Workshops
Workshop 1:Tensor Learning and Its Applications
Keywords: Tensor Learning; Image Processing; Pattern Recognition

Summary: Tensor is a natural representation of multi-modality data such as natural image, video, hyperspectral image, medial image, social network data and so on. At present, tensor learning has been widely applied in the fields of machine learning, pattern recognition, data mining and image processing. A lot of excellent work have been obtained all of the world. 
The aim of this workshop is to bring together the research accomplishments provided by researchers from academia and industry. The other goal is to show the latest research results in the field of Tensor Learning and Its Applications. We encourage prospective authors to submit related distinguished research papers on the subject of theoretical approaches and practical applications. 
Chair 1: Prof. Xiaowei Yang, South China University of Technology, China

Bio: Xiaowei Yang received the B.S. degree in theoretical and applied mechanics, the M.Sc. degree in computational mechanics, and the Ph.D. degree in solid mechanics from Jilin University, Changchun, China, in 1991, 1996, and 2000, respectively. He is currently a full-time Professor with the School of Software Engineering, South China University of Technology, Guangzhou, China. He has published over 160 journals and refereed international conference papers on IEEE Transactions on Software Engineering, IEEE Transactions on Neural Networks and Learning Systems, IEEE Transactions on Cybernetics, IEEE Transactions on Evolutionary Computation, IEEE Transactions on Image Processing, IEEE Transactions on Fuzzy Systems, IEEE Transactions on Geoscience and Remote Sensing, IEEE Transactions on Medical Imaging, Pattern Recognition, ICSE, ICDM and SDM. His current research interests include designs and analyses of algorithms for large-scale pattern recognitions, imbalanced learning, semi-supervised learning, support vector machines, tensor learning, and evolutionary computation.

Chair 2: Prof. Shuyuan Yang, Xidian University, China
Bio: Shuyuan Yang received the B.S. degree in electronic engineering, the M.Sc. degree in circuits and systems, and the Ph.D. degree in circuits and systems from Xidian University, Xi’an, China, in 2000, 2003, and 2005 respectively. She is currently a full-time Professor with the School of Artificial Intelligence, Xidian University, Xi’an, China. She has published over 60 journals papers on IEEE Transactions on Neural Networks and Learning Systems, IEEE Transactions on Image Processing, IEEE Transactions on Geoscience and Remote Sensing and so on. Her current research interests include designs and analyses of algorithms for sparse machine learning and optimization, deep learning and lightweight implementation, semi-supervised machine learning, brain-like intelligent computing, tensor learning, intelligent target information perception and interpretation.

Chair 3: Assist. Prof. Lifang He, Lehigh University, USA
Bio: Lifang He is currently an Assistant Professor in the Department of Computer Science and Engineering at Lehigh University. She received the B.S. degree in Computational Mathematics from Northwest Normal University in 2009, and the Ph.D. degree in Computer Science from South China University of Technology in 2014. Before joining Lehigh, she was a postdoc associate in the Perelman School of Medicine at University of Pennsylvania, and the Weill Cornell Medical College of Cornell University. Her research interests primarily focus on machine learning/deep learning, data mining, and tensor analysis, with major applications in social science and neuroscience. She has published more than 120 papers in refereed journals and conferences, such as WIREs Computational Molecular Science, Neural Networks, IEEE Transactions on Knowledge and Data Engineering, IEEE Transactions on Image Processing, IEEE Transactions on Medical Imaging, NeurIPS, ICML, CVPR, MICCAI, KDD, AAAI, EMNLP.
Workshop 2:AI in Medical Image Analysis
Keywords: Medical Image Processing; Deep Learning; AI; Computer Aided Diagnosis

Summary: Medical imaging is an important means of medical diagnosis. The image modality can be any type of CT, MRI, Ultrasound, X-Ray etc. In recent years, AI has promoted rapid development of medical image analysis, mainly covering medical image classification, object detection, organ or tissue segmentation, computer aided diagnosis (CAD) 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 medical image analysis. We encourage prospective authors to submit related distinguished research papers on the subject of both: theoretical approaches and practical case reviews.
Chair 1: Assoc. Prof. Guanghua Tan, Hunan University, China

Bio: Guanghua Tan received a Ph.D. degree in Computer Science and Technology from Zhejiang University. He worked as an associate professor at the School of Computer Science and Electronic Engineering, Hunan University. His research interests include Computer Vision, Computer Graphics and Deep Learning. He participated as PI in the National Natural Science Foundation, National Key Projects, National Key Research and Development Project, etc. Based on these projects, he published more than 30 papers in IEEE Trans, and other journals/conferences.

Chair 2: Assoc. Prof. Xiaoliang Zhu, Xinjiang University, China

Bio: Xiaoliang Zhu is currently a senior engineer at Xinjian University. Zhu received the PhD degree from Ningxia University in Computational Mathematics in 2020 and qualified as a senior engineer in 2014. Zhu graduated with a master's degree in North Minzu University. The research interest focuses on digital image process, Artificial Intelligence, and numerical solution of the partial differential equations

Workshop 3:Computer Vision Assisted Structural Health Monitoring
Keywords: Structural Health Monitoring, Computer Vision, Machine Learning, Deep Learning, Image Processing

Summary: Recently, computer vision has brought a novel paradigm and huge revolution in structural health monitoring, which is further enhanced by cutting-edge machine learning and deep learning techniques. With the vigorous development of various neural networks and supervised learning/unsupervised learning/semi-supervised learning/self-supervised learning/reinforcement learning algorithms, computer vision enables the autonomous discovery of embedding knowledge and the intelligent diagnosis of structural health based on inspection images and monitoring videos in a purely data-driven manner or a data-model-driven manner. This workshop aims to provide a platform to share current scientific and technical progress about computer vision assisted structural health monitoring.
Chair: Assoc. Prof. Yang XU, Harbin Institute of Technology, China

Bio: Dr. Yang XU is an associate professor at Harbin Institute of Technology in China. His research interests include structural health monitoring with computer vision and deep learning. He has published over 30 articles in top journals (4 indexed as ESI and Wiley Top Cited Papers) and over 20 national patents and software copyrights. 
As PI, he has taken over ten programs from National Natural Science Foundation of China, National Key & Develop Plan Program (Sub-projects), China Postdoctoral Science Foundation, China State Key Laboratory, Heilongjiang Province Natural Science Foundation and Postdoctoral Science Foundation. 
He was awarded the Fellowship of China National Postdoctoral Program for Innovative Talents and Heilongjiang Province Postdoctoral Program for Young Talents. He has served as the session chair of the 8th World Conference on Structural Control and Monitoring (8WCSCM), guest editor of Special Issue “Machine Learning for Structural Health Monitoring”, core member of organization committee for International Competition for Structural Health Monitoring (2020/2021/2022), and members of earlier career researchers committee of International Society for Structural Health Monitoring of Intelligent Infrastructures (ISHMII). He has delivered several keynote and invited talks on international academic conferences on the topic of Computer Vision and Deep Learning Enhanced Structural Health Diagnosis.

