CFP Workshops

Workshop 1: Intelligent Interaction Technology
Title: Intelligent Interaction Technology and Application

Summary:

Intelligent interaction technology ensures the behavior understanding and coordination of human-computer, machine-to-machine. Through technologies such as cross media perception, machine learning and cognitive computing, we can build intelligent expression and learning methods unified with the real world. Intelligent interaction technology has been widely used in self-driving, medical, games, robotics and other fields in recent years, which focuses on how to make machines understand people's intentions better, realize the interaction between machines, human-computer cooperation, and form an intelligent and trusted system. 

This workshop aims to bring together the latest research progress of academic and industry researchers, such as intelligent interaction technology, human-computer hybrid intelligence, human factors and ergonomics, safe driving behavior, wearable device interaction, multi-intelligent system collaboration, user interface design and so on. We encourage prospective authors to submit related distinguished research papers on the subject of intelligent interaction technology. 

Keywords:
Intelligent Interaction Technology, Human-machine Hybrid Intelligent, Human Factors and Ergonomics, Safe Driving Behavior, Wearable Device Interaction, Multi-agent Collaboration

Chairs:


Chair 1: Prof. Nan Ma, Beijing University of Technology, China


Nan Ma is a professor at Beijing University of Technology, the Deputy Secretary-General of China Artificial Intelligence Society, IEEE/CAAI/CCF Senior Member. Her research interests lie in interactive cognition, visual intelligence, knowledge discovery and intelligent system. She has hosted 5 national and provincial projects, such as National Natural Science Foundation of China and Beijing Natural Science Foundation. She serves as a reviewer and member of procedure committee of CVPR and other international conferences. In recent years. She presided over six projects from enterprises, such as "intelligent vehicle and road network visual simulation interactive system". Her intelligent interaction team won many championships in some intelligent driving competitions, such as the virtual scene competition of 2018, 2019 and 2020 World Intelligent Unmanned Driving Challenge respectively.

Also, her team of achievements ''unmanned cloud intelligent interaction system'' won the top prize in the final of the second China "AI +" innovation and entrepreneurship competition. She achieved the second prize of science and technology award [technological invention] of China Electronics Society in 2020. She has edited 4 books, published more than 60 academic papers including over 40 papers indexed by SCI or EI, obtained more than 10 patents and 20 software copyrights. She has taught the online course "Intelligent Interactive Technology" in Chinese University MOOC for five times, and more than 12000 people have studied the course online.

Chair 2: Prof. Hongzhe Liu, Beijing Union University, China


Hongzhe Liu received the B.E. degree from Chinese Marine University, China, in 1995, the M.A.Sc. degree from California State University, Long Beach, CA, USA, in 2000, and the Ph.D. degree from Beijing Jiaotong University, China. She is the Leader of the Beijing Key Laboratory of Information Service Engineering and a Professor at Beijing Union University. Her research interests include artificial intelligence, visual intelligence, cognitive computing, and visual computing. She is a member of the Chinese Computer Society. She has hosted or participated in many national and provincial projects, such as National Science and Technology Support Program, National Natural Science Foundation of China, And Beijing Natural Science Foundation. She published more than 60 papers in academic journals and international conferences, of which more than 30 have been indexed by SCI on journals. She has edited 4 books and more than 20 patents and software Copyrights. She led the team to participate in visual information environment cognitive basic ability offline test competition of Intelligent Vehicle Future Challenge and won three first prizes. She achieved the second prize of the Chinese Society for Artificial Intelligence in 2020. She won first prize in the WACV 2020 AVVision MTMC Tracking Challenge in 2021.

Co-chair
Assoc. Prof. Jin Wang, Beijing University of Technology, China


Jin Wang is an associate professor at Faculty of Information Technology of Beijing University of Technology. He is also an IEEE/ACM/CCF Member. His research areas include digital image processing, image/video coding, computer vision, and artificial intelligence. He authored more than 30 publications in journals and conferences, such as IEEE TIP, IEEE TMM, IEEE TCSVT, ACM MM, IEEE INFOCOM, IEEE DCC, and IEEE ICME. He holds more than 5 national invention patents. He presided over more than 7 scientific research projects supported by National Natural Science Foundation and Beijing Municipal Natural Science Foundation, etc. He serves as a session chair of ACM MM 2021, a Technical Program Committee (TPC) member for ACM MM 2022, and a Program Committee (PC) member for AAAI 2022.

Workshop 2: AI-powered Disease Screening/Diagnosis
Title: Deep Learning Technologies for Biomedical Image Analysis

Summary:

Deep learning technologies such as CNNs and vision transformers have presented increasing applications in the field of biomedical image analysis and greatly advanced the development in recent years, which is partly due to their powerful ability of representation learning. Nevertheless, there are still many open questions to be solved, such as deep representation learning for tiny lesions in biomedical images, domain generalization for unseen domains, multi-label learning with incomplete labels, etc.

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 biomedical image analysis. We encourage prospective authors to submit related distinguished research papers on the subject of image segmentation, lesion detection, disease screening, and image generation towards biomedical images. 


Keywords:
Biomedical Image Analysis, Image Segmentation, Lesion Detection, Disease Screening, Image Generation

Chair:


Dr. Qing Liu, Central South University, China


Qing Liu is a lecturer at School of Computer Science of Central South University since Sept. 2019. She is the PI of multiple funded projects including Young Scientists Fund of the National Natural Science Foundation of China, Young Scientists Fund of the Hunan Provincial Natural Science Foundation, and Changsha Municipal Natural Science Foundation. All three funded projects are related to the current project about retinal image analysis. She got her Ph.D. degree in 2017, majored in Computer Application Technology. During her Ph.D. study, she was granted a two-year scholarship by China Scholarship Council and visited CMVS. She also got the First-class General Financial Grant from China Postdoctoral Science Foundation. Dr. Qing Liu published 15 papers on influential conferences and journals.


