IEEE Fellow and RSNZ Fellow, Auckland University of Technology, New Zealand
Kasabov is Life Fellow of IEEE, Fellow of the Royal
Society of New Zealand, Fellow of the INNS College
of Fellows, DVF of the Royal Academy of Engineering
UK. He is the Founding Director of the Knowledge
Engineering and Discovery Research Institute
(KEDRI), Auckland and Professor at the School of
Engineering, Computing and Mathematical Sciences at
Auckland University of Technology, New Zealand.
Kasabov is the 2019 President of the Asia Pacific
Neural Network Society(APNNS) and Past President of
the International Neural Network Society (INNS). He
is member of several technical committees of IEEE
Computational Intelligence Society and Distinguished
Lecturer of IEEE (2012-2014). He is Editor of
Springer Handbook of Bio-Neuroinformatics, Springer
Series of Bio-and Neuro-systems and Springer journal
Evolving Systems. He is Associate Editor of several
journals, including Neural Networks, IEEE TrNN, Tr
CDS, Information Sciences, Applied Soft Computing.
Kasabov holds MSc and PhD from TU Sofia, Bulgaria.
His main research interests are in the areas of
neural networks, intelligent information systems,
soft computing, bioinformatics, neuroinformatics. He
has published more than 620 publications highly
cited internationally. He has extensive academic
experience at various academic and research
organisations in Europe and Asia, including: TU
Sofia Bulgaria; University of Essex UK; University
of Otago, NZ; Advisory Professor at Shanghai Jiao
Tong University and CASIA China, Visiting Professor
at ETH/University of Zurich and Robert Gordon
University UK, Honorary Professor of Teesside
University, UK.Prof. Kasabov has received a number
of awards, among them:Doctor Honoris Causa from
Obuda University, Budapest; INNS AdaLovelace
Meritorious Service Award; NN Best Paper Award
for2016; APNNA ‘Outstanding Achievements Award’;
INNS Gabor Awardfor ‘Outstanding contributions to
engineering applications of neural networks’; EU
Marie Curie Fellowship; Bayer Science Innovation
Award; APNNA Excellent Service Award; RSNZ Science
and Technology Medal; 2015 AUT Medal; Honorable
Member of theBulgarian, the Greek and the Scottish
Societies for ComputerScience. More information of
Prof. Kasabov can be found from:
Speech Title: 'Spiking Neural Networks and Brain-Inspired Computation for Advanced Audio-Visual Information Processing'
talk demonstrates that spiking neural networks
(SNN), named as the third generation of artificial
neural networks, can be used to build brain-inspired
SNN systems (BI-SNN) that are capable of deep,
incremental learning of temporal or spatio/spectro
-temporal data and for various applications.
Similarly, to how the brain learns, these BI-SNN
models do not need to be restricted in number of
layers, neurons in each layer, etc. as they adopt
self-organising learning principles of the brain.
This is different from the traditional deep learning
neural networks that usually have fixed structures
and are difficult to adapt to new data.
The talk explains some basic notions and methods of SNN and BI-SNN, illustrated on an exemplar BI-SNN architecture NeuCube that is built according to a 3D brain spatial template (free software and open source along with a cloud-based version available from www.kedri.aut.ac.nz/neucube). NeuCube can learn both audio and visual information simultaneously, similar to how the brain does it. Through learning, a BI-SNN model creates associations between audio and visual information presented, that can be used for scene understanding.
BI-SNN systems result not only in better classification and prediction accuracy, when used on spatio-temporal audio-visual data, but they also allow to extract meaningful knowledge, thus opening a way of building open and transparent AI in the future.
Reference: N.Kasabov, Time-Space, Spiking Neural Networks and Brain-Inspired Artificial Intelligence, Springer, 2019, https://www.springer.com/gp/book/9783662577134.
Prof. Shahram Latifi
IEEE Fellow, University of
an IEEE Fellow, received the Master of Science egree
in Electrical Engineering from Fanni, Teheran
University, Iran in 1980. He received the Master of
Science and the PhD degrees both in Electrical and
Computer Engineering from Louisiana State
University, Baton Rouge, in 1986 and 1989,
respectively. He is currently a Professor of
Electrical Engineering at the University of Nevada,
Las Vegas. Dr. Latifi is the director of the Center
for Information and Communication Technology (CICT)
at UNLV. He has designed and taught graduate courses
on Bio-Surveillance, Image Processing, Computer
Networks, Fault Tolerant Computing, and Data
Compression in the past twenty years. He has given
seminars on the aforementioned topics all over the
world. He has authored over 200 technical articles
in the areas of image processing, biosurveillance,
biometrics, document analysis, computer networks,
fault tolerant computing, parallel processing, and
data compression. His research has been funded by
NSF, NASA, DOE, Boeing, Lockheed and Cray Inc. Dr.
Latifi was an Associate Editor of the IEEE
Transactions on Computers (1999-2006) and Co-founder
and General Chair of the IEEE Int'l Conf. on
Information Technology. He is also a Registered
Professional Engineer in the State of Nevada.
