the 10 · lectures given by world renowned scholars, regular sessions with broad coverage, and some...
TRANSCRIPT
The 10th International Conference on
Brain-Inspired Cognitive System
13-14 July 2019, Guangzhou China
• School of Computer Science, Guangdong Polytechnic Normal
University (广东技术师范大学计算机科学学院)
• Committee for Master Degree of Education, Guangdong Polytechnic
Normal University (广东技术师范大学教育硕士学位分委员会)
• Guangdong Society of Image and Graphics (广东省图象图形协会)
• University of Strathclyde (斯克莱德大学)
• Edinburgh Napier University (爱丁堡龙比亚大学)
• Northwestern Polytechnical University (西北工业大学)
• Sun Yat-sen University (中山大学)
• Guangdong University of Technology (广东工业大学)
BICS-2019, Guangzhou, China
Hosted by
Co-Sponsored by
General co-Chairs
Huimin Zhao Amir Hussain Jinchang Ren
Jun Cai Jiangbin Zheng Rongjun Chen
Honorary co-Chairs
David Feng Igor Aleksander Tariq Durrani
Tieniu Tan Derong Liu
Program Chairs
Chenglin Liu, China
Jiangqun Ni, China
Bin Luo, China
Kaizhu Huang, China
Jin Zhan, China
Workshop co-Chairs
Chunmei Qing, China
Erfu Yang, UK
Zhijing Yang, China
Zheng Wang, China
Publication Chairs
Jamie Zabalza, UK
Yijun Yan, UK
Publicity Chairs
Haibo He, USA
Newton Howard, USA
El-Sayed El-Alfy, Saudi Arabia
Mohamed Chetouani, France
Anna Esposito, Italy
Giacomo Indiveri, Switzerland
Stefan Wermter, Germany
Erik Cambria, Singapore
Jonathon Wu, Canada
Syed Abd Rahman Al-Attas, Malaysia
Registrations and Local Arrangements Chairs
Jin Zhan, China
Jujian Lv, China
Guoliang Xie, UK
Finance Chairs
Sophia Zhao, UK
Yinyin Xiao, China
Organization Committee
Shaoming Luo, China (Chair)
Qingyun Dai, China
Huimin Zhao, China
Jinchang Ren, UK
Wei Huang, China
Wenxin Deng, China
Rongjun Chen, China
Jin Zhan, China
Yinyin Xiao, China
Jujian Lv, China
Leijun Wang, China
Weijian Li, China
Zhaoming Liu, China
Guoliang Xie, UK
Program Committee
Andrew Abel, Stirling University, UK
Peter Andras, Keele University, UK
Xiang Bai, Huazhong University of Science &
Technology, China
Vladimir Bajic, KAUST, Thuwal, Saudi Arabia
Yanchao Bi, Beijing Normal University, China
Jianbiao Zhang, Beijing University of Technology,
China
Erik Cambria, Nanyang Technological University,
Singapore
Lihong Cao, Communication University of China,
China
Chun-I Philip Chen, California State University,
Fullerton
Mingming Cheng, Nankai University, China
Dazheng Feng, Xidian University
David Yushan Fong, CITS Group
Marcos Faundez, Zanuy Tecnocampus, Barcelona,
Spain
Alexander Gelbukh, CIC IPN, Mexico
Hugo Gravato, Marques ETH Zurich, Zurich,
Switzerland
Fei Gao, Beihang University, China
Claudius Gros Goethe, University Frankfurt,
Germany
Junwei Han, Northwestern Polytechnical
University, China
Qi Wang, Northwestern Polytechnical University,
China
Xinbo Zhao, Northwestern Polytechnical
University, China
Jiangbin Zheng, Northwestern Polytechnical
University, China
Jiang Zejun, Northwestern Polytechnical
University, China
Wang Lifang, Northwestern Polytechnical
University, China
Dongmei Jiang, Northwestern Polytechnical
University, China
Yanning Zhang, Northwestern Polytechnical
University, China
Lei Xie, Northwestern Polytechnical University,
China
Yong Xia, Northwestern Polytechnical University,
China
Tiejun Huang, Peking University, China
Mingchen Feng, Northwestern Polytechnical
University, China
Hichem Sahli, Vrije Universiteit Brussel, Belgium
Xiangjian He, Northwestern Polytechnical
University and University of Technology, Sydney
Bingliang Hu, Xi’an Institute of Optics and
Precision Mechanics, Chinese Academy of
Sciences, China
Xiaoqiang Lu, Xi’an Institute of Optics and
Precision Mechanics, Chinese Academy of
Sciences, China
Xuelong Li, Xi’an Institute of Optics and Precision
Mechanics, Chinese Academy of Sciences, China
Lianru Gao, Key Laboratory of Digital Earth
Science, Institute of Remote Sensing and Digital
Earth, Chinese Academy of Sciences, China
Bing Zhang, Key Laboratory of Digital Earth
Science, Institute of Remote Sensing and Digital
