Workshop 1: Efficient Evolutionary Deep Learning
Evolutionary computation technique has been widely used for addressing various challenging problems due to its powerful global search ability. Meanwhile, there are many complex optimisation tasks in the fields of deep learning such as neural architecture search, weight optimisation, hyper-parameter search, feature selection, feature construction, etc. Combining evolutionary computation and deep learning, especially employing evolutionary computation technique for optimization problems in deep learning, is becoming a popular topic in both evolutionary computation community and deep learning community. However, the most prominent problem is that it is very time consuming to evolve a population of deep neural networks which involve the training processes. Efficient techniques, such as surrogate models for ranking, are need to be developed to solve the problem. This workshop aims to collect original papers that develop efficient methods for evolutionary deep learning. For all the aforementioned, we kindly invite the scientific community to contribute to this workshop by submitting novel and original research related but not limited to the following topics:
- Neural Architecture Search (NAS)
- Surrogate Model
- Surrogate assistant Relativistic Performance Rank
- Surrogate-Assisted Evolutionary Neural Architecture Search
- Surrogate model for optimisation
- Neural Predictor
- Evaluation strategy
- Performance evaluator for NAS
- Evaluation Ranking
- Surrogate Model for Classification
- Surrogate Model for Rank
- Evolutionary Deep Learning/Evolving Deep Learning
- Evolutionary Deep Neural Networks
- Evolutionary Computation for Deep Neural Networks
- Evolutionary Neural Architecture Search (ENAS)
- Evolving Deep Neural Networks
- Evolving Convolution Neural Networks
- Evolving Generative Adversarial Networks
- Evolutionary Recurrent Neural Network
- Evolutionary Differentiable Neural Architecture Search
- Evolutionary approach to deep learning
- Searching for Activation Functions
- Deep Neuroevolution
- Deep Neural Evolution
- Neural Networks with Evolving Structure
- Multi-objective Neural Architecture Search
- Evolutionary Optimisation of Deep Learning
- Evolutionary Computation for Neural Architecture Search
- Hybridization of Evolutionary Computation and Neural Networks
- Hyper-parameter Tuning with Evolutionary Computation
- Hyper-parameter Optimisation
- Evolutionary Computation for Hyper-parameter Optimisation
- Evolutionary Computation for Automatic Machine Learning
- Evolutionary Transfer Learning
- Differentiable NAS
- Differentiable Architecture Search
- Partially-Connected Neural Architecture Search
- Attention-Based Neural Architecture Search
- Large-scale Optimisation for Evolutionary Deep Learning
- Evolutionary Multi-task Optimisation in Deep Learning
- Self-adaptive Evolutionary NAS
- Evolutionary artificial neural networks
- Evolving artificial neural networks
- Evolving neural networks
- Meta learning for Training artificial neural networks
- Metaheuristic for Training Neural Networks
- Evolutionary structuring of artificial neural networks
- Structure optimisation for feed-forward neural networks
- Learning and evolution in neural networks
- Pareto evolutionary neural networks
- Pareto neuro-evolution
- Automated design of artificial neural networks
- Adjusting weights in artificial neural networks
- Hyper-parameter Tuning with Self-adaptive Evolutionary Algorithm
- Evolutionary Computation in Deep Learning for Regression/Clustering/Classification
- Full-space Neural Architecture Search
- Evolving Neural Networks
- Automatic Design of Neural Architectures
- Evolutionary Neural Networks
- Gradient-Based and Evolutionary Learning System
- Feature Selection, Extraction, and Dimensionality Reduction on High-dimensional and Large-scale Data
- Evolutionary Feature Selection and Construction
- Multi-objective Feature Selection/Multi-object classification/ Multi-object clustering
- Multi-task optimisation, Multi-task learning, Meta learning
- Learning Based Optimisation
- Hybridization of Evolutionary Computation and Cost-sensitive Classification/Clustering
- Bi-level Optimisation (BLO)
- Hybridization of Evolutionary Computation and Class-imbalance Classification/Clustering
- Numerical Optimisation/Combination optimisation/ Multi-objective optimisation
- Genetic Algorithm/Genetic Programming/Particle Swarm Optimisation/Ant Colony Optimisation/Artificial Bee Colony/Differential Evolution/Fireworks Algorithm/Brain Storm Optimisation
- Machine Learning/Data Mining/Neural Network/Deep Learning/Support Vector Machine/Decision Tree/Deep Neural Network/Convolutional Neural Network/Reinforcement Learning/Ensemble Learning/K-means
- Real-world Applications of Evolutionary Computation and Machine Learning, e.g. Images and Video Sequences/Analysis, Face Recognition, Gene Analysis, Biomarker Detection, Medical Data Analysis, Text mining, Intrusion Detection Systems, Vehicle Routing, Computer Vision, Natural Language Processing, Speech Recognition, etc
Prof. Yu Xue, Nanjing University of Information Science & Technology, China
Yu Xue received the Ph. D. degree from School of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, China, in 2013. He is a professor at School of Software, Nanjing University of Information Science and Technology. He was a visiting scholar in the School of Engineering and Computer Science, Victoria University of Wellington, New Zealand (2016.8-2017.8). He was a research scholar in the Department of Computer Science and Engineering, Michigan State University, the United States of America (2017.10-2018.11). His research interests include Deep Learning, Evolutionary Computation, Machine Learning, and Computer vision.