Workshop 4:Remote sensing image processing and interpretation with machine/deep learning
Keywords: Remote sensing, land classification, mapping, change detection

Summary: Remote sensing technique plays a critical role in many aspects of modern society, like the agriculture, urbanization, hazard, hydrology, climate, etc. Thanks to the increased availability of remote sensing data and computational resources, the use of advanced machine / deep learning methods has taken off. Nowadays, various frameworks like CNN, RNN, GNN and transformers have been widely applied and great achievements are acquired. However, remote sensing data bring new challenges. Multi source images, extremely complex scenarios, lack of training samples, etc, are all affecting the model performance, and need to be further studied. This workshop is targeted to those with remote sensing or computer vision background, who are encouraged to present their research about satellite or UAV image processing and interpretation in various fields. The specific issues would mainly involve: 
  • 1, muti-source image fusion using optical, multi-spectral and synthetic aperture radar (SAR) images; super-resolution algorithms to increase the image interpretation; cloud removal skills in the optical images. 
  • 2, land use land cover classification, like the mapping of cultivated lands, crops, buildings, roads, water, landslides, etc. 
  • 3, change detection of dual-phase or time series images in the urbanization, environmental change, crop production, etc.
Chair 1: Assoc. Prof. Panpan Tang, Nanhu Laboratory, China

Bio: Panpan Tang received received the B.S. degree in surveying and mapping engineering from the China University of Geosciences, Beijing, China, in 2008, and the Ph.D. degree in cartography and geographic information system from the Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing, in 2014. From 2014 to 2020, he worked in the aerospace information research institute, Chinese academy of Sciences as an associate researcher. He is currently a Senior research fellow in the Research Center of Big Data technology, Nanhu Laboratory. 
His research interests are remote sensing (synthetic aperture radar -SAR and optical) image processing with deep-learning methods, including pixel-based segmentation, objection detection and change detection. Main application areas are the agricultural informatization and hazard monitoring. In agriculture, now his studies include mapping and monitoring crops, cultivated lands, crop diseases, phenology and growth situation. He has published more than 20 SCI papers in the international remote sensing related journals, and hosted the project of national natural science foundation.

Chair 2: Assoc. Prof. Bo Zhao, Nanhu laboratory, China
Bio: Bo Zhao received the Bachelor’s degree in Geographical Information System from Northwest Agriculture & Forestry University in June, 2004. He received the Master’s degree in Earth Exploration and Information Technology from China University of Geosciences, in January, 2011. Received his Doctoral degree in Geochemistry from China University of Geosciences, in January, 2015. Thereafter, He did his postdoc research in Chang’an University from July 2015 to July 2017, and then in Klagenfurt University from 2017 to 2018. Now, He is a senior researcher in Research Center of Big Data Technology, Nanhu Laboratory, and his research interests include remote sensing, deep learning (or say AI), earth sciences, and relevant interdisciplines.
Workshop 5:AI in Computer-aided Diagnosis and Treatment
Keywords: Computer- aided Diagnosis and Treatment; Medical Image Analysis; Deep Learning; Image processing

Summary: Currently, artificial intelligence is undergoing rapid development and widespread application, especially in Computer-aided Diagnosis and Treatment, such as medical image fusion, registration, organ or tissue segmentation, target tracking, dose prediction, prognosis assessment, etc. The workshop aims to promote the cross-fusion and in-depth application of artificial intelligence in medical image and computer-aided diagnosis and treatment, provide reliable theoretical and technical supports for computer-aided diagnosis and treatment, improve the means and methods of medical non-invasive diagnosis, increase the accuracy and efficiency of computer-aided diagnosis and treatment, and promote the development of computer-aided diagnosis and treatment towards high precision, high efficiency, and intelligence.
Chair : Assoc. Prof. Miao Liao, Hunan University of Science and Technology

Bio: Miao Liao received the B.S., M.S., and Ph.D. degree in Biomedical Engineering from Central South University in 2010, 2013, and 2016, respectively. She currently worked as an associate professor at the School of Computer Science and Engineering, Hunan University of Science and Technology. Her research interests include medical image analysis, artificial intelligence, and pattern recognition. She has published over 30 articles in the field and over 20 national patents. As PI, she has taken nearly ten programs from National Natural Science Foundation of China, China Postdoctoral Science Foundation, Hunan Province Natural Science Foundation, Scientific Research Fund of Hunan Provincial Education Department. She has served as a technical chair of the 2022 International Conference on Virtual Reality, Human-Computer Interaction and Artificial Intelligence (VRHCIAI 2022).

Workshop 6:Artificial Intelligence applications in Healthcare
Keywords: Healthcare, Medical image processing, artificial intelligence, Deep learning

Summary: Artificial Intelligence is being widely accepted tools that will support and improve human work rather than outright supplant that of doctors and other healthcare professionals. AI is prepared to assist medical staff with a range of duties, including administrative workflow, clinical paperwork, patient outreach, and specialty assistance like image analysis, medical device automation, and patient tracking. Artificial intelligence allows healthcare practitioners to examine data at an unprecedented level of accuracy and speed- from identifying early signs of diseases, to identifying malignant tumors, to determining treatment options. This technology is revolutionizing the field of medicine, as it enables physicians to make informed decisions and provide accurate diagnosis to patients, which can ultimately lead to better outcomes. The application of AI in healthcare has the potential to revolutionize the field of medicine and improve patient outcomes. 
This workshop seeks to put together the study accomplishments provided by academic and industrial scholars. The other goal is to disseminate the most current results in the field of AI in healthcare.  Authors are highly encouraged to submit their research work on the subjects of both theoretical methods and actual case studies in AI applications in healthcare.
Chair : Dr. EJAZ UL HAQ, Dongguan University of Technology, China

Bio: EJAZ UL HAQ received B.S. degree in electrical engineering from university of engineering and technology, Peshawar, Pakistan in 2014, the M.S degree in electrical engineering from Xiamen University of Technology, Xiamen, China in 2018, and the Ph.D. degree in information and communication engineering from Shenzhen University, Shenzhen, China, in 2022. He is currently a full-time Postdoctoral fellow with the School of Cyberspace security, Dongguan University of technology, Dongguan, China. He has published over 15 journals papers in high-tiers journals and so-on. His research interests primarily focus on machine learning/deep learning, and computer vision, with major applications in medical image processing and neuroscience.