Workshop 3: AI Models for Image Denoising
Title: Deep Learning Based Image Denoising

Summary:

Image denoising is a crucial computer vision task, aiming at the restoration of degraded image content to achieve the desired target. Over the past years, deep learning has received a great deal of attention and has been widely applied in image denoising. Not only has there been a constant increase of related papers, but also significant progress has been achieved. However, there are still challenges in image denoising, including inadequate training samples, unseen noises, multi-degradation, unpaired noisy images, etc.

We introduce this Deep Learning Based Image Denoising Workshop to provide an opportunity for academic and industrial attendees to explore new solutions and advances in image denoising. This workshop highlights the latest innovations and applications of deep learning approaches designed in this area. It also seeks related datasets, evaluation platforms, and tools. 

Keywords:
Deep Learning, Unsupervised Image Denoising, Low-resource Image Denoising, Image De-raining, De-icing, De-fogging

Chair:

Dr. Xiangdong Su, Inner Mongolia University, China


Xiangdong Su is an associate professor at the School of Computer Science in Inner Mongolia University, China. Xiangdong Su received a Ph.D. degree in computer application technology from the School of Computer Science, Inner Mongolia University, Huhhot, China, in 2016. His research interests include machine learning, image denoising, image inpainting, image segmentation, optical character recognition, neural networks, data augmentation, and intelligent systems. He hosts and participates in several national and provincial scientific research projects. He has published 22 papers on influential international conferences and journals.


Workshop 4: coming soon
Title: Big Data Analytics And Deep Learning for Intelligent Transportation and Urban Computing

Summary:

Recent advances in information and communication technologies are facilitating substantial improvements in many aspects of nowadays society. Novel technologies, such as the Internet of Things, 5G, artificial intelligence, deep learning, knowledge graph, enable a huge volume of data in different formats generated by organizations, communities, individuals to be recorded and analyzed effectively. Such big data increasingly drives decision-making and is changing the landscapes of two important fields -- intelligent transportation and urban computing. Big data analytics and deep learning that discovers insights from evidence have a high demand for interpretable data mining, knowledge discovery, problem solving, and event prediction/prescription.

This workshop offers a platform for state-of-the-art research on the latest development and challenges in the fields of big data analytics and deep learning for intelligent transportation and urban computing, providing insight into the theories and technologies that are transforming our lives. Proposed submissions should be original and unpublished. Potential topics include, but are not limited to:
• Explainable/interpretable AI in transportation or urban computing
• Innovative methods for big data analytics (e.g. machine learning, deep learning, knowledge graph, etc.
• Techniques for mining big data in smart cities (e.g., traffic prediction, trajectories analysis, urban flow prediction, etc.)
• Autonomous vehicles
• Intelligent planning, scheduling, decision, and smart dispatching for urban computing and smart city.
• Human factors in an era of connected and automated transportation
• Real-world applications of big data analytics, such as anomaly/default detection, intelligent planning, scheduling, intent recognition, etc.
• Big data driven deep learning and knowledge graph for knowledge discovery and decision in urban computing.

Keywords:
Big Data Analytics, Artificial Intelligence, Deep Learning, Knowledge Graph, Intelligent Transportation, Urban Computing, Data Driven Intelligence, Explainable AI

Chair:

Assoc. Prof. Shengdong Du, Southwest Jiaotong University, China



Shengdong Du is an associate professor, director of smart city research center of Southwest Jiaotong University, IEEE/CCF Member. His research interests include machine learning, data mining, deep learning, knowledge graph and intelligent operation. He presided over 3 sub-project of the National Key R&D Project, 2 key R&D General Projects of Sichuan Province, and participated in 6 National Key R&D Project and National Natural Science Foundation of China General Project as principal investigator. He developed more than 30 information systems and products, obtained more than 20 patents and software copyrights, published 2 books, and published more than 40 papers in international journals such as IEEE Transactions on Knowledge and Data Engineering (TKDE), Neurocomputing, etc.


Workshop 5: Intelligent Technologies in Education
Title: Deep and Wide Applications of Intelligent Technologies in Education

Summary:

The development of intelligent technologies has opened countless possibilities in many industries. The field of education is taking a frontier position in the deep application of intelligent technologies The latest technologies such as virtual reality, augmented reality, learning analytics, big data analysis and processing, intelligent interaction and human-computer interfaces can find their respective pioneering application revenues in education. Significant innovations and breakthroughs are just in the corner for such applications to transform education in both educational and technological sense.