Prof. Bing Xue, Victoria University of Wellington, New Zealand
Bing Xue is currently a Professor in Artificial Intelligence, and Program Director of Science in School of Engineering and Computer Science at VUW. She has over 300 papers published in fully refereed international journals and conferences and her research focuses mainly on evolutionary computation, machine learning, classification, symbolic regression, feature selection, evolving deep neural networks, image analysis, transfer learning, multi-objective machine learning.
Prof. Xue is currently the Chair of IEEE Computational Intelligence Society (CIS) Task Force on Transfer Learning & Transfer Optimisation, Vice-Chair of IEEE CIS Evolutionary Computation Technical Committee, Editor of IEEE CIS Newsletter. Vice-Chair of IEEE Task Force on Evolutionary Feature Selection and Construction, and Vice-Chair IEEE CIS Task Force on Evolutionary Deep Learning and Applications. She is also served as associate editor of several international journals, such as IEEE Computational Intelligence Magazine and IEEE Transactions on Evolutionary Computation.
Prof. Yong Zhang, China University of Mining and Technology, China
Yong Zhang received the BSc and PhD degrees in control theory and control engineering from the China University of Mining and Technology in 2006 and 2009, respectively. He is a professor with the School of Information and Electronic Engineering, China University of Mining and Technology. His research interests include intelligence optimisation and data mining.
Prof. Adam Slowik, Koszalin University of Technology, Poland
Adam Slowik was born in Warsaw, Poland, in 1977. He received the Ph.D. degree in electronics with distinction from the Department of Electronics and Computer Science, Koszalin University of Technology, Koszalin, Poland, in 2007, and the Dr. Habil. (D.Sc.) degree in computer science from the Department of Mechanical Engineering and Computer Science, Czestochowa University of Technology, Czestochowa, Poland, in 2013. Since October 2013, he has been an Associate Professor with the Department of Electronics and Computer Science, Koszalin University of Technology. His research interests include soft computing, computational intelligence, machine learning, and bioinspired global optimisation algorithms and their applications. He is an Associate Editor for the IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS.
Prof. Ferrante Neri, University of Surrey, UK
Ferrante Neri (M’03–SM’19) received a Laurea degree (BSc + MSc) and a PhD in Electrical Engineering from the Technical University of Bari, Italy, in 2002 and 2007 respectively. In 2007, he also received a PhD in Scientific Computing and Optimisation from University of Jyvaskyla, Finland. From the latter institution, he received the DSc degree in Computational Intelligence in 2010. Dr Neri moved to De Montfort University, United Kingdom in 2012, where he was appointed Reader in Computational Intelligence and in 2013, promoted to Full Professor. In 2019 Ferrante Neri moved to the University of Nottingham, United Kingdom and in 2022 to the School of Computer Science and Electronic Engineering, University of Surrey, United Kingdom, where he is currently Professor of Machine Learning and Artificial Intelligence and Head of the Nature Inspired Computing and Engineering (NICE) research group. His research interests include algorithmics, hybrid heuristic-exact optimisation, memetic computing, differential evolution, and membrane computing. Prof Neri published over 200 items including two editions of the textbook “Linear Algebra for Computational Sciences and Engineering” and is Associate Editor of multiple journals including Information Sciences and Integrated Computing Engineering.
