Prof. Xiaogang Jin
State Key Lab of CAD&CG, Zhejiang University, China
Bio:Xiaogang Jin is currently a Professor of the State Key Lab of CAD&CG, Zhejiang University, China. He received his Ph.D. degree from Zhejiang University in 1995. His current research interests include computer animation, computer graphics, computer-aided design, and artificial intelligence. He has published over 200 journal and conference papers including ACM TOG, IEEE TVCG, IEEE TIP, IEEE TNNLS, Siggraph, Siggraph Asia, CVPR, ICCV, ECCV, AAAI and ACM MM, etc. He received the First Class Prize of National Award for Natural Sciences in Universities in 2008, and the Scientific and Technological Award of Zhejiang Province (Second Prize) in 2017. He received an ACM Recognition of Service Award in 2015, and the Best Paper Award from CASA 2017 and CASA 2018. He is a distinguished Member of CCF.
Title: Digital Human Modeling and Animation and Their Metaverse Applications
Abstract: In recent years, digital humans have become a prominent research topic, and they may be found in a wide range of applications such as animation, digital entertainment, clothing design, virtual customer service, gaming, virtual assistants, and metaverse. In this talk, I will present some of the most recent findings from my research group in digital face modeling and editing, human motion neural solvers, human motion transition, neural clothing animation, and their applications. Style 3D will also be introduced as a fashion metaverse application of an industrial implementation case of digital garment design and animation.
Nanjing University of Science and Technology, China
Bio: Xiangbo Shu is currently a Professor at the School of Computer Science and Engineering, Nanjing University of Science and Technology, China. He received his Ph.D. degree from Nanjing University of Science and Technology, in 2016. From 2014 to 2015, he worked as a visiting scholar at the National University of Singapore, Singapore. His current research interests include Computer Vision, and Multimedia. He has authored over 90 journal and conference papers in these areas, including IEEE TPAMI, IEEE TNNLS, IEEE TIP, CVPR, ICCV, ECCV, and ACM MM, etc. He has received the Best Student Paper Award in MMM 2016, and the Best Paper Runner-up in ACM MM 2015. He is also the Senior Member of CCF, the Member of ACM, and the Senior Member of IEEE. He is also severed as Associate Editor of IEEE TCSVT, Information Sciences, and The Visual Computer.
Title:Human Action Intelligent Understanding in Videos
Abstract：Video data continues to show explosive growth in the network and physical space, human action understanding is the main object of video content understanding, as well as one of the core technology requirements in human-computer interaction, security monitoring, virtual reality and other fields. In many realistic scenarios, the performance and reliability of human action understanding models need to be improved due to the limitation of data size, lack of training data, and attack of data. Based on this, this report will explore the human action understanding in open scenarios with limited labeled data, focusing on: Spatiotemporal co-attention representation learning, data augmentation and representation learning, multi-granularity contrastive representation learning, pyramid self-supervised polymerization learning, and attack-augment representation learning, which can be applied to solve human behavior prediction and recognition tasks in semi/unsupervised scenarios.
Prof. Qiang Chen
Nanjing University of Science and Technology, China
Bio: Qiang Chen received his doctoral degree from Nanjing University of Science and Technology and completed his postdoctoral research at Stanford University. He is a professor and doctoral supervisor at the School of Computer Science and Engineering/Artificial Intelligence Institute at Nanjing University of Science and Technology. He is a Senior Member of CCF and an editorial board member of "Frontiers in Medicine" and "Journal of Image and Graphics". He has served as an excellent reviewer for several journals such as Transactions on Medical Imaging and Acta Automatica. His research work mainly focuses on image processing, computer vision, and pattern recognition. He has published over a hundred papers in journals and conferences including MedIA, TMI, Ophthalmology, and MICCAI. and his publications have received over 3500 citations on Google Scholar. He has also been granted more than twenty national patents.
Qiang Chen has been honored with the Second Prize of Jiangsu Science and Technology Award (ranked 2nd), the title of "333 Project" Talents in Jiangsu Province, the title of Excellent Young Backbone Teacher in Jiangsu Province Qinglan Project, and the Jiangsu Province Six Talent Peaks Award.
Title:Assisted analysis of ophthalmology based on image generation
Abstract:The main challenges of the intelligent analysis of medical images include low image quality, high cost of image annotation and acquisition of different modalities, difficulty in obtaining rare cases and temporal data, and data privacy protection. This presentation focuses on these challenges and provides preliminary solutions for ophthalmic assistive analysis based on image generation techniques. Specifically, it includes the reconstruction and segmentation of retinal blood vessels using labeled-to-image generation for optical coherence tomography angiography (OCTA), cross-device OCTA generation, segmentation of retinal branch vein occlusion using CFP-FFA-based generation, segmentation of retinal edema regions based on anomaly detection, and generation of temporal images.
Prof. Chunquan Li
Nanchang University, China
Bio: Chunquan Li received his Ph.D. from Nanchang University in 2014. He is currently a Professor, Ganjiang Distinguished Professor, and Deputy Director of Jiangxi Provincial Key Laboratory of Intelligent Information System, School of Information Engineering, Nanchang University, Nanchang, China. He was also a a Visiting Professor with the Department of Systems and Computer Engi neering, Carleton University, Ottawa, ON, Canada.
Prof. Li’s research interests include Haptics interaction, virtual surgery, teleoperation robots, intelligent human-machine interaction, computational intelligence, and their applications to biomedical engineering and human-machine interaction. He has published more than 50 publications in international journals like IEEE Transactions on Fuzzy Systems, IEEE Transactions on Industrial Informatics, IEEE Transactions on Cybernetics, IEEE Transactions on Affective Computing, IEEE Transactions on Intelligent Transportation Systems, IEEE-ASME Transactions on Mechatronics, IEEE Transactions on Instrumentation and Measurement, IEEE Transactions on Human-Machine Systems, IEEE Transactions on Cognitive and Developmental Systems etc., and serves as reviewers for several top international journals and conferences.
He has received various awards: Baogang National Excellent Teacher Award, IEEE Third Prize in "Online Data Driven Optimization" , the second prize of Jiangxi science and technology progress, etc.
Copyright© ICMLCA 2023
2023 4th International Conference on Machine Learning and Computer Application（ICMLCA 2023） http://icmlca.org/