This workshop provides a platform for cutting-edge discussions on the application and challenges of intelligent technologies in the education field, offering the possibility of transforming our theories and technologies in education with both depth and width. Potential topics include, but are not limited to:

· Artificial Intelligence in Education
· Virtual/Augmented/Mixed Reality in Education
· Learning Analytics
· Big Data Analysis and Processing for Learning and Education
· Intelligent Tutoring Systems
· Human-Computer Interface
· Education Data Mining

Keywords:
Artificial Intelligence in Education, Virtual/Augmented/Mixed Reality in Education, Learning Analytics, Big Data Analysis and Processing for Learning and Education, Intelligent Tutoring Systems Human-Computer Interface, Education Data Mining

Chair:

Prof. Longkai Wu, Central China Normal University, China


Longkai Wu is a professor and PhD supervisor at the National Engineering Research Centre for E-Learning & MOE Educational Informatisation Strategy Research Base, Faculty of Artificial Intelligence in Education, Central China Normal University, Wuhan, China. He holds a Doctor of Philosophy degree in Learning Science and Technology from Nanyang Technological University (NTU), Singapore. His research interests include Artificial Intelligence in Education, Virtual and Augmented Reality, Formal and Informal Learning, STEM, Learning by Inquiry, Information Technology and Policy in Education. He has led and co-led several Singapore National Research Foundation and Ministry of Education funded research projects totaling over S$3 million. He has led the publication of three Springer books and published over 80 international journal articles, international book chapters and top conference papers. He is also a program committee member for international conferences organized by IEEE Technical Committee on Learning Technology, International AI & Education Society, Asia-Pacific Society of Computers in Education, and Global Chinese Society on Computers in Education.


Workshop 6: Natural Language Processing on Dialogue Systems
Title: coming soon

Summary:

Natural Language Processing (NLP) models are vital for human-computer interaction. This workshop will focus on natural language processing and its applications with a significant impact on dialogue systems. We will mainly focus our attention on creative and generative research topics. The workshop will not be limited to text generation, natural language understanding, answer generation, dialogue agents, text classification, fake texts detection and generation, machine translation, summary generation, etc. 

Keywords:
Natural Language Processing, Text Generation, Machine Translation, Summary Generation

Chair:

Prof. Juan Wen, China Agricultural University, China


Juan Wen received her B.E.degree in information engineering and Ph.D. degree in signal and information processing from Beijing University of Posts and Telecommunications. She was a visiting scholar at the University of Florida in 2019 and 2020. She is now an associate professor in the College of Information and Electrical Engineering, China Agricultural University. Her research interests include artificial intelligence, machine learning, natural language processing, and information security.


Workshop 7: Swarm Intelligence and Applications
Title: Swarm Intelligence and Applications

Summary:

Swarm Intelligence is a kind of stochastic method solving high dimensional, complicated functions we formulated to describe real-world problems. Due to the No Free Lunch (NFL) rule, there would be a balance between the capability and the application range. Therefore, swarm intelligence is still under demand in both the new algorithms and the experience of applications. New algorithms, even the improvements of the existed algorithms, might increase the capability such as the convergence rate, residual errors, stability, and so on. Meanwhile, their applications in solving real-world engineering problems such as energy dispatching, equipment disassembly, path planning, et. al. are also important and would be a guide and experiential materials for new applications.

This workshop aims to bring together the latest research progress of academic and industry researchers, such as evolutionary algorithms, human-based, physics-based, swarm-based algorithms and their applications and so on. We encourage prospective authors to submit related distinguished research papers on the subject of swarm intelligence and their applications. 

Keywords:
Swarm Intelligence, Nature-Inspired Algorithms, Evolutionary Algorithms, Swarm-Based Algorithms, Human-Based Algorithms, Physics-Based Algorithms, Optimization Algorithms, Global Optimization

Chair:

Dr. Zhengming Gao, Jingchu University of Technology, China


Zhengming Gao is an associate professor at Jingchu University of Technology. He received his D.-Eng. degree in 2010. He now serves as a faculty member with School of computer engineering, Jingchu University of Technology, Member of the Youth Working Committee of the CAAI, Member of IEEE, ACM, and Senior Member of CCF, Chairman of Jingmen Greenby Network Technology Co. Ltd. He has finished one provincial natural research foundation project, and four City Hall level foundation projects. He has published more than eighty papers, of which sixties of them having been indexed by SCI/EI, he also occupied more than 50 patents and 40 software copyrights, and he has published six monographs by now. He is now the leader of the “Research team of machine learning and its applications of Jingchu university of technology”, chairman of the institute of intelligent information technology, Hubei Jingmen industrial technology research institute; chairman of the institute of intelligent computation technology, Jingchu university of technology. And he is now focusing on intelligent information technology and development.

Workshop 8: Big Data and Artificial Intelligence
Title: Big Data & Artificial Intelligence with Applications

Summary:
With the rapid development of science and technology and the rapid rise of Internet information technology, people get more and more effective information from the Internet, and people's life has been greatly facilitated. With the gradual innovation and development of information technology, artificial intelligence has been paid more attention and applied in people's life. Artificial intelligence technology is developed by analyzing the law of people's activities through intelligent technology. It has a great degree of application function in robots, control systems and simulation. In artificial intelligence technology, the application of big data technology can analyze the potential law of data from a large amount of data, to summarize a certain development law, and then promote the further development of artificial intelligence.

This workshop aims to bring together the latest research progress of academic and industry researchers, such as big data science and foundations, big data infrastructure, big data management, big data search and mining, big data learning and analytics, data ecosystem, big data applications, artificial intelligence and technology, natural language processing, expert systems, multi-agent systems, knowledge engineering, neural network theory and architectures, artificial intelligence in modeling and simulation, pattern recognition, complex system, intelligent system, intelligent control, speech recognition, and synthesis, machine translation, computer perception, machine learning, intelligent robot, image processing and computer vision and so on. We encourage prospective authors to submit related distinguished research papers on the subject of big data and artificial intelligence. 