Earth, Chinese Academy of Sciences, China
Fengling Jiang, Institute of Intelligent Machines,
Hefei Institutes of Physical Science, Chinese
Academy of Sciences, China
Diego Monteiro, Xi'an Jiaotong Liverpool
University, China
Kaizhu Huang, Xi'an Jiaotong Liverpool
University, China
Rui Zhang, Xi'an Jiaotong Liverpool University,
China
Jieming Ma, Xi'an Jiaotong Liverpool University,
China
Sheng-Uei Guan, Xi'an Jiaotong Liverpool
University, China
Amir Hussain, Stirling University, UK
Rongrong Ji, Xiamen University, China
Yi Jiang, Institute of Psychology, Chinese
Academy of Sciences, China
Jingpeng Li, Stirling University, UK
Yongjie Li, University of Electronic Science and
Technology of China, China
Cheng-Lin Liu, Institute of Automation, Chinese
Academy of Sciences, China
Hongmei He, Cranfield University, UK
Minghui Wang, Sichuan University, China
Jing Liu, Institute of Automation, Chinese
Academy of Sciences, China
Hua Han, Institute of Automation, Chinese
Academy of Sciences, China
Fu-Jen Kao, National Yang-Ming University,
China
Weifeng Liu, China University of Petroleum,
China
Iman Yi Liao, University of Nottingham Malaysia
Campus
Bin Luo, Anhui University, China
Yu-Mei Zhang, Anhui University, China
Zhaoxia Yin, Anhui University, China
Aihua Zheng, Anhui University, China
Bo Jiang, Anhui University, China
Jinjin Zheng, University of Science and
Technology of China, China
Baochuan Fu, University of Science and
Technology of China, China
Chuangyin Dang, City University of Hong Kong,
China
Mufti Mahmud, University of Padova, Italy
Zeeshan Malik, Stirling University, UK
Deyu Meng, Xi'an Jiaotong University, China
Tomas Henrique Maul, University of Nottingham
Malaysia Campus
Junaid Qadir National, University of Sciences and
Technology, Islamabad
Jinchang Ren, University of Strathclyde, UK
David Li, University of Strathclyde, UK
Winifred Ijomah, University of Strathclyde, UK
Yijun Yan, University of Strathclyde, UK
Jaime Zabalza, University of Strathclyde, UK
Neil Mackin, Capita plc, UK
Simone Scardapane Sapienza, University of Rome,
Italy
Bailu Si, Shenyang Institute of Automation,
Chinese Academy of Sciences, China
Mingli Song, Zhejiang University, China
Genyun Sun, China University of Petroleum (East
China), China
Meijun Sun, Tianjin University, China
Zheng Wang, Tianjin University, China
Wei Feng, Tianjin University, China
Bei Hong, Hubei university, China
Walid Taha, Halmstad University, Sweden
Dacheng Tao, University of Technology, Sydney,
Australia
Dagan Feng, University of Sydney, Australia
Yonghong Tian, Peking University, China
Isabel Trancoso, INESC-ID, Portugal
Stefano Vassanelli, University of Padova, Italy
Liang Wang, Institute of Psychology, Chinese
Academy of Sciences, China
Yungang Zhang, Yunnan Normal University,
China
Junfeng Jing, Xi'an Polytechnic University, China
Jie Ren, Xi'an Polytechnic University, China
Zhijiang Wang, Institute of Mental Health, Peking
University, China
Hui Wei, Fudan University, China
Jonathan Wu, University of Windsor, Canada
Qiang Wu, University of Technology Sydney,
Australia
Weidong Cai, University of Sydney, Australia
Min Xu, Northwestern Polytechnical University
and University of Technology, Sydney
Erfu Yang, University of Strathclyde, Glasgow,
UK
Tianming Yang, Institute of Neuroscience, China
Chunmei Qing, South China University of
Technology, China
Zhijing Yang, Guangdong University of
Technology, China
Nian Cai, Guangdong University of Technology,
China
Jin Zhan, Guangdong Polytechnic Normal
University, China
Rongjun Chen, Guangdong Polytechnic Normal
University, China
Daoqiang Zhang, Nanjing University of
Aeronautics and Astronautics, China
Li Zhang, University of Birmingham, Birmingham,
UK
Yifeng Zhang, Institute of Neuroscience, China
Huimin Zhao, Guangdong Polytechnic Normal
University, China
Qingyun Dai, Guangdong Polytechnic Normal
University, China
Jun Cai, Guangdong Polytechnic Normal
University, China
Jujian Lv, Guangdong Polytechnic Normal
