Mu-ming Poo
Member of Chinese Academy of Sciences
Bio: Mu-ming Poo is the director of Institute of Neuroscience, Chinese Academy of Sciences, and Shanghai Center for Brain Science and Brain-Inspired Technology. He is a member of Chinese Academy of Sciences, Academia Sinica, and Hong Kong Academy of Science, and an international member of US National Academy of Sciences. He has received Docteur Honoris Causa from Ecole Normale Supérieure, Claude Bernard University of Lyon，Hong Kong University of Science and Technology, and Claude, and Ameritec Prize，P. R. China International Science and Technology Cooperation Award, Qiushi Distinguished Scientist Award, and Gruber Neuroscience Prize. He currently serves as an editorial board member of many international prestigious journals, such as Neuron, and the executive editor-in-chief of National Science Review. He is also a member of Scientific Advisory Committee of many international institutes such as Queensland Brain Institute.
Title:
Abstract:
Wen Gao
Member of Chinese Academy of Engineering
Bio: Wen Gao is now a member of the Chinese Academy of Engineering, Director of Pengcheng Laboratory, Peking University Boya Chair Professor, IEEE Fellow and ACM Fellow. He once won the first prize of National Technological Invention Award, and once won the second prize of National Technological Invention Award, and five times won the second prize of National Scientific and Technological Progress Award. He also won the title of "2005 China's Top Ten Educational Talents" and the Wang Xuan Award of China Computer Society. He is mainly engaged in areas of artificial intelligence application and multimedia technology, computer vision, pattern recognition and image processing, and virtual reality. His major publications include "Principles of Digital Video Coding Technology", "Advanced Video Coding Systems", etc. He has published more than 200 papers in international journals and more than 600 papers in international conferences.
Title:
Abstract:
Yaonan Wang
Member of Chinese Academy of Engineering
Bio: Yaonan Wang is an Academician of Chinese Academy, and an expert in robotic and intelligence control. He is serving as a professor of Hunan University and the director of RVC-National Engineering Lab. He is currently a CAA Fellow ( Chinese Association of Automation ), a CCF Fellow ( Chinese Computer Federation Fellow) and a CAAI Fellow (Chinese Association for Artificial Intelligence Fellow). He is also the chairman of the council of Chinses Society of Image and Graphics (CSIG), the vice chairman of the council of China Artificial Intelligence Robot Industry Alliance, a standing member of the council of CAA, a member of the supervisor board of CAAI, a member of the executive committee of Artificial Intelligence and Block Chain Technology in Ministry of Education, and the chairman of the council of Hunan Association of Automation. He was the specialist in intelligent robot area of "863 Plan", and the chief scientist of EU Fifth Framework International Cooperation Major Project.He has long been engaged in research and teaching work of robot perception, control technology and engineering application. He won 1 second prize of the National Technological Invention Award, 3 second prizes of the National Science and Technology Progress Award, and 11 first prizes of the provincial /ministerial level award. Moreover, he has published more than 200 papers indexed by SCI, published 15 scientific books, and obtained more than 80 invention parents. He was also selected as a German Humboldt Scholar. Additionally, he has cultivated more than 70 doctoral students, and won the honorary titles of outstanding backbone teachers of national colleges and universities, national May 1st labor medal, national advanced worker, national innovation competition award, and advanced individual in fighting against the covid-19 in Hunan Province.
Title: 机器视觉高光谱检测技术应用与发展趋势
Abstract: 机器视觉感知作为机器人的“高精密眼睛”，其发展对机器人起着重要的作用。高光谱机器视觉感知具备多模态成像系统与智能分析识别功能，是当前机器视觉领域的研究前沿。报告将从研究背景与意义、研究现状与面临挑战、关键技术等方面介绍高光谱机器视觉感知技术应用。首先，以智能机器人在高端制造过程中面临的感知手段有限、测量检测精度低、缺陷样本数量少等挑战为牵引，介绍了高光谱机器视觉研究的总体技术路线与关键科学问题，包括高速高精快照式成像、无监督异常检测方法、跨场景模型部署等方面；最后介绍了高光谱机器视觉未来的发展趋势与展望。
Yirong Wu
Member of Chinese Academy of Sciences
Bio: 吴一戎，中国科学院院士，现任中国科学院空天信息创新研究院院长、中国科学院大学电子电气与通信工程学院院长，担任国务院学科评议组信息与通信工程学科召集人，高等学校教学指导委员会电子信息类专业教学指导委员会副主任委员。长期从事微波成像技术以及大型遥感地面处理系统的设计和研制，推动国家航空遥感系统的发展。微波成像领域，发明了多维度微波成像技术和稀疏微波成像技术。遥感卫星地面处理与应用系统领域，解决了一系列理论问题与关键技术，提高了我国在该领域的技术水平。主持了国家航空遥感系统的建设，推动了一系列国际领先的航空对地观测载荷的发展。曾获得国家科技进步一等奖、二等奖，全国创新争先奖，国防科技工业杰出人才奖，陈嘉庚科学奖，何梁何利科技进步奖等奖项。
Title:
Abstract:
Hong Qiao
Member of Chinese Academy of Sciences