Workshop 2: Reinforcement Learning Methods and Applications
Reinforcement learning methods are useful for developing smart decision-making agents through trial-and-error interaction with the given environments. Reinforcement learning algorithms have achieved impressive performance after being combined with deep neural networks to handle high-dimensional or continuous state spaces, e.g., playing the games of Go, Atari, StarCraft and Dota. In addition, they are also effective for solving complex non-linear control problems that are typicallyhard to model in dynamic environments. Specifically, deep reinforcement learning can be used to learn versatile skills for robots and unmanned systems, such as walking for legged robots, landing for a quadrotor UAV, and swarming for fixed-wing UAVs.
The aim of this workshop is to bring together researchers who are interested in reinforcement learning methods as well as their applications. We encourage not only the sharing of novel RL theories, models, and algorithms, but also the ideas of how RL can be used to solve real-world tasks. The scope of this workshop includes but is not limited to the following topics:
- Reinforcement learning theories and algorithms
- Deep reinforcement learning
- Multi-agent reinforcement learning
- Distributed reinforcement learning
- Reinforcement learning for robot control
- Reinforcement learning for swarms
- Reinforcement learning for games
- Imitation learning
- Transfer learning
- Active learning
- Curriculum learning
- Interactive reinforcement learning
- Hierarchical reinforcement learning
- Evolutionary reinforcement learning
- Explainable reinforcement learning
- Reinforcement learning applications
Deep Learning, Reinforcement Learning, Mulit-agent, Game Theory
Assoc. Prof. Chang Wang, National University of Defense Technology, China
Dr. Chang Wang is currently an associate professor at the College of Intelligence Science and Technology, National University of Defense Technology (NUDT), China. He obtained the PhD degree on robot learning from Delft University of Technology (The Netherlands), the master degree on applied mathematics from NUDT, and the bachelor degree on mathematics from University of Science and Technology of China (USTC). His research interests include reinforcement learning, developmental robotics, multi-agent systems, UAV swarms, human-robot teamwork, augmented reality, etc. He has published more than 50 peer-reviewed papers and serves as a reviewer for several prominent journals and conferences.
Associate Research Fellow. Shengde Jia, National University of Defense Technology, China
Shengde Jia received his bachelor degree in control theory and engineering from Harbin Institute of Technology in 2008, his master and PhD degrees also in control theory and engineering from National University of Defense Technology in 2010 and 2015, respectively. He is an associate research fellow with the College of Intelligence Science and Technology, National University of Defense Technology. His research interests include reinforcement learning control theory in unmanned aerial vehicle, decision and optimal theory.
Workshop 3: Application of Specialty System, Neural Network, Information Mixing or Other Techniques in Health Condition Monitoring and Fault Diagnosis for Mechanical Equipment
According to the International Society of Automation, industrial asset shutdowns cost the world $647bn a year. "Made in China 2025" mentioned, "cultivate intelligent monitoring, remote diagnosis, whole industry chain traceability and other new industrial Internet applications, implement industrial cloud and industrial big data innovation and application pilot..." This points to the latest development direction in the field of intelligent maintenance, namely real-time monitoring and evaluation of equipment and product performance degradation, remote monitoring and diagnosis of equipment status, which could help the plant to establish a new tube, maintenance, inspection and repair system, providestrong guarantee for stable operation and contributes to the goal of maximizing the efficiency, thereby achieving greater benefits. Predictive maintenance based on early failure prediction, health status assessment, automatic failure mode identification and residual working life degradation trend prediction has attracted more and more attention from entrepreneurs and researchers.
The aim of this workshop is to bring together the research accomplishments provided by researchers from academia and the industry. The other goal is to show the latest research results in the field of health condition monitoring and predictive maintenance for mechanical equipment. We encourage prospective authors to submit related distinguished research papers on the subject of both: theoretical approaches and practical case reviews.
Condition monitoring, fault diagnosis,failure prediction, residual working life degradation trend prediction, predictive maintenance, specialty system, neural network, information mixing
Prof. Fan Gao, Chongqing Chuanyi Automation Co.,Ltd.