University, China
Leijun Wang, Guangdong Polytechnic Normal
University, China
Fangyuan Lei, Guangdong Polytechnic Normal
University, China
Yinyin Xiao, Guangdong Polytechnic Normal
University, China
Bing Zhou, Sam Houston State University, USA
Chenxiao Hu, Shanghai University, China
Jianzhen Tang, Shanghai University, China
Cuntai Guan, Nanyang Technological University,
Singapore
Jun Wang, Beihang University, China
Banghua Yang, Beihang University, China
Xiaolin Hu, Tsinghua University, China
Huaping Liu, Tsinghua University, China
Hui Chen, Tsinghua University, China
Guiguang Ding, Tsinghua University, China
Jun Zhu, Tsinghua University, China
Zijia Lin, Microsoft ,USA
Jungong Han, Lancaster University, Lancaster,
UK
Cailing Wang, Xi'an Shiyou University, China
Jia Wen, Tianjin Polytechnic University, China
Jeevanandam Jotheeswaran, Galgotias University,
India
Aizhu Zhang, China University of Petroleum,
China
Genyun Sun, China University of Petroleum,
China
The 10th International Conference on Brain-Inspired
Cognitive System
(BICS’2019)
Welcome to the Proceedings of BICS 2019 - the 10th International Conference on
Brain Inspired Cognitive Systems. BICS has now become a well-established
conference series on brain-inspired cognitive systems around the world, with growing
popularity and increasing quality. BICS 2019 followed on from BICS 2004 (Stirling,
Scotland, UK), BICS 2006 (Island of Lesvos, Greece), BICS 2008 (Sao Luis, Brazil),
BICS 2010 (Madrid, Spain), BICS 2012 (Shenyang, China), BICS 2013 (Beijing,
China), BICS 2015 (Hefei, China), BICS 2016 (Beijing, China) and BICS 2018
(Xi’an, China).
Geographically located at the south of China, Guangzhou is the capital city of
Guangdong Province. It covers an area of 7,434 square kilometers. With a population
of about 14 million, the city, which is a civilized city of more than 2,200 years, was
the main port of the Maritime Silk Road in history. The city has always been the
political, economic and culture center of South China for more than 2000 years. The
climate here is so pleasant through out the whole year that it seems there were
4 springs in the city. There are lots of trees and flowers in it, which wins the
name of flower city. Because of its beautiful scenery, tourists from home and
abroad are deeply attracted.
BICS 2019 aims to provide a high-level international forum for scientists, engineers,
and educators to present the state of the art of brain inspired cognitive systems
research and applications in diverse fields. The conference will feature plenary
lectures given by world renowned scholars, regular sessions with broad coverage, and
some special sessions and workshops focusing on popular and timely topics.
BICS 2019 conference proceedings will be published as part of Springer LNAI
Series and indexed by EI. Selected best papers will be recommended to SCI Journals
including Cognitive Computation (Impact Factor 4.279). Selected papers will also be
recommended to several journal special issues including Journal of the Franklin
Institute, Complexity (Hindawi) and others.
BICS 2019 conference is mainly hosted by Guangdong Polytechnic Normal
University (GPNU) and Guangdong Society of Image and Graphics (GSIG). Many
organizations and volunteers made great contributions toward the success of this
event. We are grateful to the great support from University of Strathclyde, Edinburgh
Napier University, Northwestern Polytechnical University, Sun Yat-sen University
and Guangdong University of Technology. We would also like to sincerely thank all
the committee members for their great efforts and time in organizing the event.
Special thanks go to the Program Committee members and reviewers whose insightful
reviews and timely feedback ensured the high quality of the accepted papers and the
smooth flow of the conference. We would also like to thank the publisher, Springer.
Finally, we would like to thank all the speakers, authors, and participants for their
support.