Workshop 7:Broad learning based pattern classification and image recognition
Keywords: Broad learning algorithms, pattern classification, image recognition , deep broad learning

Summary: The recent years have witnessed significant development of deep learning in artificial intelligence. However, deep models are naturally inexplicable models due to the complex multilayer structures with high computational complexity. Very recently, a novel neural network called broad learning system (BLS) caves out a research wave in machine learning and pattern recognition. The BLS broadens the network by paralleling feature mapping nodes and enhancement nodes, and only the weights connected to the output layer need to be trained, resulting in a very fast and accurate learning capacity without deep structure. The designed neural networks expand the neural nodes broadly and update the weights of the neural network incrementally when additional nodes are needed or when the input data entering to the neural network continuously. Such a structure and incremental learning algorithm are perfectly suitable for modeling and learning big data environment. This workshop will discuss new broad learning models and their applications in regression and recognition tasks. The topics include but not limited to robust broad learning models, broad learning for image processing, broad learning for pattern recognition, deep broad learning networks, semi-supervised/un-supervised broad learning algorithms, broad learning for image recognition, and so on.
Chair : Assoc. Prof. Licheng Liu, Hunan university, China

Bio: Licheng Liu received the Ph.D. degree from the University of Macau, Macau, China, in 2016. He is currently an Associate Professor and a Yuelu Scholar in Hunan University, and a researcher in the National Engineering Research Center of Robot Visual Perception and Control Technology. His research interests include image processing, pattern recognition, deep learning and broad learning. Around these topics, he has published more than 35 papers in top journals/conferences, among which 13 papers are IEEE Transactions /ACM Transactions papers (first author/corresponding author). Two papers are elected as ESI highly cited papers. He has severed as a reviewer for many top journals including the TIP, TNNLS, TCYB, TSMC: System, TCSVT, TMM, SPL, Information Sciences, and so on. He has won the Macau Science and Technology Award for Postgraduates in 2016, and the Special Award for Teaching Achievements of Higher Education in Hunan Province.

Workshop 8:Real Time applications in Machine Vision
Keywords: Computer vision, Camera, Lightning, Text Recognition, Real-time applications

Summary: This workshop is intended to provide good exposure to machine vision technology with particular emphasis on real time applications in manufacturing Industry. A short introduction to computer vision, barcode reading, quality inspection, surface inspection, profile inspection and the methodology involved in the algorithm development will be presented in the sessions. Methods to select frame grabbers and other lens and lightings will be presented with hands-on models. Text recognition will be explained to enable the participant to understand and use these functions for designing machine vision applications. Thus the workshop introduces the participants to real time applications in the area of machine vision. Exercises and problems are planned to be included at the end of the each session for self-assessment. This workshop would serve as a learner’s guide for beginners as well as a reference guide for researchers. At the end of the program, the participant will be confident in program execution
Chair 1 : Prof. L.Priya, Industry Institute Interaction Cell, India

Dr.L.Priya received Ph.D. degree in computer vision from Anna University India.  She has 20 Years of teaching experience and been with Rajalakshmi Engineering College, India since June 2009. She has delivered invited talks in both academic institute and conducted practical training sessions to many leading industries in Chennai. She has received many awards which includes life time achievement award from Institute of Researchers, Kerala, India. She has chaired sessions and acted as reviewer for SCI indexed journals from Springer, Elsevier and Wiley Publications. She is currently in the editorial board of technical journals.  She has been engaged in teaching, research and consultancy and completed more than 20 consultancy projects in the area of quality control in Machine vision for the reputed companies in India. Being a Training co-ordinator in the centre of Excellence in Machine Vision at Rajalakshmi Engineering College she has conducted more than 70 Hands-on training programs in the area of Machine vision. She has published more than 50 research papers in reputed journals. She authored a book titled A Guide to quality control in machine vision with a publisher CRC Press Taylor and series. Her area of specialization includes Machine Vision, 3D object recognition, Digital Image Processing.

Chair 2 : Assoc. Prof. A.Sathya, Rajalakshmi Engineering College
Bio: Dr.A.Sathya, Associate Professor, Department of Information Technology ,Rajalakshmi Engineering College has 15 Years of teaching experience. She has undertaken and guided many social relevant project works. A patent has been filed in her name and authored book chapters in reputed publications like springer and Wiley. She published more than 25 papers in conferences and journals. Her area of interest includes Cloud security, Data Analytics. She is presently working on consultancy projects in the area of machine vision, image processing,web application, mobile application and cloud computing.

Chair 3 : Assist. Prof. K.Poornimathi, Rajalakshmi Engineering College
Bio: Ms.K.Poornimathi, Assistant Professor(SG), Department of CSBS ,Rajalakshmi Engineering College has 16 Years of teaching experience. She published more than 15 papers in conferences and journals. Her area of interest includes Deep learning, Image Processing,Machine Learning. She is presently working on consultancy projects in the area of machine vision, image processing, web application, mobile application and cloud computing.
Workshop 9:Face Image Reliability and Cognitive Analysis
Keywords: Face Anti-spoofing; Face Forgery Detection; Face Image Generation; Face Attribute Editing; Facial Expression Manipulation; Facial Expression Recognition; Facial Micro-Expression Recognition.