Keywords:
Big Data, Artificial Intelligence, Data Mining, Data Science, Natural Language Processing, Expert Systems, Multi-Agent Systems, Knowledge Engineering, Neural Network, Pattern Recognition, Complex System, Intelligent System, Intelligent Control, Speech Recognition and Synthesis, Machine Translation, Computer Perception, Machine Learning, Intelligent Robot, Image Processing and Computer Vision

Chair:

Assoc. Prof. Shan Liu, Communication University of China, China


Shan Liu is an associate professor and Chair of Intelligent Science Department at Communication University of China. She received her Ph.D. degree from Texas A&M University, in United States. Now she is a committee member of Chinese Association for Artificial Intelligence, a committee member of Chinese Institute of Electronics, a committee member of Beijing Society of Image and Graphics, a committee member of Association of Fundamental Computing Education in Chinese Universities, Member of China Automation Society, Member of Institute of Electrical and Electronics Engineers. She has served as a peer reviewer for a series of IEEE Transactions and other high-level SCI journals. Her main research areas include complex networks, intelligent tags, big data and artificial intelligence. In recent years, she has been invited to the University of California, National Laboratory of the United States, and other countries such as Brussels and Belgium, to give lectures and speeches, and has gained broad academic influence. She has presided over more than 30 research projects such as National Science Foundation and National Science and Technology Support Program, published more than 100 high-level academic papers, received many best paper awards, and applied for more than 30 patents of invention.

Co-Chair:

Prof. Zhe Dong, North China University of Technology, China


He is the Vice-president of School of Electrical and Control Engineering, director of the Beijing Key Laboratory of Fieldbus Technology and Automation, the Selected youth talent support program of Beijing universities, and the Deputy Secretary-General of the Internet of Things Working Committee of the China Instrument and controls Society, the standing committee member of the CCF Technical Committee on IPC, and the Director of the Beijing Artificial Intelligence Society. From 2000 to 2009, he graduated from Beijing University of Aeronautics and Astronautics and the Institute of Automation of the Chinese Academy of Sciences with a Bachelor of Engineering degree and a Ph.D. in Engineering, respectively. In 2014, he was a visiting scholar at the University of Michigan, USA. He has taught in the Department of Automation at North China University of Technology since 2009. In the past 5 years, he has presided over 2 national-level projects, 6 provincial and ministerial-level projects, 18 enterprise projects, published 34 academic papers, including 19 papers indexed by SCI or EI, 19 patents authorized, 6 software copyrights, 2 textbooks, and won 6 provincial-level awards such as the 2016 Beijing Second Prize for Science and Technology.



Workshop 9: Artificial Intelligence Algorithms
Title: When Deep Learning Meets Traditional Machine Learning/Computer Vision Technics

Summary:
Nowadays, deep learning methods, such as convolutional neural networks (CNN), Long-Short Term Memory network (LSTM), Recurrent Neural Networks (RNN), outperform the traditional methods in various areas, such as computer vision, handwriting character recognition, speech recognition, and so on. However, deep learning needs much more data to train the model than the traditional methods. Combining deep learning and traditional technics can not only overcome the insufficient data problem but also greatly improve performances of traditional methods in many real-world applications.

This workshop aims to bring together the research accomplishments provided by researchers from academic and the industry, such as deep learning with manifold regularization for classification and clustering, deep learning enhanced optical flow method for human action analysis, deep learning enhanced method for SAR. We encourage prospective authors to submit related distinguished research papers on the subject of deep learning methods combining traditional technics for potential applications.

Keywords:
Deep Learning, Manifold Learning, Optical Flow, SAR, Classification, Clustering

Chair:

Dr. Chao Yao, Shaanxi Normal University, China



Chao Yao is a lecturer at Shaanxi Normal University. He received his B.Sc. in telecommunications engineering in 2007, and his Ph.D. degree in communication and information systems in 2014, both from Xidian University, Xi’an, China. He was a visiting student at Center for Pattern Recognition and Machine Intelligence (CENPARMI), Montreal, Canada, during 2010–2011. He has published 20 research papers in influential journals, such as TIP, TNNLS, TOCN. He also hosts 4 research national and provincial projects.

Workshop 10: Information Technology
Title: to be announced

Summary:
Pursuing Research in Computer Science and Engineering from Dec 2020 till date in IoT and Security in the Smart Health Care Systems and Industries.
An active researcher with a keen interest in interdisciplinary and collaborative research. Working on five projects allied with Cyber-Physical Systems. Developed a Private Cloud Lab for the Department of IT with industry-institute collaboration at a cost of Rs.11,55,000, with 20 dedicated systems to the server.
Developed an Open Source Lab with the latest applications and software, to encourage students toward Research and Innovation. Developed In-house Applications, Created IT club, and facilitated innovative student projects. Developed an industry-aligned curriculum, MongoDB for Java Developers. Framed syllabus for cutting edge technology courses - Cloud Computing, IoT, Security in Big Data, Web collaboration and technology, Programming in Hadoop.

Keywords:
IoT & Machine learnin, Data Science, Cloud and Web Security, Blockchain

Chair:

Dr. R. Priyadarshini, Computer Science Engg.Lincoln Universiti College, Malaysia


She published 10 Scopus Indexed Journals, published 5 Web of Science Indexed Journals, communicated / Accepted 5 SCI indexed Journals, presented in 26 International Conferences and 4 National Conferences. Her Google Scholar H-Index is 5.  Her Scopus H-Index is 3. She works as a  reviewer for Journals published by Wiley, Springer, Sage & Inderscience and for International Conferences-CECNET 2017(Taiwan), 2018(Bangkok), 2019(Japan) and 2020 (Seoul).