July 2019
Huimin Zhao
Amir Hussain
Jinchang Ren
Jun Cai
Jiangbin Zheng
Rongjun Chen
Programme
Friday 12 July 2019 Venue: Ramada Pearl Hotel Guangzhou (lobby)
14:00-21:30 Registration
Saturday 13 July 2019
Venue: Room 208, #1 Teaching Building, Guangdong Polytechnic Normal University
08:30-09:05 Bus from hotel to GPNU
Registration
09:05- 09:30
Open Ceremony
(Chairs: Huimin
Zhao and
Jinchang Ren)
Introduction to the VIPs
Open speech (Prof. Shaoming Luo, President of GPNU, China)
Welcome speech (Prof. Amir Hussain, Chair of BICS'19, Edinburgh Napier University, UK)
Programme summay (Prof. Jiangqun Ni, Program Chair of BICS'19, Guangdong Society of Image and
Graphics, Sun Yat-sen University)
09:30- 10:20
Keynote Speech
#1
Biologically-inspired Pattern Recognition: the State of the Art (by Prof. Tieniu Tan, Chinese Academy of
Sciences, China)
10:20-10:50 Group Photos and Tea Break
10:50-11:40
Keynote Speech #2
(Chair: Amir
Hussain)
Data Processing and AI for Future Medical Research and Healthcare Delivery (by Prof. David Feng, The
University of Sydney, Australia)
11:40- 12:00
Special Report
#1
The Integration and Development of Intelligent Computing technology and Vocational Education Teaching (Prof. Huimin Zhao and Yinyin Xiao,
GPNU, China)
Special Report
#2
Exploration on the Training of Senior Talents in the Information Technology Direction of Vocational and Technical Education (Prof. Jun Cai and Yinyin Xiao,
GPNU, China)
12:00-12:35 Bus journey back to hotel
12:35-13:45
Lunch California Cafe Hall, Ramada Pearl Hotel Guangzhou
(Ground Floor)
Venue: Conference Hall #7, Ramada Pearl Hotel Guangzhou (2nd Floor)
13:45-14:30
Keynote Speech #3
(Chair: Jiangqun
Ni)
Enhanced water consumption behaviour through intelligent IoT technologies (by Prof. Shuanghua
Yang, Southern University of Science and Technology, China)
14:30-15:10
Oral Session I
Conference Hall 7, Ramada Pearl Hotel Guangzhou (2nd Floor)
15:10-15:40 Tea Break and Poster Session I (chair: Jin Zhan
and Zheng Wang)
15:40-17:15
Oral Session I
(Continued)
(Chair: Kaizhu Huang)
Conference Hall 7, Ramada Pearl Hotel Guangzhou (2nd Floor)
17:15-17:45 Poster Session I (chair: Jin Zhan and Zheng Wang)
18:30-20:30
Dinner Regal Gallery (A) Room, Ramada Pearl Hotel
Guangzhou (1st Floor)
Sunday 14 July 2019
Venue: Conference Hall #7, Ramada Pearl Hotel Guangzhou (2nd Floor)
08:45-
09:30 Keynote
Speech #4 (Chair:
Jinchang
Ren)
Person Identification across Multiple
Moving-Camera Videos (by Prof. Song Wang,
University of South Carolina, USA)
09:30-
10:10
Oral
Session II Conference Hall 7, Ramada Pearl Hotel Guangzhou
(2nd Floor)
10:10-10:40 Tea Break and Poster Session II (Chairs: Zhijing
Yang and Jing Zhao)
10:40-
12:25 Oral
Session II
(Continued)
(Chair:
Meijun
Sun)
Conference Hall 7, Ramada Pearl Hotel Guangzhou
(2nd Floor)
12:25-12:45 Poster Session II (Chairs: Zhijing Yang and Jing
Zhao)
12:45-
13:45 Lunch
California Cafe Hall, Ramada Pearl Hotel Guangzhou
(Ground Floor)
13:45-
14:30 Keynote
Speech #5 (Chair:
Song
Wang)
MAT: Information Theoretical Adversarial Example
Theory and Applications (by Prof. Kaizhu Huang,
Xi'an Jiaotong-Liverpool University, China) 14:30-
15:10
Oral
Session III Conference Hall 7, Ramada Pearl Hotel Guangzhou
(2nd Floor)
15:10-15:40 Tea Break and Poster Session III (Chairs: Rongjun
Chen and Rui Zhang)
15:40-
17:15 Oral
Session III
(Continued)
(Chair:
Zheng
Wang)
Conference Hall 7, Ramada Pearl Hotel Guangzhou
(2nd Floor)
17:15-17:45 Poster Session III (Chairs: Rongjun Chen and Rui
Zhang)
18:30-
20:30
Closing Ceremony
Regal Gallery (A) Room, Ramada Pearl Hotel
Guangzhou (1st Floor)
Best Paper Awards
Best Poster Awards
Banquet
List of Oral Session I (July 13th PM)
Index Authors Title
1 Yupeng Cao, Qiufeng Wang, Kaizhu
Huang and Rui Zhang
Improving Image Caption Performance with Linguistic
Context
2 Danning Lin, Zhijing Yang, Meilin Wang,
Yongqiang Cheng and Qing Pan
Collaborative-Representation-Based Nearest Neighbor
Classifier for Hyperspectral Image Classification
Combined with Superpixel and Loopy Belief
Propagation
3 Guoqiang Zhong, Xin Lin, Kang Chen,
Qingyang Li and Kaizhu Huang Long Short-Term Attention
4
Muhammad Ilyas, Jawad Ahmad, Alistair
Lawson, Jan Sher Khan, Ahsen Tahir,
Hadi Larijani, Abdelfateh Kerrouche, M.