Summary: In recent years, the rapid development of artificial intelligence (AI) technology has also brought about the problem that AI technology may be abused. The current face image synthesis technology can create realistic virtual characters, which are likely to be utilized by criminals. In order to avoid the serious negative impact on social security and stability, the research of face image reliability is urgent. Besides, Facial expression analysis has attracted much attention in many human-computer interaction applications, especially facial micro-expression recognition. Furthermore, it is essential to investigate the relationship between face expression and cognitive psychology on mental health, which contributes to  provide a scientific measure of mental health improving. Therefore, we will mainly focus on the above aspects to research of the topic of "face image Reliability and cognitive analysis".
Chair : Prof. Lifang Zhou, Chongqing University of Posts and Telecommunications, China

Prof. Lifang Zhou has received a Ph.D. degree in Computer Science and Technology from Chongqing University. She worked as a professor at the school of Software Engineering, Chongqing University of Posts and Telecommunications. Her research interests include Face recognition, target detection and tracking, medical image segmentation. Lifang Zhou has published more than 30 papers on top international journals (TIFS, PR and TCSVT), authorized 13 Chinese Patents and published 2 monographs. She has received two best paper awards. Lifang Zhou has been an active volunteer in the China MM, ICCAI、PRMVIA conferences. She will serve as TPC chair for MVIPIT . Now she serves as the guest editor for Frontiers in Signal Processing about the research topic 'face image reliability and cognitive analysis'.

Workshop 10:AI in Near-Duplicate Video Retrieval
Keywords:  Information Retrieval, Web video, Artificial Intelligence, Big Data

Summary: The popularity of social networks and smartphones has led to an explosive growth in the number of videos, gradually replacing text as the main carrier of information exchange for ordinary users. Near-duplicate video retrieval aims to find the copies or transformations of the query video from a massive video database. It plays an important role in many video related applications, including copyright protection, tracing, filtering and etc. AI is crucial to any video retrieval system. This workshop aims to provide a platform to share current scientific and technical progress about AI in Near-Duplicate Video Retrieval.
Chair : Chengde Zhang, Zhongnan University of Economics and Law, China

CHENGDE ZHANG received the Ph.D. degree in Southwest Jiaotong University in 2015. From 2012 to 2013 he was a visiting scholar at the Department of Electrical and Computer Engineering (ECE), University of Miami (UM), USA. He is currently an associate professor in the School of Information and Safety Engineering, Zhongnan University of Economics and Law. His research interests include multimedia information retrieval, data mining, image processing and pattern recognition. He has published more than 40 SCI papers. He has received the supports from nearly 40 projects, including National Social Science Foundation Project, Ministry of Education Humanities and Social Sciences Fund Project, Major Project of Philosophy and Social Science Research in Higher Education Institutions in Hubei Province, etc.. He has received the Provincial Social Science Excellent Achievement Award and the Municipal Social Science Excellent Achievement Award. He is the Member of AAIA, IEEE and CCF.

Workshop 11: Multi-modal Image based Intelligent Perception
Keywords: Multi-modal image; Intelligent perception; Image fusion; Object detection

Summary: Thanks to the diversification of data acquisition, multimodal images, e.g., optical, infrared, hyperspectral and radar images, are available in most cases. Thus, complementary information from multiple perspectives is provided, which can improve the performance of traditional tasks. Yet, it raises a profound challenge to the integration and utilization of multimodal images at the same time. This workshop aims to provide a communication and sharing platform for those who are interested in multi-modal image processing and intelligent perception.
Chair 1 : Assoc. Prof. Wenda Zhao, Dalian University of Technology, China

Wenda Zhao received the B.S. degree in Jilin University, Changchun, China, in 2011, and the Ph.D. degree in Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun, China, in 2016. He now is an Associate Professor in Dalian University of Technology (DUT). His research interests are multimodal image fusion, object detection and recognition, etc. Now, he has published over 40 papers, including CVPR, ECCV, AAAI, as well as IEEE TPAMI, IEEE TIP, etc. He was awarded the IEEE MMTC best conference paper and ISAIR best student paper. He serves as a deputy secretary-general of the Intelligent Fusion Professional Committee of the Chinese Association for Artificial Intelligence, a member of the Youth Work Committee of the Chinese Association for Command and Control, and the Executive AC of the Vision and Learning SEminar (VALSE).

Chair 2 : Prof. Xiangzhi Bai, Beihang University, China
Xiangzhi Bai. He is currently a Full Professor with the Image Processing Center, Beihang University, where he is also with the State Key Laboratory of Virtual Reality Technology and Systems and the Beijing Advanced Innovation Center for Biomedical Engineering. He holds around 40 national invention patents and has published more than150 international journal and conference papers in the field of artificial intelligence, fuzzy theory, mathematical morphology, medical image analysis, and bioinformatics. He served as editor for 3 journals, and also acts as an active reviewer for around 100 international journals and conferences.

Chair 3 : Assoc. Prof. Yu Liu, Hefei University of Technology, China
Yu Liu received the B.S. degree and Ph. D degree from the Department of Automation, University of Science and Technology of China in 2011 and 2016, respectively. He is currently an associate professor in the Department of Biomedical Engineering at Hefei University of Technology. His research interests include image processing, computer vision and information fusion. In particular, He is interested in image fusion, image restoration, visual recognition and medical image analysis. He has published over 90 scientific articles in prestigious journals and conferences including IEEE TIP/TCSVT/TGRS/TIM/TCI/JBHI/SPL, ELSEVIER INFFUS/CBM/CMPB/JVCIR, etc. Among them, 13 journal articles have been identified as ESI Highly Cited Papers. His publications have received over 8000 citations (Google Scholar). He is serving as an Editorial Board Member for Information Fusion, and an Associate Editor for IEEE Signal Processing Letters. He was a recipient of the IEEE Instrumentation and Measurement Society Andi Chi Best Paper Award in 2020 and the IET Image Processing Premium (Best Paper) Award in 2017. He was identified as a Highly Cited Chinese Researcher by Elsevier (2020, 2021, 2022).

