Workshops
Workshop 1: Efficient Evolutionary Deep Learning
Summary:
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
  • AutoML
  • 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
  • EvolNAS
  • NASNet
  • Neuroevolution
  • 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
  • Classification/Clustering/Regression
  • 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
Chairs:
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
Summary:
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

Keywords:
Deep Learning, Reinforcement Learning, Mulit-agent, Game Theory
Chairs:
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
Summary:
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.

Keywords:
Condition monitoring, fault diagnosis,failure prediction, residual working life degradation trend prediction, predictive maintenance, specialty system, neural network, information mixing
Chair:
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
Summary:
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

Keywords:
Data Mining,Machine learning, Fault diagnosis and Prognosis, Fault-tolerant control, Safety and Reliability,Big data analysis, System safety ,Intelligent equipment, Transfer learning ,Deeplearning
Chairs:
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
Summary:
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.

Keywords:
Environment Perception, Semantic Segmentation, Terrain Reconstruction, Object Detection, Intelligent Driving
Chairs:
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
Summary:
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.

Keywords:
Intelligent Manufacturing, Big data, Intelligent Mining, Machine Learning, Cloud Computing
Chairs:
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
Summary:
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.

Keywords:
Intelligent ManufacturingImage enhancement; Image restoration; Machine learning and deep learning
Chairs:
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
Summary:
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.

Keywords:
Deep learning, Visual understanding, visual detection, recognition
Chairs:
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
Summary:
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
Mission Planning
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
Learning-based Control
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

Keywords:
Unmanned Swarm Systems, Coordination, Swarming, Intelligent Unmanned Systems, Autonomous Control
Chairs:
Assoc. Prof. Zhihong 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.
Workshop 10: Deep Learning for Intelligent Scene Perception
Summary:
Visual understanding and multi-modality representation fusion are essential to intelligent scene perception. With the rapid progress in machine learning technologies, there are tons of remarkable advances in intelligent scene understanding, whose performance and application fields are extended greatly. However, the complexity of scene could be a challenge for efficient perception. For some application as automatic drive, pedestrian re-identification and robot tracking, the performance and efficiency are typically affected by disturbances in the natural scene. How to efficiently combine information from visual and other modalities to enhance the robustness of perception systems under accidental perturbation and complexity issues is crucial and meaningful.
This workshop aims 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 intelligent scene perception. We encourage prospective authors to submit related distinguished research papers on the subject of both: theoretical approaches and practical case reviews.

Keywords:
Computer Vision, Multi-modality Representation Learning, Intelligent Scene Perception and Application, Person re-identification, Deep Learning.
Chairs:
Prof. Zhigang Liu, Northeast Petroleum University

Zhigang Liu, received a Ph.D. degree in Computer Resources and Information Engineering from Northeast Petroleum University, and was a visiting scholar with the Department of Electrical & Computer Engineering at National University of Singapore from 2018 to 2019. As a senior CCFmember, he is currently the Department Director of Computer Science and Engineering, Northeast Petroleum University. His research interests include machine learning, computer vision, especially, data/label- and computation-efficient deep learning for visual recognition.
He participated in the National Natural Science Foundation, Natural Science Foundation of Heilongjiang Province, Scientific and Technological Projects of Petro-China, and Youth Science Foundation of Northeast Petroleum University. Based on these projects, he published many academic papers.
Workshop 11: Deep Learning in Multi-Object Tracking
Summary:
Multi-object tracking is a fundamental and important step in the computer vision. It has a wide range of applications in the fields of

intelligent monitoring, automatic driving and so on. Deep learning advances the state-of-the-art in this field. However, there are still many challenges, such as how to apply deep learning to guide association, how to achieve effective online multi-object tracking, how to improve detection and tracking simultaneously, etc.

This workshop aims to show the latest research results in the field of multi-object tracking. We encourage potential authors to submit related distinguished research papers on the subject of both: theoretical approaches and practical case reviews.