Workshop 11: Deep Learning based Object Detection Models
Title: Deep learning based object detection and Application

Summary:

Object detection is a crucial computer vision task, aiming at classification and localization of objects in an image or video. It has gained prominence in recent years due to its widespread applications. Over the past years, deep learning has received a great deal of attention and has been widely applied in object detection. Not only has there been a constant increase of related papers, but also significant progress has been achieved. However, there are still challenges in object detection, including intra- class variation, number of categories, efficiency, etc.

This deep learning based object detection workshop aims to bring together the latest research progress of academic and industry researchers, such as dense object detection, rotation object detection, 3D object detection, video object detection, weakly-supervised object detection, self-supervised object detection, few-shot object detection and so on. We encourage prospective authors to submit related distinguished research papers on the subject of deep learning-based object detection.

Keywords:
Object Detection, Few Shot Object Detection, Weakly-Supervised Object Detection, Rotation Object Detection


Chair:

Dr. Hongli Lin, Hunan University, China


She is an associate professor at the school of information science and engineering at Hunan University, China. She specializes in teaching image processing, computer version, and AI. Her research interests include object detection in image and video, image segmentation, text detection and recognition, action recognition, re-identification/detection, and intelligent systems. She hosts and participates in several national and provincial scientific research projects. She has published more than 10 papers in international conferences and journals.

Workshop 12: Drug AI
Title: Artificial Intelligent in Drug Discovery and Design

Summary:
Artificial intelligence has undergone rapid development in recent years and has been successfully applied to real-world problems such as drug discovery and design. Much of the initial skepticism regarding applications of AI in pharmaceutical discovery has started to vanish, consequently benefitting medicinal. This workshop is going to discuss the advantages of current deep learning applications, together with a perspective on next-generation AI for drug discovery. Deep learning-based approaches have begun to address some fundamental problems in drug discovery. Certain methodological advances, such as deep neural networks, message-passing models, hybrid de novo design, and other innovative machine learning paradigms, will likely become commonplace and help address some of the most challenging questions. Open data sharing and model development will play a central role in the advancement of drug discovery and design with AI.

This workshop aims to bring together the latest research progress of academic and industry researchers, such as artificial intelligence methods, machine learning, and deep learning models, especially in drug discovery and design areas. We encourage prospective authors to submit related distinguished research papers on this subject.

Keywords:
Artificial Intelligence, Machine Learning, Deep Learning， Representation Learning, Transfer Learning, Drug Design, Virtual Screening, Computer-Aided Synthesis Planning, De Novo Molecule Generation, Natural Language Processing, Smiles, Generative Models, Prediction Uncertainty, Model Interpretability


Chair:

Prof. Li Wang, Nantong University, China


Li Wang is a professor at Research Center for Intelligence Information Technology at Nantong University. He received his Ph.D. from Tokushima University, Japan in 2011. He was a postdoctoral fellow at Nanjing Medical University and visiting scholar at the University of Texas. He has presided over or participated in 13 national, provincial and municipal research projects, and has published nearly 100 papers in domestic and foreign journals, including more than 20 SCI/EI papers as the first author. His research interests are medical big data mining and management, especially the application of NLP, ML and DL in drug AI.

Workshop 13: Artificial intelligence technology and Application
Title: Artificial intelligence technology and Application

Summary:
Artificial intelligence has undergone rapid development in recent years and has been successfully applied to real-world problems such as economic, social, life, and other industries discovery and design. n the future, the field of artificial intelligence will continue to make rapid progress, and language, sound, and vision technologies and multimodal solutions will make great progress, completely changing "human efficiency".This seminar will discuss the advantages of current deep learning applications, the comprehensive application of artificial intelligence with computer vision, deep learning, and big data as the core, as well as the application prospect and development trend of the next generation of artificial intelligence. The method based on deep learning has begun to solve some basic problems in industry, agriculture and other fields. Some methodological advances, such as deep neural networks, message passing models and other innovative machine learning paradigms, may become commonplace and help solve some of the most challenging problems. Open data sharing and model development will play a central role in using artificial intelligence to promote smart city, smart transportation, smart agriculture and design.
This workshop aims to bring together the latest research progress of academic and industry researchers, such as artificial intelligence methods, machine learning, and deep learning models, especially in knowledge representation, automatic reasoning and search methods, machine learning and knowledge acquisition, knowledge processing systems, natural language understanding, computer vision, intelligent robots discovery and design areas. We encourage prospective authors to submit related distinguished research papers on this subject.

Keywords:
Artificial Intelligence, Machine Learning, Deep Learning, Representation Learning, Transfer Learning, Knowledge Representation, Automatic Reasoning And Search Methods, Machine Learning And Knowledge Acquisition, Knowledge Processing System, Natural Language Understanding, Computer Vision, Intelligent Robot, Intelligent City, Intelligent Transportation, Intelligent Agriculture


Chair:

Prof. Qiudong Yu, Tianjin University of Technology and Education, China


He is a Professor of computer science and doctoral supervisor, member of the young scientist Club of China Electronics Society, expert of the "national training program" of the Ministry of education, expert of project technical evaluation of Tianjin Science and Technology Bureau and Tianjin Agricultural and Rural Committee, expert of digital campus construction specification of Vocational Colleges of the Ministry of education, director of Tianjin automation society, and honorary president of Tianjin high tech Enterprise Association. With nearly 20 years of computer software and hardware development experience and theoretical foundation, he has deeply integrated computer technology with the production of various industries and specializes in the research on the combination of computer digital technology such as Internet of things, informatization, automation and intelligence with the application fields such as agriculture and vocational education. He has successively presided over and completed dozens of national projects, provincial and ministerial science and technology plan projects and enterprise horizontal entrusted projects, and accumulated more than 100 scientific research achievements. Won one first prize of the Tianjin Science and technology progress award, three second prizes of Tianjin Science and Technology Progress Award (two of which were presided over), and young and middle-aged backbone innovative talents in Colleges and universities in Tianjin.