Guftar Shaikh, William Buchanan and
Amir Hussain
Pre-treatment Height Prediction in Growth Hormone
Deficiency Domain using Deep Learning
5 Canyao Li, Jujian Lv, Huimin Zhao and
Kaihan Lin
Dimensionality Reduction with Extreme Learning
Machine Based on Manifold Preserving
6 Tahani Albalawi, Kambiz Ghazinour and
Austin Melton
Quantifying the Effect of Cognitive Bias on Security
Decision-Making for Authentication Methods
List of Posters I (July 13th PM)
Index Authors Title
1 Sibao Chen, Ruirui Wang and Bin Luo Low-Rank Laplacian Similarity Learning
2 Yuehan Yao, Chunmei Qing and
Xiangmin Xu
EEG-Based Emotion Estimate Using Shallow Fully
Convolutional Neural Network with Boost Training
Strategy
3 Shan Jin, Chunmei Qing and Xiangmin
Xu
Emotion Recognition Using Eye Gaze Based on Shallow
CNN with Identity Mapping
4 Rami Ahmed, Kia Dashtipour, Ali Raza,
Amir Hussain and Kaizhu Huang
Offline Arabic Handwriting Recognition using Deep
Machine Learning: A Review of Recent Advances
5
Kia Dashtipour, Ali Raza, Alexander
Gelbukh, Erik Cambria, Amir Hussain
and Kaizhu Huang
PerSent 2.0: Persian Sentiment Lexicon Enriched with
Domain-Specific Words
6
Kaihan Lin, Huimin Zhao, Jujian Lv, Jin
Zhan, Xiaoyong Liu, Rongjun Chen,
Canyao Li and Zhihui Huang
Face Detection and Segmentation with Generalized
Intersection over Union Based on Mask R-CNN
7 Jujian Lv, Huimin Zhao,Rong jun Chen,
Jin Zhan
Semi-supervised Batch Mode Active Learning for
Multi-class Classification
8 Rongfu Zhou, Lan Liu, Jun Lin, Min Ye
and Shunhe Wei
SDN Topology Security Analysis Based on Zero-sum
Game
9 Jing Zhao, Cailing Wang and Nina Chang
The Research and Application of Mathematical
Morphology in Seismic Events Edge Detection and
Machine Vision
List of Oral Session II (July 14th AM)
Index Authors Title
1 Yan Xu, Yuexuan Li and Andrew Abel Gabor Based Lipreading with a New Audiovisual
Mandarin Corpus
2 Guanyu Yang, Kaizhu Huang, Rui Zhang,
John Goulermas and Amir Hussain
Self-Focus Deep Embedding Model for Coarse-Grained
Zero-Shot Classification
3 Jinlong Hong, Kaizhu Huang, Hai-Ning
Liang, Rui Zhang and Xinheng Wang
Fine-Grained Image Classification with Object-Part
Model
4 Yuanye Fang, Rui Zhang, Qiufeng Wang
and Kaizhu Huang
Action Recognition in Videos with Temporal Segments
Fusion
5 Jun Rong, Genyun Sun, Aizhu Zhang and
Hui Huang
Impervious Surface Extraction from Hyperspectral
Images via Superpixels based Sparse Representation with
Morphological Attributes Profiles
6
Yijun Yan, Sophia Zhao, Yuxi Fang,
Yuren Liu, Zhongxin Chen and Jinchang
Ren
VIP-STB Farm: Scale-up Village to County/Province
Level to support Science and Technology at Backyard
(STB) Program
7 Zhejian Zhang, Rui Zhang, Qiufeng
Wang and Kaizhu Huang
Improving Disentanglement-Based Image-to-Image
Translation with Feature Joint Block Fusion
List of Posters II (July 14th AM)
Index Authors Title
1 Xiaochang Li, Zhengjun Zhai, Xin Ye,
Feiyao Dong
Partition Compression Flash Translation Layer Based on
Data Separation
2 Binbin Yong, Zebang Shen, Yongqiang
Wei Jun Shen, Qinguo Zhou
Short-Term Electricity Demand Forecasting Based on
Multiple LSTMs
3 Manjin Sheng, Jiayu Shi, Dengdi Sun,
Zhuanlian Ding and Bin Luo
Adaptive Video Summarization via Robust
Representation and Structured Sparsity
4 Zhanbo Yang, Lingyan Ran, Yong Xia
and Yanning Zhang
MSA-Net: Multiscale Spatial Attention Network for the
Classification of Breast Histology Images
5
Cai Jun, Xuebin Hong, Qingyun Dai,
Huimin Zhao, Yan Liu, Jianzhen Luo and
Zhijie Wu
A User Profile based Medical Recommendation System
6 Qin Xu and Zehui Sun Hyperspectral Image Classification Via Hierarchical