Fan Gao, professor of engineering, Expert of China equipment engineering expert database, Chief designer of Chongqing Chuanyi Automation Co.,Ltd., ISO 18436-2 International Vibration Analyst, Technical Program Committee Member of MLCCIM 2022, "Steel Rolling" Young Editorial Board, "Metallurgical Industry Automation" Young Editorial Board, Early Career Editor in chief of "Emergency Management Science and Technology", Guest reviewer of "SAFETY HEALTH & ENVIROMENT", IEEE Member. Recent years have published More than 20 EI and core papers on engineering applications. Participated in several scientific research projects of Ministry of Industry and Information Technology, Chongqing Economic and Information Commission, China Silian Instrument group Co. LTD.
Workshop 4: Data Mining Based Fault Diagnosis and Control Methods for Intelligent Equipment
With the development of science and technology as well as the advancement of production technology, contemporaryequipment is increasingly developing towards large-scale, complex, automated and intelligent direction. Fault diagnosis andcontrol technology is an important method and necessary means to improve the system operation reliability and reduce the system operation risk.In order to ensure the safetyand reliability of intelligent equipment, the fault diagnosis and prognosis technology has received widespread attention and beenwidely used. Traditional statistical data-driven methods are obviously influenced by the choice of models. Data mining haspowerful data processing ability, and does not need exact physical models and prior knowledge of experts. Therefore, machinelearning has a broad application prospect in the field of fault diagnosis and prognosis .
The aim of this workshop is to bring together the research accomplishments provided by researchers from academia and the industry. The other goal is to show the latest research results in the field of fault diagnosis and control technology and understand how machine learning strategy can influence it. We encourage prospective authors to submit related distinguished research papers on the subject of both: theoretical approaches and practical case reviews. The scope of this workshop includes, but is not limited to the following topics:
- Intelligent fault detection, diagnosis and prediction withdata mining
- Fault tolerant control and safety control with artificial intelligence
- Reliability assessment, prediction and design with artificial intelligence
- Prognosisand health management with data mining
- Intelligent maintenance technology with data mining
- Residual life prediction technology with artificial intelligence
- Computer vision aided Condition monitoring and fault diagnosis with machine learning
- Deep neural network-based designs for intelligent equipment
- Transfer learning- and reinforcement learning-inspired deep neural networks with application in intelligent equipment
- Domain adaptation model-based deep learning framework aided fault diagnosis and prediction for intelligent equipment
- Application and case analysis
Data Mining,Machine learning, Fault diagnosis and Prognosis, Fault-tolerant control, Safety and Reliability,Big data analysis, System safety ,Intelligent equipment, Transfer learning ,Deeplearning
Prof. Zhao-Hua Liu, Hunan University of Science and Technology
Zhao-Hua Liu (Senior member,IEEE) , received Ph.D. degree in automatic control and engineering from Hunan University, Changsha, China, in 2012. During 2015–2016, he was a Visiting Researcher with the Department of Automatic Control and Systems Engineering, University of Sheffield, Sheffield, U.K. He is currently aProfessor of AutomaticControl and Systems with the School of Information and Electrical Engineering, Hunan University of Science and Technology, Xiangtan, China. He was a selected as a Hu-Xiang Excellent Young Talents of Hunan Province of China in 2018.His current research interests include intelligent information processing and control of wind turbines, computational intelligence and learning algorithms design, machine learning aidedfault diagnosis and prognosis, parameter estimation and control of permanent-magnet synchronous machine drives, and condition monitoring and fault diagnosis for electric power equipment.
Dr. Liuhas published more than 50 research papers in refereed journals . He is a regular reviewer for several international journals and conferences.
Assoc. Prof. Lei Chen, Hunan University of Science and Technology
Lei Chen received the Ph.D. degree in automatic control and electrical engineering from the Hunan University, China, in 2017.
He is currently a Lecturer with the School of Information and Electrical Engineering, Hunan University of Science and Technology, Xiangtan, China. His current research interests include deep learning, network representation learning, information security of industrial control system and big data analysis.
Dr. Ming-Yang Lv, Hunan University of Science and Technology
Ming-Yang Lv, received the Ph.D. degree in automatic control and engineering from the Hunan University, China, in 2020.
He is currently a Lecturer with the School of Information and Electrical Engineering, Hunan University of Science and Technology, Xiangtan, China. His current research interests include deep learning, network representation learning,condition monitoring and fault diagnosis for electric power equipments.