Chair 4 : Dr. Hui Li, Jiangnan University, China
Hui Li received the B.Sc. degree in School of Internet of Things Engineering from Jiangnan University, China, in 2015. He received the PhD degree at the School of Internet of Things Engineering, Jiangnan University, Wuxi, China, in 2022. He is currently a Lecturer at the School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China. His research interests include image fusion and multi-modal visual information processing. He has been chosen among the World's Top 2% Scientists ranking in the single recent year dataset published by Stanford University, Version 5, Nov 2022. He has published several scientific papers, including IEEE TPAMI, IEEE TIP, Information Fusion, IEEE TCYB, IEEE TIM, ICPR etc. He achieved top tracking performance in several competitions, including the VOT2020 RGBT challenge (ECCV20) and Anti-UAV challenge (ICCV21).
Workshop 12: Video image signal processing
Keywords: Super-resolution (SR); Image Encoding; Video Encoding; Image Processing; Multimedia Technologies

Summary: This workshop is mainly about the related technologies of multimedia video image processing, including video and image coding and decoding, super-resolution processing and image enhancement. Through video and image coding and decoding technology, the redundancy in time and space of information itself is eliminated, which greatly improves the storage and transmission of multimedia data. Through super resolution, image enhancement and other technologies, the image and video data are clearer and more detailed.
Chair : Assoc. Prof. Jianping Luo, College of Electronics and Information Engineering, Shenzhen University, China


He is an Associate Professor with the College of Electronics and Information Engineering, Shenzhen University. His research interests include theories and applications of Machine learning, Video signal process, Intelligent optimization algorithm, and Evolutionary computation.

Workshop 13: Visual Inspired Information Processing and Industrial Data Identification
Keywords: biological visual system, multi-source unstructured samples, industrial data identification

Summary: With the continuous developments of brain science and brain-like intelligence, neurobiology researches are constantly providing supports for the artificial intelligence systems. Current machine vision systems based on the artificial neural networks for multi-source unstructured samples have three problems. Firstly, in order to enhance the perception of complex data features, the mainstream models require massive training samples and deep structures. Yet the methodology is not consistent with the cognitive mechanism of the biological visual system, which leads to a significant increase of the computational complexity. Secondly, the network architecture operator merely works on the data with fixed adjacent relationships, thus it is difficult for the differentiable programming paradigms to effectively extract features on the multi-source unstructured samples with large distribution differences. Three research contents will be focused in this project, which are modeling and optimization of visual cortex information interaction mechanism under complex data, collaborative optimization modeling of visual cortex segmentation and topology under deep structure, identification method for multi-source unstructured samples based on information interaction and structure collaborative heuristic network. Consequently, we aim to solve the aforementioned two key scientific problems by building up differentiated programming frameworks to model the information and structural coordination regulation mechanism of the visual cortex in the brain.
Chair 1 : Assis. Prof. Bing Wei, Donghua University, China

Bing Wei is currently a Assistant Professor at College of Information Sciences and Technology, Donghua University, Shanghai, China. He obtained his Ph.D. degree in College of Information Sciences and Technology, Donghua University, Shanghai, China. He has been a Joint Ph.D. Student with the Department of Electrical, Computer, and Biomedical Engineering, University of Rhode Island, Kingston, RI, USA, from 2018 to 2019. He was a Postdoctoral Research Fellow with Fudan Univerity. His scientific interests include biological computing, deep learning, image processing and digitized textile technology. He has published over 40 articles in journals and conferences.

Chair 2 : Yudi Zhao, Shanghai Jiao Tong University, China
Yudi Zhao is currently a post-doctor at School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University. She received her Ph.D. degree in Control Science and Engineering from Donghua University, Shanghai, China, in 2022. She has been a Joint Ph.D. Student with the Department of Electrical, Computer, and Biomedical Engineering, University of Rhode Island, Kingston, RI, USA, from 2017 to 2020. Her scientific interests include deep learning, brain-inspired conpupting, artificial intelligence, and computer vision.

Workshop 14: AI in Computer Vision, Multimodal Data Analysis and AIGC
Keywords: Computer Vision, Multimodal Data, Deep Learning, Healthcare

Summary: We are honored to introduce the workshop of this conference, which focuses on computer vision, multimodal data, and AI generated content. The workshop welcomes academic experts to submit research papers related to the latest progress in computer vision, multimodal data, and AI generated content (AIGC). The aim of this workshop is to promote and advance key technologies and application studies in the field of artificial intelligence. 
The focus of this workshop will be on the following areas: 1) Computer Vision: Computer vision is a discipline that analyzes and understands digital images using computer and image processing technologies. This workshop will discuss how to improve the accuracy and efficiency of AI algorithms by applying computer vision technology. 2) Multimodal Data: With the use of various sensor technologies, we can obtain a large amount of multimodal data such as images, text, and sound. Experts will discuss how to use more advanced algorithms to process multimodal data and improve the generalizability of related research. 3) AI generated content: AI generated content refers to the use of artificial intelligence algorithms to generate text, images, and other forms of media. At this workshop, we will explore how to leverage AI generated content to improve and enhance computer vision or other research fields. 
In summary, we believe that this workshop will have a profound impact on related research fields and make a significant contribution to promoting the development of computer vision, multimodal data, and AI generated content research. We warmly welcome experts and researchers who are passionate about the field of artificial intelligence to actively submit papers or attend the workshop.
Chair 1 : Assoc. Prof. Wenjian Liu, City University of Macau, Macau S.A.R., China

Wenjian Liu is an esteemed academic who holds B.S., M.S., and Ph.D. degrees from the School of Electrical and Information Engineering, South China University of Technology, Guangzhou, China. He obtained these degrees in 1996, 2001, and 2010 respectively. Currently serving as an Associate Professor and Vice Dean of the Faculty of Data Science at the City University of Macau, his research is primarily focused on the areas of intelligent transportation, intelligent health, computer vision, and big data in psychology.

Chair 2 : Lumin Xing, The First Affiliated Hospital of Shandong First Medical University & Shandong Provincial Qianfoshan Hospital, Jinan, China
Xing Lumin obtained a PhD in Data Science from the City University of Macau. He is a Principal Senior Engineer in Big Data Systems Research and Development and a master's supervisor. His professional fields include data governance, smart healthcare, and intelligent transportation. He is also a certified expert in Google TensorFlow development. He has authored or co-authored more than a dozen papers in journals such as IEEE T Intell Transp, Adv Nano Res, and Eur Rev Med Pharmaco.

Workshop 15: Trustworthy Machine Learning in Medical Imaging
Keywords: Trustworthiness, Medical Imaging, Machine Learning, Transparency, Interpretability, Data Privacy, Image Quality, Malicious Attacks, Backdoor Designs, Quality Assurance, Security.

