelligence, on the other, EEG-based brain activity classification demands more efforts for improvement with respect to its accuracy, generalization, and interpretation, yet the relationship between the EEG signals and the corresponding multimedia content still remains to be further explored. By integrating implicit and explicit learning modalities into a context-supported deep learning framework, a number of improved solutions for classification of brain activities via EEGs are presented in this talk to explore the possible exploitation of brain intelligence. Such exploration contains: (i) a dual-modality learning mechanism via consistency test to exploit the contexts of brain images and establishing a mapping between the visual level features and the EEG cognitive level features; and (ii) a region-level bi-directional attention deep network for EEG-based image classification. Inspired by the hemispheric lateralization of human brain, contextual information can be extracted at regional level to strengthen and emphasize the differences between two hemispheres. The deep learning framework integrates the mechanism of attention to measure and seize the importance of channel-based spatial information, and a bi-directional long short-term memory is applied to capture the dynamic correlations hidden from both the past and the future to the current state in EEG sequences. Extensive experiments are carried out and their results are demonstrated to show the effectiveness of such explored deep learning networks towards computerized understanding and interpretation of brain activities.

• Professor Song Wang received the B.E. degree from Tsinghua University in 1994 and the Ph.D. degree in electrical and computer engineering from the University of Illinois at Urbana–Champaign in 2002. He is currently a professor in the Department of Computer Science and Engineering at University of South Carolina.

Keynote Title: Person Identification across Multiple Moving-Camera Videos

Abstract: 

The use of multiple moving cameras, such as various wearable cameras, provide a new perspective for video surveillance by simultaneously collecting videos from different and time-varying view angles. These videos can better cover the targets and scene of interest. For integrated analysis of such videos, it is important to relate the targets, especially the persons, across these videos and this can be very challenging given their different and time-varying view angles. In this talk, I will describe this new problem of cross-video person identification, discuss its difference from the traditional person re-identification, and then introduce the machine-learning based approaches that can extract view-invariant appearance, motion, and human pose features for handling this cross-video person identification problem.