Workshop 5: Intelligent 3D Point Cloud Processing for Intelligent Driving
Real-time 3D point cloud processing for environment perception technology has led to significant advances in the field of intelligent driving, such as object detection, path planning, and environment interaction. The Simultaneous Localization and Mapping (SLAM) and Lidar Odometry and Mapping (LOAM) systems allow for precise and real-time autonomous terrain modeling of dynamic environments. The accurate 3D understanding of the surrounding environment is essential for path planning. Deep neural network research on semantic segmentation, instance segmentation, and panoptic segmentation from LiDAR point clouds has inspired interest in the growing interest in environment perception for intelligent driving.
The aim of this workshop is to discuss recent advances in 3D scene modeling and environmental understanding systems that make use of point cloud data obtained from laser scanners and other 3D imaging devices. We also encourage potential authors to submit related distinguished research articles on 3D point cloud processing for smart manufacturing, smart building, and remote sensing applications in ecology.
Environment Perception, Semantic Segmentation, Terrain Reconstruction, Object Detection, Intelligent Driving
Prof. Wei Song, North China University of Technology
Wei Song is currently a professor at the School of Information Science and Technology, and vice dean of International School, North China University of Technology, China. He is also a Ph.D. Supervisor at Department of Multimedia Engineering, Dongguk University, Korea.
He received B.S. degree in software engineering from Northeast University, China in 2005, M.S. and Ph.D. degrees in multimedia engineering from Dongguk University, Korea in 2008 and 2013, respectively.
His current research interests include Environment Perception, 3D Object Recognition, Semantic Segmentation, 3D Reconstruction, and LiDAR applications. In current years, he published 2 textbooks about 3D Programming, 37 SCI papers, and 2 authorized patents. He finished more than 10 projects as PI, including National Natural Science Foundation of China (61503005), High-Potential Individuals Global Training Programs (2019-0-01585 and 2020-0-01576), etc.
Jinkun Han, Georgia State University
Jinkun Han is a Ph.D. student of Computer Science at Georgia State University. Jinkun's research mainly focuses on various recommendation systems and personalization. Recommendation systems are becoming society's critical infrastructures in retail, online shopping, entertainment, advertising, finance, etc. against the information explosion era. Meanwhile, personalization is the key to fitting various tastes of users. Jinkun works in the recommendation and personalization field and published hiswork on top conference CIKM 2022(31st ACM International Conference on Information and Knowledge Management). Additionally, Jinkun is the reviewer of PAKDD 2023 (Pacific-Asia Conference on Knowledge Discovery and Data Mining) and high-confidence computing.
Workshop 6: MLCCIM on Intelligent Manufacturing
With the rapid development and wide application of new generation information technology, the world focuses on intelligent manufacturing once again. Aman-machine integrated intelligent system composed of intelligent machines and human experts. carrying out intelligent activities in the manufacturing process, such as analysis, reasoning, judgment, conception and decision-making.
The workshop aims toshow the latest research results of Machine Learning, Cloud Computing and Intelligent Mining( MLCCIM ) on Intelligent manufacturing technology and application. We encourage authors to submit related distinguished research papers on the subject of theoretical approaches and practical case reviews such as Intelligent factories, flexible production lines, large-scale collaborative manufacturing, two-way collaboration of procurement and circulation, support the construction of demonstration application scenarios such as artificial intelligence, Internet of vehicles, big data, blockchainetc.
Intelligent Manufacturing, Big data, Intelligent Mining, Machine Learning, Cloud Computing
Prof. Ying Yang, Guangxi University
Ying Yang works as a professor at School of Compute＆Electronics and Informationof Guangxi University. She received a Bachelor's degree from Beihang University in 1991, a master's degree at Guangxi University in 1996, a doctoral degree at Donghua University in 2006 and postdoctoral degree at Fudan University in 2013. Moreover, she went to Vermont University in the United States from January to May 2010 as a visiting scholar. Her research areas include big data, Machine Learning, Cloud Computing and Intelligent Miningon intelligent manufacturingetc. She participated in 16 projects such as supported by National Natural Science Foundation, key special provincial and ministerial scientific research, and won a prize for scientific and technological progress in Guangxi province,anda first prize and for Guangxi computer promotion＆application achievement. Besides, she owns 20 computer patents and software copyright registration certificates. She published more than 30 papers on domestic and abroad journals, some papers indexed by SCI and EI.
