PRCV-中国模式识别与计算机视觉大会

主旨报告嘉宾

蒲慕明

中国科学院院士、中国科学院神经科学研究所学术所长和上海脑科学与类脑研究中心主任

高文

中国工程院院士、鹏城实验室主任、北京大学博雅讲席教授、IEEE/ACM Fellow

王耀南

中国工程院院士、机器人视觉感知与控制技术国家工程研究中心主任

王耀南

中国工程院院士、机器人视觉感知与控制技术国家工程研究中心主任

简介：王耀南，中国工程院院士，机器人技术与智能控制专家，湖南大学教授,机器人视觉感知与控制技术国家工程研究中心主任。中国科协委员、中国图象图形学学会理事长、中国自动化学会会士、中国计算机学会会士、中国人工智能学会会士、全国智能机器人创新联盟副理事长、国家自然科学基金委员会专家咨询委员、中国自动化学会常务理事、中国人工智能学会监事、教育部科技委人工智能与区块链技术委员会委员、湖南省自动化学会理事长等。曾任湖南大学电气与信息工程学院院长、机器人学院院长、国家863计划智能机器人领域专家、欧盟第五框架国际合作重大项目首席科学家。长期从事机器人感知与控制技术教学科研工作，成果获国家技术发明二等奖1项、国家科技进步二等奖4项、国际IEEE机器人与自动化领域“工业应用最高奖”。发表国际IEEE等SCI论文200余篇，出版机器人感知与智能控制等著作15部，获国家发明专利80余项，培养博士70余名（含IEEE Fellow、长江、杰青等）。荣获国家百千万工程人才、德国杰出洪堡学者、全国高等学校优秀教师、全国五一劳动奖章、全国先进工作者、全国创新争先奖、全国教材建设先进个人、湖南省抗击新冠疫情先进个人等荣誉称号。

报告题目：机器视觉高光谱检测技术应用与发展趋势

报告摘要：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。

吴一戎

中国科学院院士、中国图象图形学报主编

乔红

中国科学院院士、中国科学院自动化研究所研究员

Kyoung Mu Lee

Editor in Chief of the IEEE TPAMI、IEEE Fellow

Kyoung Mu Lee

Editor in Chief of the IEEE TPAMI、IEEE Fellow

简介：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).

报告题目：Toward Real-World Image Super-Resolution: Challenges and Approaches

报告摘要：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

张正友

腾讯首席科学家、腾讯AI Lab及腾讯Robotics X实验室主任、ACM/IEEE Fellow

张正友

腾讯首席科学家、腾讯AI Lab及腾讯Robotics X实验室主任、ACM/IEEE Fellow

简介：张正友博士，腾讯首席科学家，腾讯AI Lab及腾讯Robotics X实验室主任。张正友是ACM Fellow和 IEEE Fellow，是世界著名的人工智能和机器人专家，在立体视觉、运动分析、摄像机标定、机器人导航、沉浸式远程交互等方面均有开创性贡献。他在国际顶尖会议和杂志上发表论文250余篇，论文引用次数超6万4千次， 9篇文章引用数超1000次，H-index 超100，发明的专利200多项。他发明的平板摄像机标定法在全世界被普遍采用，被称之为“张氏方法”。2013年，他因为“张氏方法”获得 IEEE Helmholtz 时间考验奖。在2018年加入腾讯前，他是美国微软公司合伙人，微软研究院首席研究员和研究经理，法国国家计算机和自动化研究院（INRIA）高级研究员及日本先进技术研究院（ATR）特邀研究员。他带领的微软研究团队在微软很多产品里都有贡献，包括Windows、Office、Xbox、Kinect、Skype for Business、Office Lens等。张正友是国际计算机视觉顶级会议CVPR 2017大会共同主席，是国际认知和发育系统杂志《IEEE Transactions on Cognitive and Developmental Systems》的创始主编，国际计算机视觉杂志《International Journal of Computer Vision》的荣誉编委，国际计算机视觉和应用杂志《Machine Vision and Applications》的指导委员会委员，担任多个国际顶级期刊主编副编委和国际著名会议大会主席和程序委员会主席。

报告题目：虚实集成世界里的数字人和机器人

报告摘要：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

Alan Yuille

Bloomberg Distinguished Professor of Cognitive Science and Computer Science at Johns Hopkins University

简介：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.

报告题目：What Have Deep Nets ever done for us?

报告摘要：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.