Workshop 14: Deep Neural Network Compression Technology
Title: Deep Neural Network Compression Technology

Summary:
Deep neural network compression technology arises with the development of deep learning technology, where the computation cost and storage cost deep neural networks are increasing drastically in recent years. By compressing neural network models using technologies including network pruning, weight quantization, and knowledge distillation, researchers can deploy these deep learning models on devices with limited resources. Developments in recent years are trying to study the cooperation between model compression technology and network architecture, and also efficient implementation of hardware.

This workshop aims at gathering the latest unpublished research on deep neural network compression technology, including network compression, weight quantization, low rand decomposition, neural architecture search, knowledge distillation, and so on. We encourage researchers to join us with their excellent work on deep neural network compression technology and together promote the development of the research area.


Keywords:
Deep Neural Network Compression, Network Pruning, Weight Quantization, Low-Rank Decomposition, Knowledge Distillation



Chair:

Prof. Honggang Qi, University of Chinese Academy of Sciences, China


Honggang Qi is a professor at University of Chinese Academy of Sciences (UCAS) of School of Computer Science and Technology. He is a member of ISO / IEC JTC 1 / SC 29, executive member of CCF multimedia technology special committee, editorial member of Chinese Journal of Image and Graphics, and distinguished researcher of the State Key Laboratory of Digital Multimedia Chip Technology. He graduated from the Institute of Computing Technology, Chinese Academy of Sciences, and has been engaged in the research of video image compression and computer vision for a long time. As the main participant, he completed the key project of NSFC "efficient digital video coding and decoding technology and its application in international and national standards", and the National 863 major project "digital audio and video coding and decoding SOC1". So far, he has published more than 80 academic papers, including top journals IJCV, top conferences in the ICCV, ECCV, AAAI, and IEEE Transactions, and more than 10 as the first author. The citation rate of a single paper is more than 1000. He has 8 Chinese authorized invention patents and 2 international patents (authorized in the United States and Japan). As an active participant in the national Audio and Video Standards (AVS), he has contributed more than 50 technical proposals, including mode coding optimization, buffer management and motion vector prediction. He also has participated in MPEG International Conferences many times and proposed more than 20 technical proposals including integer inverse transform (IDCT) and reconfigurable video coding (RVC). At present, her research interests include computer vision and related video image understanding.


Workshop 15: Multi-modal and Brain-inspired Vision
Title: Advances of Multi-modal Learning and Brain-inspired Vision

Summary:
In recent years, multi-modal data emerges everywhere and greatly improves the ability of AI. Meanwhile, brain-inspired vision models have attracted more and more attention from researchers. Compared with traditional methods, brain-inspired models have a more reasonable structure design and data processing mode. However, most models are very large-scale models designed for single-mode data. While achieving high performance, the overall complexity of these models is very high and the number of parameters is large, which requires strong computing resources to support. Therefore, it is difficult to directly apply to large-scale multi-modal data and resource-constrained computing equipment, which seriously restricts the application in multi-modal cognitive computing scenarios. At the same time, current models lack a solid and unified theoretical basis and practical verification in small sample learning, interpretability, training stability, and other aspects, which seriously affect the robustness of relevant algorithms and hinder the further development in the field of real-world applications.

This workshop hopes to present an opportunity for exchanging new findings in a multi-modal and brain-inspired vision, mainly including the innovative technology and breakthrough research results. Researchers are welcome to contribute to this direction. Proposed submissions should be original and unpublished.

Potential topics include, but are not limited to:
• Multi-modal and multi-task learning
• Multi-modal models for real-world applications, such as image-text retrieval, scene graph generation, referring segmentation, etc.
• Big data driven multi-modal learning for big models
• Vision transformer for applications, such as object detection, image classification, semantic segmentation, etc.
• Multi-modal model compression, information extraction, structural representation, data generation, etc.
• Innovative structures or learning methods for spiking neural network (SNN)
• Neuromorphic computation
• Retinal neural network
• Neural network of visual cortex
• High-speed photoelectric sensing devices and chips


Keywords:
Multi-modal Learning, Multi-task Learning, Vision Transformer, Deep Learning, Neuromorphic Computation, Spiking Neural Network, Visual Cortex



Chair:

Assoc. Prof. Pingping Zhang, Dalian University of Technology, China


Pingping Zhang is an Associate Professor at School of Artificial Intelligence of  Dalian University of Technology. He is also a member of IIAU-Lab (Intelligent Image Analysis and Understanding Lab). His research interests include deep learning, computer vision and multimedia analysis. He serves as the PC member or reviewer for some top journals and conferences, such as IEEE TPAMI, TIP, TITS, TMM, TCSVT, PR, CVPR, ICCV, ECCV, NeurIPS, AAAI, IJCAI. He published 50+ peer reviewed papers (CCF-A/B with 2800+ citations) in artificial intelligence and computer vision. He has been with ACRV Lab as a visiting researcher from 2017 to 2018. He was awarded the Young Talents of Dalian High-level Talents, Xinghai Young Talent Training Program of Dalian University of Technology, and CSIG Excellent Doctoral Dissertation in 2020.