Bio: Hong Qiao is a member of the Chinese Academy of Sciences and a Professor of the Institute of Automation, Chinese Academy of Sciences. She serves as a deputy director of the State Key Laboratory of Management and Control for Complex Systems (SKL-MCCS) and a deputy director of the Central Science and Technology Committee of Jiusan Society, and established the Beijing Key Laboratory of Robot "Hand-Eye-Brain" Integrated Intelligence Research and Application. She has been engaged in robot theory and application and has made systematic and creative contributions to human-inspired robot decision-making, perception, control, and structure design. She won the second prize of the National Natural Science Award, the first prize of Beijing Science and Technology, and the first prize of Technological Invention of the Chinese Association of Automation, and ranked first for all awards. She was elected from mainland China for the first time and was reappointed as a member of the Administrative Committee of IEEE Robotics and Automation Society. She served as a member of IEEE Fellow Committee (2022), IEEE Awards Committee (2020, 2021), IEEE Robot Pioneer Award Selection Committee (2021), IEEE Robot and Automation Society Fellow Nomination Committee (2022), etc. She was invited to serve as Editor-in-Chief and Editor for many SCI journals.
Title:
Abstract:
Kyoung Mu Lee
Editor in Chief of the IEEE TPAMI
Bio: KYOUNG MU LEE (Fellow, IEEE) is currently the Editor in Chief of the IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (TPAMI); He received the B.S. and M.S. degrees in control and instrumentation engineering from Seoul National University (SNU), Seoul, South Korea, in 1984 and 1986, respectively, and the Ph.D. degree in electrical engineering from the University of Southern California, in 1993. He is the director of the Interdisciplinary Graduate Program in Artificial Intelligence at SNU. He is an Advisory Board Member of the Computer Vision Foundation (CVF). He was a Distinguished Lecturer of the Asia-Pacific Signal and Information Processing Association (APSIPA), from 2012 to 2013. He has received several awards, in particular, the Medal of Merit and the Scientist of Engineers of the Month Award from the Korean Government, in 2018 and 2020, respectively; the Most Influential Paper Over the Decade Award by the IAPR Machine Vision Application, in 2009; the ACCV Honorable Mention Award, in 2007; the Okawa Foundation Research Grant Award, in 2006; the Distinguished Professor Award from the College of Engineering of SNU, in 2009; and the SNU Excellence in Research Award in 2020. He has also served as a General Chair for ICCV2019, ACMMM2018, and ACCV2018; a Program Chair for ACCV2012; a Track Chair for ICPR2020 and ICPR2012; and an Area Chair for CVPR, ICCV, and ECCV many times. He has served as an Associate Editor-in-Chief (AEIC) and an Associate Editor for the Machine Vision and Application (MVA) journal, the IPSJ Transactions on Computer Vision and Applications (CVA), and the IEEE SIGNAL PROCESSING LETTERS (SPL); and an Area Editor for the Computer Vision and Image Understanding (CVIU). He is the founding member and served as the President of the Korean Computer Vision Society (KCVS). Prof. Lee is a Fellow of IEEE, a member of the Korean Academy of Science and Technology (KAST) and the National Academy of Engineering of Korea (NAEK).
Title: Toward Real-World Image Super-Resolution: Challenges and Approaches
Abstract: Image Super Resolution (SR) which aims to reconstruct a high-resolution (HR) image from a low-resolution (LR) input, plays an essential role in computer vision, digital photography, and many real applications. Recently, a plethora of SR methods have been developed based on deep CNNs and large-scale datasets. However, most of the state-of-the-art methods still do not generalize well to real-world scenarios even though they perform relatively well on public benchmarks. In this talk, we will address some of the technical issues and challenges in the real-world SR problem including the domain gap, arbitrary scale transformation, and real-time processing issues. And then we introduce new approaches to tackle these challenges by learning unknown real down-sampling process via GAN with new effective losses, allowing generalized Image SR under arbitrary transformation, and optimizing the network structures via adaptive quantization and pruning. We empirically demonstrate that our new strategie
Zhengyou Zhang
Director of AI Lab and Robotics X, Tencent
Bio: Dr. Zhengyou Zhang is currently serving as Director of AI Lab and Robotics X, Tencent, and he is the first T17 distinguished Scientist in Tencent. He is an ACM Fellow (Association for Computing Machinery Fellow) and an IEEE Fellow (Institute of Electrical and Electronics Engineers Fellow), He is also a world-renowned expert in computer vision, multimedia technology, stereo vision, motion analysis, camera calibration, robot navigation, immersive remote interaction. He has published more than 250 papers in top international conferences and journals, which have been cited more than 55,000 times, and he holds nearly 200 issued patents. He received the IEEE Helmholtz Test of Time Award in 2013 for his “Zhang’s method”.