Workshop 7: Deep CNNs for image enhancement
In the era of the Internet of Things, images have played important roles in human–computer interactions, and with the arrival of big data technology, people have higher requirements of image qualities, especially ones collected in dark light. This can be addressed through the development of camera hardware quality, i.e., the resolution and exposure time of cameras, which may require high computational costs. As an alternative, image enhancement techniques can exact salient features to improve the quality of captured images according to the differences of diverse features, although they suffer from some challenges, i.e., a low contrast, artifacts and overexposed, thus, making it decidedly necessary to determine how to use advanced image enhancement techniques.
Intelligent ManufacturingImage enhancement; Image restoration; Machine learning and deep learning
Assoc. Prof. Chunwei Tian, Northwestern Polytechnical University
Chunwei Tian is currently an Associate Professor with the School of Software, Northwestern Polytechnical University, China. Also, he is a member of National Engineering Laboratory for Integrated Aerospace Ground-Ocean Big Data Application Technology. He received his Ph.D degree in Computer Application Technique from Harbin Institute of Technology in Jan, 2021. His research interests include image restoration and deep learning. He has published over 50 papers in academic journals and conferences, including IEEE TNNLS, IEEE TMM, IEEE TSMC, Pattern Recognition, Neural Networks, Information Sciences, KBS, PRL, ICASSP, ICPR, ACPR and IJCB. He has four ESI highly-cited papers, three homepage papers of the Neural Networks, one homepage paper of the TMM, one excellent paper in 2018 and 2019 for the CAAI Transactions on Intelligence Technology. Also, his three codes are rated as the contribution codes of the GitHub 2020. His three paper techniques are integrated on the iHub, Profillic and OSCS, respectively. His one paper technique is purchased by an American Medical Imaging Company. His one paper is rated as an excellent paper in Taichang in 2022. He has obtained Excellent Doctoral Dissertation of 2021 Shenzhen CCF and 2022 Harbin Institute of Technology. He has obtained Excellent Doctoral Dissertation of 2022 Heilongjiang. Also, he becomes a Jiangsu High-level talent and Suzhou Youth Science and Technology Talent. Besides, he is an associate editor of the Journal of Electrical and Electronic Engineering, International Journal of Image and Graphics and Journal of Artificial Intelligence and Technology, a youth editor of CAAI Transactions on Intelligence Technology, Defence Technology, Data Science and Management, Ordnance Industry Automation, reviewer editor of Frontiers in Robotics and AI, a guest editor of Mathematics, Electronics, Drones, Mathematical Biosciences and Engineering, International Journal of Distributed Sensor Networks and Applied Sciences, PC Chair and Workshop Chair of MLCCIM 2022, SI Chair of ACAIT 2022, Special Session Co-Chair and Workshop Chair of ICCSI 2022, Publicity Chair of AMDS 2022, a workshop chair of ICCBDAI 2021, a reviewer of some journals and conferences, such as the IEEE TIP, the IEEE TNNLS, IEEE TCYB, the IEEE TII, the IEEE TSMC, the IEEE TCYB, the IEEE TKDE, the IEEE TMM, the IEEE ITSTM, the IEEE TDSC and the IEEE TCDS, etc
Assist. Prof. Qi Zhang, Harbin Institute of Technology
Qi Zhang is an assistant professor with the School of Management at Harbin Institute of Technology, Weihai. She received her Ph.D degree in Business Administration from Harbin Institute of Technology in Nov, 2021. Her research interests include accounting big data, deep learning and image processing. She has published papers more than 20 papers.
Dr. Haokui Zhang, Northwestern Polytechnical University
Dr. Zhang received the M.S. and Ph.D. degrees in computer application technology from the Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, Northwestern Polytechnical University, Xi’an, China, in 2021 and 2016, respectively. He is currently an Algorithm Researcher with Intellifusion, Shenzhen, China. His research interests cover information retrieval, image restoration, and hyperspectral image classification
Assist. Prof. Tao Dai, Shenzhen University
He is currently an Assistant Professor at the Department of Computer Science and Software Engineering of the Shenzhen University. He is working on ITML projects under the guidance of Prof. Shuto Xia. He completed my bachelor's degree with honor in Electronic Engineering (2010-2014) from Xidian University. His main research interests include machine learning, compressed sensing, image processing and computer vision, including image restoration and image quality assessment.
Workshop 8: Deep Learning for Visual Understanding
With the explosive growth of visual data, how to automatically understand the visual semantics becomes an urgent demand. As a machine learning and artificial intelligence technique that can imitate the way humans understand the world, deep learning has achieved significant breakthroughs for almost all of visual fields, e.g., image classification, object detection, segmentation, etc. However, there are still many issues to be discussed, e.g., class imbalance, data deficiency, network lightweight, etc.