Features Adaptive Fusion Network
7 Xinyu Yan, Zheng Wang and Meijun Sun Eye Fixation Assisted Detection of Video Salient Objects
8 Jianwen Zhou, Zhao, Guo, Xu and Yang Real Time Detection of Surface Defects with
Inception-based MobileNet-SSD
List of Oral Session III (July 14th PM)
Index Authors Title
1 Aizhu Zhang, Genyun Sun, Xiuping Jia,
Chenglong Zhang and Yanjuan Yao
Multi-level thresholding using adaptive gravitational
search algorithm and fuzzy entropy
2 Hongyu Liu, Qingyun Dai, Ya Li, Chuxin
Zhuang, Siyu Yi and Tao Yuan
The Design Patent Images Classification Based on Image
Caption Model
3 Xixian Zhang, Zhijing Yang, Jinchang
Ren, Meilin Wang and Wing-Kuen Ling
Graph Embedded Multiple Kernel Extreme Learning
Machine for Music Emotion Classification
4 Yanjun Liu, Zhijing Yang, Jiangzhong
Cao, Wing-Kuen Ling and Qing Liu
Detection of Invisible Damage of Kiwi Fruit Based on
Hyperspectral Technique
5 Dengdi Sun, Hang Wu, Zhuanlian Ding,
Sheng Li and Bin Luo
Salient Object Detection Based on Deep Multi-Level
Cascade Network
6 Xue Zhang, Zheng Wang and Meijun Sun Semantical Knowledge Guided Salient Object Detection
with Multiple Proposals
List of Posters III (July 14th PM)
Index Authors Title
1
Fangyuan Lei, Xun Liu, Qingyun Dai,
Huimin Zhao, Lin Wang and Rongfu
Zhou
A Multi-view Images Classication Based On Shallow
Convolutional Neural Network
2 Vank Xu, Jian Cen, Hushan Li, J Zhao
and Lianyue Hu
A character superposition method based on object
detection
3 Ying Yang, Bo Jiang, Yun Xiao and Jin
Tang
Salient Object Detection via Graph-Based Extended
Manifold Ranking
4 Zhanlan Chen and Jiangbin Zheng Deep Neural Network for Pancreas Segmentation from
CT images
5
Zhihui Huang, Jin Zhan, Huimin Zhao,
Kaihan Lin, Penggen Zheng and Jvjian
Lv
Real-Time Visual Tracking base on SiamRPN with
Generalized Intersection over Union
6 Jie Ren, Nannan Chang and Weichuan
Zhang
A Contour-based Multi-Scale Corner Detection using
Gabor Filters
7 Qin Xu and Fenglei Li Multi-Layer Weight-Aware Bilinear Pooling for
Fine-Grained Image Classication
8 Ai Zhang Effect on probabilistic language model for cross-domain
corpus
Abstract of keynote Speakers
Biologically-inspired Pattern Recognition: the State of the Art
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.
Tieniu Tan received his BSc degree in electronic engineering from Xi'an
Jiaotong University, China, in 1984, and his MSc and PhD degrees in electronic
engineering from Imperial College London, U.K., in 1986 and 1989, respectively. In
October 1989, he joined the Computational Vision Group at the Department of
Computer Science, The University of Reading, Reading, U.K., where he worked as a
Research Fellow, Senior Research Fellow and Lecturer. In January 1998, he returned
to China to join the National Laboratory of Pattern Recognition (NLPR), Institute of
Automation of the Chinese Academy of Sciences (CAS), Beijing, China, where he is
currently a Professor and the director of Center for Research on Intelligent Perception
and Computing (CRIPAC), and was former director (1998-2013) of the NLPR and
Director General of the Institute (2000-2007). He is currently also Deputy Director of
Liaison Office of the Central People’s Government in the Hong Kong S.A.R. He has
published 14 edited books or monographs and more than 600 research papers in
refereed international journals and conferences in the areas of image processing,
computer vision and pattern recognition. His current research interests include
biometrics, image and video understanding, and information content security.