Workshop 16: Deep Reinforcement Learning
Title: Deep Reinforcement Learning and Applications

Summary:
Supervised and unsupervised learning have been extensively researched in the past decades and have achieved immense success. What makes reinforcement learning stands out is that a reward instead of an example is necessary for training. Reinforcement learning tries out different actions with different policy and record different outcomes (rewards). Much attention has been paid to reinforcement learning until the recent emergence of deep reinforcement learning. By integrating deep learning into reinforcement learning, deep reinforcement learning is not only capable of continuing sensing and learning to act, but also capturing complex patterns with the power of deep learning. Recent years have witnessed the enormous success of deep reinforcement learning such as AlphaGo, leading up to increasing advances in intelligent decision-making in many areas.

This workshop will bring together researchers working at the intersection of deep learning and reinforcement learning, and it will help researchers exchange their ideas in this field. Proposed submissions should be original and unpublished. Potential topics include, but are not limited to: research and improvement on deep reinforcement learning, applications of deep reinforcement learning in enterprise production scheduling, vehicle routing, data packets routing, logistics, quantitative transaction, and so on.

Keywords:
Deep Reinforcement Learning, Intelligent Decision-Making, Enterprise Production Scheduling, Vehicle Routing, Data Packets Routing, Logistics, Quantitative Transaction



Chairs:

Chair 1：
Assoc. Prof. Yongming Tao, Dongbei University of Finance and Economics, China



Yongming Tao is an associate professor at the School of Data Science and Artificial Intelligence at Dongbei University of Finance and Economics, China. He was the head of Computer Science and Technology department. He is council member of Computer Education Research Association of Chinese Universities, and one Drafter of Specification for Core Courses of Computer Science: “Programming”, and “Data Structures”. His research interests include Deep Reinforcement Learning, Artificial Intelligence in Finance, and Quality Management. He participated in multiple funded projects including Key International Cooperation and Exchanges Project, General Program, Young Scientists Fund of the National Natural Science Foundation of China. And he obtained 4 patents.


Chair 2：
Dr. Taixin Li, Dongbei University of Finance and Economics, China

                                                                                                                     

Taixin Li is a lecturer at School of Data Science and Artificial Intelligence of Dongbei University of Finance and Economics, IEEE Member. He received a B.S. degree in telecommunications engineering and a Ph.D. degree in telecommunications and information system from Beijing Jiaotong University in 2013 and 2018. He joined Huawei Technologies in 2018 where he was the Senior Engineer of the Network Technology Laboratory. He joined Computer Network Information Center of Chinese Academy of Sciences in 2020 where he was the assistant professor. His research interests include deep reinforcement learning, enterprise production scheduling, routing algorithms and protocols, and space-terrestrial integrated networks. He has authored over 20 peer-reviewed papers in leading journals and conferences (such as IEEE Transactions on Mobile Computing and IEEE ICC) and obtained 5 patents. He served as a reviewer of international journals and conference such as Journal of Ambient Intelligence and Humanized Computing, Mathematical Problems in Engineering, and Globecom2019.

Workshop 17: Multimodal Information Intelligent Processing Technology
Title: Multimodal Information Intelligent Processing Technology and Its Applications

Summary:
Multimodal information processing is developed based on single-media information processing such as text, image, and audio. The existing methods for processing single-media data are the basis for multimodal data processing. Research content specific to multimodal information processing focuses on modeling, acquisition, fusion, semantic metrics, analysis, and multimodal information retrieval. Many research results show that information processing algorithms and methods based on multimodal concepts often yield better performance and results than traditional methods. In content-based multimedia information retrieval, for the semantic gap problem in content-based video and audio retrieval, using textual information that is co-occurring or co-occurring with video and audio data to perform multimodal semantic analysis and similarity metrics is a very effective method to overcome the semantic gap problem. The semantic gap problem is common in cross-media information processing tasks. The semantics of the processed information objects, whether based on episodic semantics (denotational semantics) or connotational semantics (associative semantics) concepts, are not fully or finally expressed within the scope of single media information. Multimodal information processing methods provide new ideas and methods for solving this problem. Therefore, multimodal information intelligent processing is still under demand in both the new algorithms and the experience of applications. New algorithms, new applications, and even the improvements to the existed algorithms might increase the capability of the system such as the accuracy, percision, recall, and so on. Meanwhile, their applications in solving real-world problems in many areas such as image processing, pattern recognition, computer vision, natural language processing, et. al. are also important and would be a guide and experiential materials for new applications.

This workshop aims to bring together the latest research progress of academic and industry researchers, such as “text classification, text mining, sentiment analysis, video/image processing, video/image coding, video/image classification, video/image recognition, video/image understanding, speech processing techniques, speech recognition, speech synthesis, multimodal retrieval techniques, cross-modal retrieval" and their applications and so on. We encourage prospective authors to submit related distinguished research papers on the subject of multimodal information intelligent processing technology and its applications.