Summary: In this workshop, we delve into the crucial theme of "Trustworthy Machine Learning in Medical Imaging". As we incorporate machine learning methodologies extensively into medical imaging, ensuring their dependability and safety becomes paramount. We will engage in in-depth discussions encompassing several sub-fields of this subject matter. We will delve into the transparency and interpretability of machine learning algorithms, discussing how to make these complex systems more understandable and accountable. We will explore the methods and techniques to ensure data privacy, confronting challenges that arise from using patient-sensitive data in machine learning models. 
Quality assurance in medical imaging is another critical area of focus. We will evaluate how to maintain and enhance the quality of medical images used for training and validating machine learning models, addressing the impact of image quality on model performance. We will also tackle the critical issue of security in machine learning, focusing on potential threats like malicious attacks and backdoor designs that may compromise the model's integrity and performance. We will discuss the latest research and mitigation strategies to safeguard these models from such threats. The workshop aims to foster interdisciplinary dialogue, encouraging the development and implementation of safer, more efficient, and reliable machine learning solutions in medical imaging. We look forward to your participation as we strive to catalyze progress in this pivotal field.
Chair : Assoc. Prof. Xin Xie, Hunan University of Information Technology, China

Communication Committee Member of the Young Teachers Working Committee of the National Higher Education Computer Education Research Association, member of the Guangdong Provincial Department of Science and Technology Review Expert Database, key teacher in Hunan Province, and leader of the Excellent Ideological and Political Teaching Team in Hunan Province. 
I have presided over and completed one Hunan Provincial Natural Science Foundation project and one key scientific research project in Hunan Province. I have participated in the completion of two National Natural Science Foundation Youth Projects, one National Natural Science Foundation project, and one Hunan Provincial Natural Science Foundation (Science and Education Joint Fund Project). I have published one SCI paper as the first author, four EI papers, a total of eight papers in Chinese core and scientific and technological core, and have obtained four software copyrights. I have won one second prize for scientific and technological progress in Henan Province (ranked 10th), one second prize for ideological and political teaching in Hunan Province, and one second prize in classroom teaching competition. Main research directions are trustworthy machine learning and software security.
Workshop 16: Multimodal Medical Imaging and Image Analysis
Keywords: medical image analysis ; machine learning; data fusion; multi-fidelity methods; multi-source learning

Summary: Workshop on Multimodal Medical Imaging and Image Analysis aims at tackling the important challenge of acquiring and analyzing medical images at multiple scales and/or from multiple modalities, which has been increasingly applied in research studies and clinical practice. Include, but not limited to: 1) techniques involving multi-modal image acquisition and reconstruction, or imaging at multi-scales; 2) novel methodologies and insights of multiscale multimodal medical images analysis, including image fusing, multimodal augmentation, and joint inference; and 3) empirical studies involving the application of multiscale multimodal imaging for clinical use.
Chair : Assoc. Prof. Chang Qing, East China University of Science and Technology, China

Qing CHANG received the BS and the MS degree in Automatic Control,and PhD degree in Navigation, guidance, and control from Northwestern Polytechnic University (NWPU), in1997,2000 and 2003. She is an Associate Professor from East China University of Science and Technology Shanghai, China. Her research interests include medical imaging and recognition, biomedical image analysis, with an emphasis on computational modeling of high-level vision.
Workshop 17: Deep Learning in Computer Vision and Multimodal AI
Keywords: Deep Learning, Computer Vision, Multimodal AI, Image Processing

Introduction
The workshop on "Deep Learning for Computer Vision and Multimodal Artificial Intelligence" aims to bring together researchers, practitioners, and industry experts from around the world to discuss recent developments and practical applications of deep learning techniques in computer vision and multimodal AI. 
Workshop Themes
The workshop will cover a range of topics related to deep learning in computer vision and multimodal AI, including (but not limited to):
  • Deep learning models for image classification, object detection and segmentation, and image synthesis 
  • Multimodal fusion techniques for combining information from different modalities such as text, audio, and video 
  • of deep learning in healthcare, autonomous vehicles, robotics, and other domains 
  • Interpretability and explainability of deep learning models 
  • Challenges and future directions for deep learning in computer vision and multimodal AI
Conclusion
We believe that the workshop on "Deep Learning for Computer Vision and Multimodal Artificial Intelligence" will provide a valuable forum for researchers and practitioners to share their experiences and insights in applying deep learning techniques to computer vision and multimodal AI tasks. We look forward to welcoming attendees from around the world to participate in this exciting event!
Chair : Assoc. Prof. Yuantao Chen, Hunan University of Information and Technology, China

Yuantao Chen received the B.S. degree in Computer Science and Technology from Jianghan Petroleum Institute. He received the M.S. degree in Geodetection and Information Technology from Yangtze University. He received the Ph.D. degree in Control Science and Engineering from Nanjing University of Science and Technology, Nanjing, China, in 2014. He is an associate professor at Hunan University of Information Technology. His research interests include pattern recognition, image processing, deep learning, computer vision, etc. He has published several scientific papers, including JVCIR, TVCJ, JMLC, JKSU-CIS, JAIHC, Applied Intelligence, MTAP etc.
Workshop 18:Understanding Intention with Multi-modal Data in Human Machine Interaction
Keywords: intentional and video understanding; posture estimation; multi-modal learning

Summary
Understanding intention is one of the cutting-edge types of research in human-computer interaction. Simultaneously, there is an urgent need for multi-modal data analysis in human-machine scenes to understand the semantics in an interactive dialogue with posture estimation. Focusing on human-computer interaction and dealing with deep learning methods, the workshop collects related works about intentional and video understanding, posture estimation, and multi-modal learning.