Title: 虚实集成世界里的数字人和机器人
Abstract: 随着AI、VR、AR、XR等数字技术的飞速发展，以及几乎无处不在的移动宽带互联网的覆盖，我们正在进入一个虚实集成世界（Integrated Physical-Digital World，IPhD），也即虚拟世界(数字世界)与真实世界(物理世界)的紧密结合。 虚实集成世界(IPhD)需要具有四大关键技术：现实虚拟化、虚拟真实化、全息互联网、智能执行体。互联网将以更快的速度和更宽的带宽继续发展，最终将能够传输包括 3D 形状、外观、空间音频、触觉和气味在内的全息内容。智能执行体，例如智能数字人(虚拟人)和数字/物理机器人，在数字世界和物理世界之间穿梭。在本次演讲中，我们将描述这个虚实集成世界需要的两大关键领域，数字人和机器人。数字人技术包括3D建模，口型驱动，肢体驱动，TTS(语音合成)，文本理解和生成，游戏解说等。机器人技术包括A2G理论 (AI, Body, Control, Developmental learning, Emotional intelligence, Flexible Manipulation, Guardian angel)，以及在此理论指导下我们的进展。
Alan Yuille
Bloomberg Distinguished Professor of Cognitive Science and Computer Science at Johns Hopkins University
Bio: Prof Alan Yuille is a Bloomberg Distinguished Professor of Cognitive Science and Computer Science at Johns Hopkins University. He directs the research group on Compositional Cognition, Vision, and Learning. He is affiliated with the Center for Brains, Minds and Machines, and the NSF Expedition in Computing, Visual Cortex On Silicon. Alan Yuille received the BA degree in mathematics from the University of Cambridge in 1976. His PhD on theoretical physics, supervised by Prof. S.W. Hawking, was approved in 1981. He was a research scientist in the Artificial Intelligence Laboratory at MIT and the Division of Applied Sciences at Harvard University from 1982 to 1988. He served as an assistant and associate professor at Harvard until 1996. He was a senior research scientist at the Smith-Kettlewell Eye Research Institute from 1996 to 2002. He was a full professor of Statistics at the University of California, Los Angeles, as a full professor with joint appointments in computer science, psychiatry, and psychology. He moved to Johns Hopkins University in January 2016. His research interests include computational models of vision, mathematical models of cognition, medical image analysis, and artificial intelligence and neural networks.
Title: What Have Deep Nets ever done for us?
Abstract: A recent opinion paper about the strength and weaknesses of Deep Nets argues that despite the huge successes of deep networks they will be unable to overcome the fundamental problems of computer vision due to the complexity of the real world (Yuille & Liu 2021). This talk revisits these ideas taking into account recent progress in Deep Nets caused by transformers and self-supervised learning. We argue that the fundamental problems of vision remain and the limitations of current algorithms are obscured by the way the vision community evaluates performance. We argue for more challenging evaluation criteria, such as out-of-distribution testing, adversarial examiners, and the construction of more challenging evaluation datasets. We argue that approaches that build generative models of the three dimensional world, inspired by properties of the human visual system, are most likely to overcome these challenges.
Wenwu Zhu
Professor of Computer Department of Tsinghua University
Bio: 朱文武，清华大学计算机系教授，信息科学与技术国家研究中心副主任，清华大学人工智能研究院大数据智能中心主任，大数据算法与分析技术国家工程实验室副主任，国家973项目首席科学家。现主要从事多媒体网络计算、大数据智能等研究工作。目前担任IEEE Transactions on Multimedia 指导委员会主席，曾任IEEE Transactions on Multimedia主编。IEEE Fellow、AAAS Fellow、SPIE Fellow、欧洲科学院院士。两次获国家自然科学二等奖（排1和排2）。
Title: 图机器学习研究进展
Abstract: 图数据，例如社交网络、交通网络、蛋白质网络等，广泛存在于各行各业。时空图、知识图、场景图等广泛用于计算机视觉领域中。图机器学习是近年来计算机视觉与机器学习的研究热点之一，已成为视频分析、目标识别、视觉推理等计算机视觉应用的核心技术。本报告首先回顾图机器学习的发展，包括图表征学习，即将网络/图转化为低维向量表征，和图神经网络，即在网络/图上进行端到端学习。然后介绍图机器学习研究新进展，1）自动图机器学习，包括图超参优化（HPO）和图神经架构搜索（NAS）；2）分布外泛化图机器学习，即针对动态开放环境中训练与测试数据非独立同分布情况的图机器学习。本报告将全面介绍图机器学习的基本概念、面临的挑战、研究进展和未来研究方向。