Keywords:
Text classification, text mining, sentiment analysis, video/image processing, video/image coding, video/image classification, video/image recognition, video/image understanding, speech processing techniques, speech recognition, speech synthesis, multimodal retrieval techniques, cross-modal retrieval



Chair:

Prof. Kurban Ubul, Xinjiang University, China



Kurban Ubul is a Professor, Doctoral supervisor, Director of China Computer Federation (CCF) and China Image and Graphics Society(CISG), Vice Chairman of Urumqi branch of CCF, Deputy Secretary General of Technical Committee on Pattern Recognition and Machine Intelligence of Chinese Automation Association (CAA-PRMI), member of Computer Vision Technical Committee (CCF-CV) and Artificial Intelligence and Pattern Recognition Technical Committee (CCF-AI) of CCF, member of Document Analysis and Recognition Technical Committee of China Graphics and Image Society (CISG-DIAR), member of Pattern recognition Technical Committee (CAAI-PR) and multilingual intelligent information processing Technical Committee (CAAI-IMLIP) of Chinese Association for Artificial Intelligence, senior member of CCF, member of IEEE, IAPR, ACM and IAENG, Director of Department of Electronics, School of Information Science and Engineering, Xinjiang University. He is a reviewer of TPAMI, Neurocomputing, IEEE THMs, IET biometrics and other journals. Served as General Chair of NLPAI2020/ NLPAI2021/ NLPAI2022, Local Chair of NCIG 2020/CPCC2022, Area Chair of PRCV2019/ IJCB 2021 TPC chair of CCBR2018, and TPC member/reviewer of many conferences such as CVPR, ICPR, ICDAR, CCFAI, CCDM, NCIG and CCBR. He has held the subproject of China's National Key R & D projects, 3 projects of National Natural Science Foundation of China, and more than 10 other projects, published more than 150 papers, 3 academic monographs, 1 work chapter, 8 patents, more than 40 computer software copyrights, and won 8 awards at the provincial and ministerial level.


Workshop 18: Digital Human Technology and Metaverse
Title: Digital Human Technology and Metaverse

Summary:
As we are yearning and pursuing the web 3.0, virtual reality and augmented reality technologies, together with blockchain, artificial intelligence, Internet of things, and big data, have jointly spawned the metaverse, a product of the digital economy era. A digital person is an important medium for the interaction between the real world and the virtual world, and therefore digital human technology is fundamental in constructing metaverse scenarios.

This workshop aims to bring together academic and industry researchers to share the latest research progress regarding digital human technology and metaverse, including but not limited to the following issues.
1. Modelling, algorithms, and theories of digital human and metaverse;
2. 3D reconstruction of face, hands, and other body parts;
3. Comprehensive perception of non-verbal and verbal features;
4. Multi-modal human-computer interaction;
5. Expression capture and transfer for high naturalness digital human;
6. Real time mouth animation rendering driven by speech;
7. Collaborative of multiple digital human
8. Applications of digital human to AR/VR based metaverse.

We encourage prospective authors to submit related distinguished research papers on the subject of digital human technology and metaverse.

Keywords:
Digital human, metaverse, intelligent interaction, multi-model interaction, 3D reconstruction, expression capture and transfer, AR/VR




Chair:

Prof. Yinwei Zhan, Guangdong University of Technology, China



Yinwei Zhan is a professor and the director of Institute of Interactive and Visual Informatics, at School of Computer Science and Technology, Guangdong University of Technology. Besides, he is the director of Guangdong Engineering Technology Research Center of Human Computer Interaction and Video Analysis, a vice president of Guangdong Society of Image and Graphics (GSIG) and the director of Virtual Reality and Intelligent Interaction Professional Committee of GSIG, and a deputy director of Image Application and System Integration Professional Committee of China Society Image and Graphics (CSIG). His research interests cover computer vision and intelligent interaction and their applications to VR/AR and industrial vision. He has been PIs for more than 20 projects in which 2 funded by National Natural Science Foundation of China and others by local governments and enterprises. He has edited 1 book and published more than 100 academic papers.



Workshop 19: Natural User Interface
Title: Technology and Application of Natural User Interface

Summary:
Natural User Interfaces (NUIs) allow users to access interactions with their daily-life behaviors or experiences. The advantage of NUIs is that the user interaction feels interesting, easy, and natural because the user can use a broader range of basic skills compared to more traditional graphical user interfaces(GUIs). NUIs leverage some of the natural human abilities and build on them to integrate artificial technology woven into learned human interactions. NUIs focus on traditional human abilities, such as vision, touch, speech, handwriting, and motion, as well as cognition, creation, and exploration to replicate real world environments to optimize interaction between physical and digital objects.
This workshop aims to bring together the latest research progress of academic and industry researchers, such as adaptive interaction technology, emotional computing, human factors and ergonomics, exoskeleton interaction, multichannel interaction technology, tangible user interface, and user behavior study, touch or touchless user interface and so on. We encourage prospective authors to submit related distinguished research papers on the subject of natural user interfaces.

Keywords:
Natural user interfaces, Adaptive interaction technology, Emotional computing, Human factors and ergonomics, Exoskeleton interaction, Multichannel interaction technology, Tangible user interface, User behavior study, Touch or touchless user interface




Chair:

Assoc. Prof. Jibin Yin, Kunming University of Science and Technology, China



Jibin Yin is an associate professor in the Faculty of Information Engineering and Automation and the director of Intelligent Interaction Lab at Kunming University of Science and Technology. He is a Member of the ACM and the IEEE. He has been working on fundamental studies in the field of human-computer Interaction for around 20 years. His research interests include all aspects of human-computer interaction, particularly wearable computing, emotional computing, exoskeleton interaction, human performance models, multi-touch interaction, eye-based interaction, tangible user interface, gesture input, game interaction. He has hosted 5 national and provincial projects, such as National Natural Science Foundation of China and Yunnan Natural Science Foundation. He serves as reviewer and member of procedure committee of ISFT and other international conferences. He has published 3 books, published more than 50 academic papers including over 30 papers indexed by SCI or EI, and obtained more than 5 patents and 20 software copyrights.