Professor Tieniu Tan,
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.
Data Processing and AI for Future Medical Research and
Healthcare Delivery
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.
David Feng is Director, Biomedical and Multimedia Information Technology
(BMIT) Research Group, Funding Head, School of Information Technology (recently
renamed as School of Computer Science) and Funding Director, Institute of
Biomedical Engineering & Technology (before the recent formation of the School of
Biomedical Engineering) at the University of Sydney. He received his ME in
Electrical Engineering & Computer Science (EECS) from Shanghai Jiao Tong
University in 1982, MSc in Biocybernetics and PhD in Computer Science from the
University of California, Los Angeles (UCLA) in 1985 and 1988 respectively, where
he received the Crump Prize for Excellence in Medical Engineering. In conjunction
with his team members and students, he has been responsible for more than 50 key
research projects, published over 900 scholarly research papers, pioneered several
new research directions, and made a number of landmark contributions in his field.
He has served as Chair of the International Federation of Automatic Control (IFAC)
Technical Committee on Biological and Medical Systems, Special Area Editor /
Associate Editor / Editorial Board Member for a dozen of core journals in his area,
and Scientific Advisor for a number of prestigious organizations. He has been invited
to give over 100 keynote presentations in 23 countries and regions, and has organized
/ chaired over 100 major international conferences / symposia / workshops. Professor
Feng is Fellow of ACS, HKIE, IET, IEEE, and Australian Academy of Technological
Sciences and Engineering.
Professor David Feng,
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.
Enhanced water consumption behaviour through intelligent IoT
technologies
The talk introduced an interdisciplinary effort of specialists from water
management and ICT research respectively to develop an intelligent IoT supported
Efficient WATer USage and resources management (EWATUS), funded by European
Commission H2020. The work developed several innovative IoT methods aiming to
exploit the untapped water-saving potential in EU. This main goal is achieved by
developing an innovative, multi-factor system capable to optimize water management
and reduce water usage. At household level- to increase the awareness of water
consumption an information system for gathering data about water usage is developed.
The interpreted data is presented to household consumers in an understandable way
using mobile devices (smartphones, tablets); To reduce water consumption a
household decision support system (DSS) for mobile devices is developed.
Recommendations regarding water-saving devices and behaviour is produced; To
reinforce water-saving behaviour of consumers by means of social interactions among
people a social-media platform is developed and widely deployed in the EU.
Shuang-Hua Yang is a chair professor in Computer Science at Southern
University of Science and Technology (SUSTech) in China. He spent over 20 years in
the UK Higher Education Institutions before moving back to China. He joined
Loughborough University in 1997 as a research assistant, and progressing to a
research fellow in 1999, a lecturer in 2000, a senior lecturer in 2003, a professor in
2006, and Head of Department of Computer Science in 2014. His educational history
originated in China where he received a BSc in 1983, an MSc in 1986, both from the
Petroleum University and a PhD in 1991 from Zhejiang University. He was awarded a
Doctor of Science (DSc) degree, a higher doctorate degree, in 2014 from
Loughborough University to recognize his scientific achievement in his academic
career. He is a fellow of the Institute of Engineering and Technology (IET) since 2014,
a fellow of the Institute of Measurement and Control since 2005, and a senior member
of IEEE since 2003. He was awarded the 2010 Honeywell Prize by the Institute of
Measurement and Control in the UK in recognition of his contribution to home
automation research. He was the author of four research monographs and over 200
academic journal papers.
Professor Shuanghua Yang,
PhD, Chair Professor, Department of
Computer Science and Engineering,
Southern University of Science and
Technology.
Person Identification across Multiple Moving-Camera Videos
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.
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.
His research interests include computer vision, image processing, and machine
learning. He has published more than 110 papers in relevant journals and conferences,
including IEEE-TPAMI, IJCV, IEEE-TIP, ICCV, CVPR, NIPS, AAAI and IJCAI, with
more than 3000 Google Scholar citations. He is serving as an associate editor of IEEE
Transactions on Pattern Analysis and Machine Intelligence (IEEE-TPAMI), Pattern
Recognition Letters, and Electronics Letters. He is also serving as the Publicity/Web
Portal Chair of the Technical Committee of Pattern Analysis and Machine Intelligence
of the IEEE Computer Society.