Chair : Dr. Cong Shen, Tianjin University of Technology, China

Dr. Cong Shen obtained his Ph.D. degree from Tianjin University in 2019. He is currently a lecturer and a master's supervisor at the School of Computer Science and Engineering at Tianjin University of Technology. His interests include theoretical computers, bioinformatics, and computer vision. He is currently hosting a National Natural Science Foundation Project. He is a member of CCF and IEEE.
Workshop 19:Robot Vision
Keywords: Robotics, Vision , Learning, Information System, Computer Vision

Summary
Welcome to the fascinating world of Robot Vision! This workshop is designed to immerse you in the cutting-edge field of computer vision and its application to robotics. In this rapidly advancing technological era, robots equipped with visual perception capabilities have become increasingly prevalent and are revolutionizing various industries, from manufacturing to healthcare, and from autonomous vehicles to space exploration.
Workshop Overview:
During this workshop, we will explore the fundamental concepts, techniques, and challenges related to Robot Vision. Whether you're a student, researcher, engineer, or simply curious about the field, this workshop offers something for everyone, from the basics to the latest breakthroughs.
Why Robot Vision Matters:
Robot Vision is a crucial aspect of robotics, enabling machines to perceive and interpret the world through visual data, just like humans. By mimicking human visual capabilities, robots become more versatile, adaptive, and capable of interacting with their environments effectively. This opens up a multitude of possibilities for automation, remote sensing, and intelligent decision-making.
What You'll Learn:
Throughout this workshop, you will gain an in-depth understanding of the following key topics:

oImage Processing.

oComputer Vision Algorithms.

oCamera Calibration.

oDeep Learning for Robot Vision.

o3D Vision.

oRobot Navigation and Mapping.

oApplications and Real-World Use Cases.

oHands-on Experience.

This workshop is designed to be interactive and practical. You will have the opportunity to work on coding exercises, implement computer vision algorithms, and experiment with robotic simulations to reinforce your understanding.


Chair 1: Dr. Asif Khan,  Faculty of Engineering and IT

Dr ASIF KHAN (Member, IEEE)  received the B.Sc. (Hons.) and M.C.A. (Master of Computer Science and Application) degrees from Aligarh Muslim University, India, and the Ph.D. degree (Hons.) in computer science and technology from the University of Electronic Science and Technology of China (UESTC), China, in 2016. He was an Adjunct Faculty with the University of Bridgeport, USA, for China Program in summer 2016. Previously, He was a Visiting Scholar for Big data Mining and Application at the Chongqing Institute of Green and Intelligent Technology (CIGIT), Chinese Academy of Sciences, Chongqing, China. He done Postdoctoral Scientific Research Fellow with UESTC. He is also holding a position of Assistant Professor with Integral University, India. He is a Contributor to many international journals with robotics and vision analyses about the contemporary world in his articles. His interests include machine learning, robotics vision, and new ideas regarding vision based information critical theoretical research. He awarded by UESTC Academic Achievement Award and Excellent Performance Award, from 2015 to 2016.

Chair 2: Dr. Sarosh Patel, University of Bridgeport


Workshop 20:SATELLITE IMAGE ANALYSIS AND CLASSIFICATION USING DEEP LEARNING TECHNIQUES
Keywords: Remote sensing, Image classification, Deep learning, Preprocessing, Feature Fusion
Summary
Recently, remote sensing image (RSI) classification becomes a difficult task, which aims to determine the images depending upon the entities find useful for various application areas such as urban planning, land resource management, disaster management, traffic surveillance, etc. The latest advances of the deep learning (DL) models have gained significant attention on RSI classification. Due to the familiarity of the convolution neural network (CNN) in the image processing communities, several CNN based approaches have been developed to classify the RSI. In this aspect, this study designs a novel deep learning based feature fusion model for RSI analysis, named DLFF-RSI technique. The proposed DLFF-RSI technique involves pre-processing to improve the quality of the RSI in three different ways namely Gaussian filtering based noise elimination, contrast enhancement, and data augmentation. Besides, two DL based models namely Inception v3 and Densely Connected Networks (DenseNet201) are employed for feature extraction process. Finally, two feature vectors are fused together to raise the overall performance of the proposed model. In order to demonstrate the improved performance of the DLFF-RSI technique, a wide-ranging of simulations take place on benchmark datasets and the results reported the improvements of the DLFF-RSI approach compared to other approaches


Chair 1: Dr. Vijay R Rathod, PhD IIT ROORKEE

 An IITian Aged 49 years, having 23 years of teaching experience Out of which 12 years are in one of the top college as Professor & Head , Dept of Electronics & Telecommunications St Xavier’s Technical Institute( Govt aided & Autonomous Institute) with proven operational and administrative capabilities. Joined as on lien approved Principal at G H Raisoni college of engineering and management Amravati now become G H Raisoni University taken the charge of Vc and Dean faculties of science & technology I am a man of amicable nature and polished habits aged 29 years, a workaholic and go-getter who believe in achieving goals and growing in life with the growth of organization. Stability in job is priority with good working environment and areas to prove my capabilities. Curriculum Development, structure design & contact Strategic Planning Critical thinking, Innovation and Inventions Best practices in teaching learning process Quality assurance in Teaching learning process Examination and Evaluation process. Research and Development program Implementation of Learning management systems Faculty Recruitment, training and Faculty Recharge program Development of inclusive learning environment International collaborations, Faculty and students Exchange program Employability enhancement program Entrepreneurship development program Experiential Learning & Participative Learning ABET & IET Accreditation Experience


Chair 2: Vaishnavee Rathod, Department of Computer Science Engineering SVNIT SURAT GUJARAT

Completed B.E. in Electronics & Telecommunication from Thakur college of Engineering Mumbai.INDIA MTECH in Electronics & Telecommunication from GHRIET NAGPUR INDIA Research Scholar Pursuing PhD in Remote Sensing Image Analysis at SVNIT SURAT Received Best paper award for feature extraction and classification of biomedical images.