The aim of this workshop is to bring together the research accomplishments provided by researchers from academia and the industry. The other goal is to show the latest research results in the field of deep learning for visual understanding, especially visual detection and recognition. We encourage prospective authors to submit related distinguished research papers on the subject of both: theoretical approaches and practical case reviews. Please name the title of the submission email with “paper title_workshop title”. Warmly welcome to your join.
Deep learning, Visual understanding, visual detection, recognition
Prof. Yi Liu, Changzhou University
Prof. Yi Liu received a Ph.D. degree in Control Theory and Control Engineering from Xidian University in 2019. He once studied in Lancaster University and University of Warwick as a visiting scholar. He is currently working at Changzhou University, China. His research interests include saliency detection, few-shot object detection, 3D point cloud analysis, digital twin, etc. He was awarded grants from the National Natural Science Foundation of China and Natural Science Foundation of Jiangsu Province.
Guangqi Jiang, Changzhou University
Guangqi Jiang received her Ph.D. degree from the Information Science and Technology College, Dalian Maritime University, Dalian, Liaoning, China. Now, she is works as a lecturer in Changzhou University. Her research interests include computer vision and machine learning.
Workshop 9: Autonomous Coordination of Unmanned Swarm Systems
Nowadays, unmanned swarm systems have been revealing great potential values in applications such as surveillance, disaster rescue, mapping, cargo delivery, etc. Through coordination among a large number of unmanned systems, unmanned swarm systems can improve mission capability, survivability, and flexibility. Regarding the key technologies, autonomous coordination techniques are the essential building blocks in unmanned swarm systems, which provide the foundation for enabling group behavior, including cooperation in observation, orientation, decision-making, action, and other aspects at the group level. This workshop solicits key theoretical and practical contributions to coordination techniques for unmanned swarm systems. It aims to bring studies from related fields (perception, control, navigation, and networking) together. The scope of this workshop includes but is not limited to the following topics:
Cooperative Target Detection
Multimodal and Distributed Data Fusion
Relative Positioning and Navigation
Obstacle Detection and Avoidance
Flocking for Unmanned Swarm Systems
Reliable and Scalable Networking for Unmanned Swarm Systems
Networked Control under Communications Constraints
Resource Description and Allocation for Complex Systems
Formation Control and Reconfiguration
Interoperability Technology for Cross-Domain Collaboration
Security And Safety in Unmanned Systems
Swarm-Based Counter UAV Defense System
Platform Design for Unmanned Swarm Systems
Unmanned Swarm Systems, Coordination, Swarming, Intelligent Unmanned Systems, Autonomous Control
Assoc. Prof. Zhilong Liu, National University of Defense Technology
Zhihong Liu received a Ph.D. degree in computer science from the National University of Defense Technology (NUDT), in 2016. He was a visiting student with the David R. Cheriton School of Computer Science, University of Waterloo, Waterloo, ON, Canada, from 2013 to 2015. He is currently an Associate Professor with the College of Intelligence Science and Technology, NUDT. He has authored or co-authored more than 50 publications in peer-reviewed journals and international conferences. His research interests include learning-based robotic control, UAV swarming, and reinforcement learning. He is a regular reviewer for several prominent journals and conferences.
Assoc. Prof. Dong Yin, National University of Defense Technology
Dong Yin received the M.S. degree and the Ph.D. degree in network engineering from Northwestern Polytechnical University in 2007 and 2011. He was a visiting student in University of Massachusetts, US, from 2008 to 2010. He has been with the College of Intelligence Science and Technology, National University of Defense Technology, China, since 2011, and is currently an associate professor. His research interests include wireless communication, mobile network and network security of unmanned system. He is a regular reviewer for several prominent journals and conferences.
Assoc. Prof. Huangchao Yu, National University of Defense Technology
Huangchao Yu received his B.S. degree in Mechanical Engineering and Automation from National University of Defense Technology in 2011, and Ph.D. degree in Mechanical Engineering from University of Alberta, Canada in 2017. He is currently working as an associate professor at National University of Defense Technology. He has authored or co-authored more than 40 publications in peer-reviewed journals and international conferences. His research interests include UAV design and flight control, learning-based robotic control and topology optimization.