Professor Song Wang,
Professor in the Department of Computer
Science and Engineering at University of
South Carolina.
MAT: Information Theoretical Adversarial Example Theory and
Applications
Recently proposed adversarial training methods show the robustness to both
adversarial and original examples and achieve state-of-the-art results in supervised
and semi-supervised learning. Most existing adversarial training methods consider
only how the worst perturbed examples (i.e., adversarial examples) could affect the
model output. Despite their success, such setting may be in lack of generalization,
since the output space (or label space) is apparently less informative. In this talk, we
discuss a novel method, called Manifold Adversarial Training (MAT). MAT manages
to build an adversarial framework based on how the worst perturbation could affect
the distributional manifold rather than the output space. Particularly, a latent data
space with the Gaussian Mixture Model (GMM) will be first derived. On one hand,
MAT tries to perturb the input samples in the way that would rough the distributional
manifold the worst. On the other hand, the deep learning model is trained trying to
promote in the latent space the manifold smoothness, measured by the variation of
Gaussian mixtures (given the local perturbation around the data point). Importantly,
since the latent space is more informative than the output space, the proposed MAT
can learn better a robust and compact data representation, leading to further
performance improvement. The proposed MAT is important in that it can be
considered as a superset of one recently-proposed discriminative feature learning
approach called center loss. We conducted a series of experiments in both supervised
and semi-supervised learning on three benchmark data sets, showing that the proposed
MAT can achieve remarkable performance, much better than those of the
state-of-the-art adversarial approaches.
Kaizhu Huang has been working in machine learning, neural information
processing, and pattern recognition. He was the recipient of 2011 Asia Pacific Neural
Network Society (APNNS) Younger Researcher Award. He also received Best Book
Award in National Book Competition 2009. Until June 2019, he has published 8
books in Springer and over 160 international research papers including about 60
SCI-indexed international journals, e.g., in journals (JMLR, Neural Computation,
IEEE T-PAMI, IEEE T-NNLS, IEEE T-IP, IEEE T-BME, IEEE T-Cybernetics) and
conferences (NIPS, IJCAI, SIGIR, UAI, CIKM, ICDM, ICML, ECML, CVPR). He
serves as associated editors in three international journals (including two JCR-1
journals) and board member in three international book series. His homepage can be
seen at http://www.premilab.com/KaizhuHUANG.ashx.
Professor Kaizhu Huang,
Department of Electrical and Electronic
Engineering, Xi’an Jiaotong Liverpool
University, Founding Director of Suzhou
Municipal Key Laboratory of Cognitive
Computation and Applied Technology.
Guest List
Professor Shaoming Luo
Ph.D., President of Guangdong Polytechnic
Normal University.
Professor Qingyun Dai
Ph.D., Vice President of Guangdong
Polytechnic Normal University.
Professor Wei Huang
Ph.D., President of the Vocational Education
Institute at Guangdong Polytechnic Normal
University.
Professor Amir Hussain
Ph.D., Professor and Founding Head of the
Cyber and Cognitive Big Data Lab at
Edinburgh Napier University, U.K.
Professor Jinchang Ren
Ph.D., Deputy Director of Strathclyde
Hyperspectral Imaging Centre for Signal and
Image Processing, Visiting professor of
Guangdong Polytechnic Normal University.
Guest List
Professor Wenguo Wei
Ph.D., Director of Scientific Research
Department at Guangdong Polytechnic
Normal University.
Professor Jiangbin Zheng
Ph.D., Dean of the School of Software at
Northwestern Polytechnical University.
Professor Jiangqun Ni
Ph.D., Professor of Sun Yat-Sen University,
Executive Director and Secretary-General of
the Guangdong Society of Image and
Graphics.
Professor Huimin Zhao
Ph.D., Dean of the School of Computer
Science at Guangdong Polytechnic Normal
University.
Professor Jun Cai
Ph.D., Deputy Dean of the School of
Electronics and Information at Guangdong
Polytechnic Normal University.
Professor Wenxin Deng
Ph.D., Director of Development and
Planning Department at Guangdong
Polytechnic Normal University.
Transportations
Ramada Pearl Hotel Guangzhou: #9 Mingyue 1st Road, Middle
Guangzhou Avenue Yuexiu District, Guangzhou, CHINA
Guangdong Polytechnic Normal University: Address: #293 West
Zhongshan Avenue, Tianhe District, Guangzhou