Workshop 21:Advancements in Artificial Intelligence for Healthcare and Computer Vision: From Medical Imaging to Object Detection and Content-Based Recommendation Systems
Keywords: Artificial intelligence, healthcare, medical imaging, Image/Video object detection or classification, content-based recommendation systems, automated identification, localization, Saliency detection, recommendations,
Introduction:
The healthcare field has witnessed significant advancements in recent years, thanks to the rapid progress in artificial intelligence (AI) technologies. AI has shown immense potential in revolutionizing healthcare and computer vision practices, from medical imaging to object detection and content-based recommendation systems. This summary explores the workshop's theme, which focuses on AI's latest developments and applications in healthcare and computer vision, encompassing medical imaging, object detection, and content-based recommendation systems.
Workshop Theme:
The workshop aims to bring together researchers, practitioners, and industry experts to delve into the advancements in AI for healthcare and computer vision, especially in deep learning. The first focus area is medical imaging, where AI algorithms have dramatically improved disease detection and classification accuracy and efficiency. By leveraging AI techniques, medical professionals can obtain more precise diagnoses, leading to better treatment outcomes. The second theme revolves around object detection, Salient object detection, where AI algorithms enable automated identification and localization of objects of interest in images and videos. This has immense implications for healthcare and robotic visions, streamlining processes and enhancing decision-making. Lastly, the workshop explores content-based recommendation systems leveraging AI to provide personalized and relevant recommendations for healthcare and computer vision interventions and treatment plans. Healthcare and computer vision professionals can offer tailored and evidence-based recommendations by combining patient data with AI algorithms.
Conclusion:
The workshop on "Advancements in Artificial Intelligence for Healthcare and computer vision: From Medical Imaging to Object Detection and Content-Based Recommendation Systems" serves as a platform for collaboration and knowledge exchange among experts in the field. By exploring the latest developments and applications of AI in healthcare and computer vision, including medical imaging, object detection, saliency detection, and content-based recommendation systems, the workshop aims to accelerate the adoption of AI technologies, ultimately improving patient outcomes and revolutionizing healthcare practices. Participants can expect insightful discussions, sharing of best practices, and exploration of future directions in this rapidly evolving field.

Chair 1 : Dr Inam Ullah   Shandong Jianzhu University, Jinan, China

Dr Inam Ullah received his Ph.D. from the School of Computer Science & Technology, Shandong University, Jinan, China, in 2021. He received his bachelor's degree from the University of Peshawar, Pakistan, and his master's from the International Islamic University of Islamabad, Pakistan. He was a visiting Teacher at  Islamia Collage University Peshawar, Pakistan. He was a lecturer at Sheikh Zaid Islamic Center, University of Peshawar, Pakistan.
He works as an assistant professor at Shandong Jianzhu University, China. He is a Contributor to many international journals with robotics and computer vision analyses about the contemporary world in his articles. He is a reviewer in many well-reputed international journals. He is also a member of the IEEE and the Chinese Association for Artificial Intelligence (CAAI).
His current research interests include image processing, computer vision, machine learning, deep learning, salient object detection, medical imaging, object detection and classification, recommendation system, and biometric recognition.

Chair 2 :  Dr Yuling Ma, Shandong Jianzhu University, Jinan, China
Dr Yuling Ma received the B.Sc., M.Sc., and Ph.D. degrees in computer science from Shandong University, China in 2003, 2008, and 2020, respectively. She is currently an associate professor with the School of Computer Science and Technology, Shandong Jianzhu University, China. She has published in numerous reputable journals and has served as a reviewer for multiple journals. She is also a member of prestigious organizations such as CAAI. Her research interests include machine learning and educational data mining.

Chair 3 :Dr Zafar Ali, Southeast University, Nanjing, China
Dr. Zafar Ali received his M.Sc. degree in computer science (2011) from university of Peshawar.  Then he completed his MS degree (2017) in web engineering from the same university. Recently, Zafar Ali has completed his Ph.D. degree in the field of Computer Science and Engineering from the Southeast University, China. He is currently working as a postdoctoral fellow in the School of Computer Science and Engineering, Southeast University, China. He has published more than thirty research papers in reputed conferences and SCI journals. He is reviewer in different prestigious journals and conferences including Knowledge-based systems, AI Review, Information Fusion, Scientometrics, Soft Computing, IEEE Access, Information Processing & Management and CIKM. His research interests include recommender systems, information retrieval, natural language processing, graph embedding, deep learning, and machine learning.

Workshop 22: Image Processing, Machine Learning and Deep Learning In Machine Vision
Keywords: Image processing, machine learning, deep learning, machine vision

Introduction: The workshop on "Image Processing、Machine Learning and Deep Learning In Machine Vision" aims to bring together researchers, practitioners, and industry experts from around the world to discuss recent developments and practical applications of techniques in Machine Vision.

Workshop themes: This workshop will cover a series of topics related to computer vision, including (but not limited to) the following: Industrial and Automation Applications of Computer Vision: Introducing real-world use cases of machine vision technology in industrial production, quality control, and automation fields. Participants will learn how computer vision enhances productivity, reduces costs, and ensures product quality.

Medical and Life Science Applications of Computer Vision: Discussing the latest research and applications in medical image processing, disease diagnosis, cell analysis, and related areas. Participants will understand the significant role of computer vision in the medical domain and its support for clinical decision-making. 
Applications of Computer Vision in Intelligent Transportation and Security: Exploring applications of computer vision in traffic monitoring, pedestrian recognition, vehicle detection, and other intelligent transportation and security aspects. Participants will learn how machine vision technology can enhance traffic management and safety performance. 
The goal of this workshop is to promote exchange and collaboration among participants, inspire new ideas and research directions, and drive the practical applications and development of computer vision in various domains. We cordially invite experts, scholars, and practitioners from all fields to join us and together advance and innovate the field of computer vision technology.


Chair : REN FEI, Nanjing Intelligent Transportation Information Co., Ltd./Nanjing Institute of Technology

Ren Fei, deputy director/technical expert of Nanjing Smart Transportation engineering Technology Research Center, and a python senior development engineer certified by the Ministry of Industry and Information Technology, has published more than 10 papers at home and abroad, published and authorized nearly 30 patents, and won more than 10 national and provincial competitions. He used to be the general manager of Nanjing Supercontrol Electronics and the technical director of Sinoma Mining Research Institute. He is now an off campus tutor of university graduate students in Nanjing , a member of Baidu PaddlePaddle Doctor Association, a member of Baidu Deep Learning PaddlePaddle Developers Experts (PPDE), a member of the editorial board of American journals and Hong Kong journals, a peer reviewer of SCI journals, a peer reviewer of the second international conference on network, communication and information technology, and the second automation, a peer reviewer of International Academic conference on Control and Telecommunications engineering; a peer reviewer of the 7th International Academic Conference on Economics and Enterprise Management, IEEE Member, IEEE Computer Society Member,a member of the Chinese Artificial Intelligence Society, and a member of the Jiangsu Provincial Artificial Intelligence Society. Published one monograph.