Keywords:
Multi-Object Tracking , Deep Learning, Data Association
Chairs:
Shu Tian, University of Science and Technology Beijing

Shu Tian received a Ph.D. degree in Computer Science from the University of Science and Technology Beijing, China, in 2016. Currently, he is a lecturer in the Department of Computer Science and Technology, University of Science and Technology Beijing, China. He has published many research papers (IEEE TPAMI, IEEE TIP, Neurocomputing, IJCAI, ICDAR, IJCNN, etc.). His research interests include object tracking, pattern recognition, and document analysis and recognition.
Prof. Zhu Xiaobin, University of Science and Technology Beijing

Zhu Xiaobin, received his Ph.D. degree from Institute of Automation, Chinese Academyof Sciences, Beijing, China, in 2013.He is currently aProfessor at the School of Computer & Communication Engineering, University of Science and Technology Beijing. His research interests include machine learning,pattern recognition, video and image analysis, etc. He has published over 20 papers in top journals and refereed conference proceedings, including the IEEE T-NNLS, IEEE TITS, Pattern Recognition, AAAI, ICCV, CVPR, etc.
Workshop 12: User Role Discovery in Location Based on Social Network
Summary:
According to the 51th Statistical Report on the Development of China’s Internet, as of December 2022, the number of Chinese netizen reached 1.067 billion, of which more than 99 percent are mobile netizen. 
With the explosive use of mobile phones with built-in GPS positioning function, users can share their location in anytime and anywhere when they attending various social activities, which prompt the foundation of Location-based Social Network (LBSN). 
LBSN is a complex network with rich physical and social information. It includes various colorful functions and is capable to provide intelligent service to end users, which attract many users to engage in various activities. 
A large amounts of user data are accumulated by the activities that users conducted in LBSN. These data include a wealth of user knowledge.
Although users’activities may be varied, these activities may take on regularities in the long run. These regularities, which are shared by a group of users can be abstracted as user roles. User roles are closely related to users’ social background, occupation, and living habits, which is an important means to reveal user characteristics. 
The concept of role used in sociology is an abstraction of "patterned human behavior". In traditional sociological studies, user role are either determinedby profession, such as lawyeror actor, or assigned legally, such as commissioneror minister. The concept of role is not only limited to realistic society, but also meaningful in online social networks. However, the identification of user roles in online scenario is challenging for several reasons. Firstly, user is transparent to the managers of social network and cannot communicate directly, the information that can be obtained directly is the virtual accounts of the user without social attributes. Secondly, user's behavior in social networks is varied. Thirdly, Users are reluctant to provide their true identities because of privacy and security concerns. 
Fortunately, the use of social networks by users generates massive amount of user data, which contains a wealth of user information. The identification and analysis of user role is helpful to understand the social attributes and living habits of users, and provide them with more intelligent services.

Keywords:
User role discovery; location based social network
Chairs:
Prof. Yuanbang Li, Zhoukou Normal University

Prof. Yuanbang Li get the Master's degree in School of Information Engineering from Zhengzhou University, and get the Ph.D. degree in School of Computer Science from Wuhan University. He is an Associate Professor working in Zhoukou Normal University. His research interests include ubiquitous computing, requirements engineering, location-based social network and smart city. Dozens of the research papers he published have been indexed by SCI and EI journals.

Assoc. Prof. Chi Xu, Zhoukou Normal University

Chi Xu get the Master's degree and the Ph.D. degree in Sun Yat-sen University. He is an Associate Professor working in Zhoukou Normal University. His research interests include data mining, machine learning.
Workshop 13: Intelligent Manufacturing and Testing—The Application of Artificial Intelligence in Manufacturing Industry
Summary:
Artificial intelligence issues in the field of intelligent manufacturing, including the intelligence of manufacturing processes, involve machine learning, cloud computing, data mining, multi-sensor information fusion, and big data analysis. Manufacturing process detection, including instruments and sensors, and the intelligence of instruments and the industrial internet of things, et al.

Keywords:
Intelligent instruments, sensors, Industrial big data analysis, Image and Imaging,Non-destructive testing,Industrial internet of things
Chairs:
Assoc. Prof. Guoqiang Han, Fuzhou University

Assoc. Prof. Guoqiang Han is an associate Professor from Fuzhou University. He is Senior Talent Class C in Fujian Province, Ph.D. in Instrumentation and Technology from the School of Mechanical Engineering, Xi'an Jiaotong University, under the guidance of Academician Jiang Zhuangde. He was a post octoral fellow at the Haixi Research Institute of the Chinese Academy of Sciences and avisiting scholar at the Optoelectronics Center of Boston University in the United States. His Research field: Computational imaging and imaging, machine learning, instruments and sensors (miniaturization or intelligence of instruments and measurement and control systems), artificial intelligence and robots, industrial internet of things, signals and systems, etc.