Speech Title: 'Facial Recognition- The most error-prone, yet enduring modern biometrics trait? '
Abstract: In recent years, there has been much progress in the area of Facial Recognition (FR) that address the shortcomings in conventional FR systems. Spoofing using a high resolution image, high false negative rates due to partial occlusion of the face (ex. mask), and high positive rates due to similarity of subjects are among such shortcomings. Aided by advancements in AI and image acquisition technology (i.e. high resolution 2D/3D) cameras, researchers have been able to push the quality of the facial recognition systems to an impressive new level. Despite the progress, there are still challenging issues lingering around ranging from technology matters (ex. real-time standoff detection) to policy concerns (ex. privacy and ethics). In this talk, I will address the progress in facial recognition and present the state of the art technologies developed by the world software giants such as Google, Facebook, Microsoft and Baidu in FR. Amid the growing concerns about misuse of FR by governments and other public entities, companies have started to move away from broad identification toward more restrictive forms of personal identification. At the end, I will focus on the trade-offs of restrictive FR and the need for including control, privacy and transparency in future systems.
Xidian University, China
Wang Nannan, Huashan Scholar distinguished professor and doctoral supervisor at Xidian University, is currently the director of Intelligent information processing center in State Key Laboratory of Integrated Services Networks. In recent years, he has been engaged in the research of computer vision and statistical machine learning. His research mainly involves cross-domain image reconstruction and credible identity authentication, including sketch-photo synthesis and recognition, image/video super-resolution reconstruction, image restoration, behavior analysis and recognition, person re-identification, etc. He has published over 150 papers in top international journals and conferences such as IEEE TPAMI, IJCV, CVPR, ICCV, ECCV, NeurIPS, ICML, etc. He has received Outstanding Youth Foundation from National Natural Science Foundation of China. He has been selected as Young Elite Scientists Sponsorship Program by China Association of Science and Technology (CAST). He has been awarded the first prize for Ministry of Education Natural Science Award, the first prize for Shaanxi Province Science and Technology Award, the second prize of China Society of Image and Graphics (CSIG) Natural Science Award. He is the recipient of the Chinese Association for Artificial Intelligence (CAAI) Outstanding Doctorate Dissertations Award and Shaanxi Province Outstanding Doctorate Dissertations Award.
Speech Title: ' Cross-domain Image Reconstruction
Abstract: As an important task for “Safe City” construction, city-level video surveillance has evolved from the first generation of "visible" and the second generation of "readable" to the third stage of "intelligible". Due to the wide spatial distribution of city level cameras and large differences in their types and parameters, it is a major challenge to realize the "intelligible" city level video surveillance system. This lecture mainly introduces the recent progress on cross-domain image reconstruction and credible identity authentication technology, including (1) Behavior analysis (abnormal behavior detection, behavior location and recognition): complete semantic information extraction through multi-scale boundary sensitive network for temporal action localization; the differentiation of reconstruction quality of normal and abnormal data through the detection of temporal-spatial fusion features; (2) Cross-modality person re-identification: improving the feature modality invariance by measuring and constraining the modality differences between cross-modality person high-dimensional features; (3) Video object clarity (underlying vision): Improving the representation ability of inter-frame temporal dependence by joint priori information and motion invariance; (4) Cross-domain image synthesis (heterogeneous image generation and image stylization): Transforming the images from different modalities into unified modality to achieve information completion. (5) Cross-domain image recognition (heterogeneous face image recognition): Improving the interpretability and accuracy of cross-domain image synthesis and recognition through representation disentanglement learning. This research can provide a systematic solution for the intelligent analysis of network video streaming; (6) Credible identity authentication: here “credible” mainly refers to reliability and security. The algorithm is supposed to not only defend against external attacks (adversarial learning), but also protect private information.
Prof. Guodong Ye
Guodong Ye was
born in China, He received the PhD degree in
department of Electronic Engineering at City
University of Hong Kong. From 2016 to 2018, He did
the Post-doctoral research at Zhejiang University of
China. At present, Dr. Ye is a Professor in Faculty
of Mathematics and Computer Science at Guangdong
Ocean University of China. His areas of interests
are cryptography, application of chaotic system,
compressive sensing, reversible information hiding,
image encryption, and etc.
Speech Title: ' Compressive Sensing and Random Numbers Insertion based Image Encryption and Hiding Algorithm '
Abstract: Most current image encryption algorithms encrypt plain images directly into meaningless cipher images. Visually, a few of them are vulnerable to illegal attacks on a few sharing platforms or open channels when being transmitted. Therefore, this paper proposes a new meaningful image encryption algorithm based on compressive sensing and information hiding technology, which hides the existence of the plain image and reduces the possibility of being attacked. Firstly, the discrete wavelet transform (DWT) is employed to sparse the plain image. This is followed by confusion operation on pixel positions, where logistic-tent map is employed to produce a confusion sequence. And then the image is compressed and encrypted by compressive sensing to form an intermediate cipher image. Here, measurement matrix is generated using low-dimension complex tent-sine system. To further enhance recovery quality, we suggest that the inter-mediate cipher image be filled with random numbers according to the compression ratio and confusing them to obtain the secret image. Finally, two-dimensional (2D) DWT of the carrier image is performed, followed by singular value decomposition. The singular values of the secret image are embedded into the singular values of the carrier image with certain embedding strength to obtain the final visually meaningful encrypted image.