Plenary Speaker of IScIDE2019

Prof. Xu ZHANG,
Institute of Brain-Intelligence Science and Technology, Zhangjiang Laboratory;
Shanghai Research Center for Brain Science and Brain-Inspired Intelligence;
Institute of Neuroscience, Chinese Academy of Sciences Academician of the Chinese Academy of Science, (English)中文)
Title: Brain Science and Artificial Intelligence
Abstract: For understanding of the brain working mechanisms, it is important to know how many neuron types, neural circuits and functional networks in the brain. It is also important to construct the basis for deciphering brain and developing brain-inspired artificial intelligence (AI). In 2012, Chinese Academy of Sciences started the Strategic Priority Research Program, mapping brain functional connections. In 2014, we started the Shanghai Brain-Intelligence Project, for the translational research of neuroscience and R&D of AI technology. We tried to link the principles and findings of neuroscience and AI development. Our team has produced the deep-learning, neural network processors, and achieved the applications of AI technologies, such as the speech recognition and translation technology, and the bionics of eyes and control system through the physiological, mathematical, physical and circuit models. The interdisciplinary research on brain science and information technology should be promoted in the future.
Bio:Dr. ZHANG Xu is a Senior Principal Investigator and Head of the Laboratory of Sensory System. He graduated from the Fourth Military Medical University in Xi’an, China. He received his Ph. D. at the Department of Neuroscience at the Karolinska Institute in Stockholm, Sweden in 1994. He was a professor of neurobiology and vice-director of the Institute of Neuroscience at the Fourth Military Medical University from 1995 to 1999. He was recruited as a Principal Investigator in 1999 by the Institute of Neuroscience, Chinese Academy of Sciences. He was the vice president of Shanghai Institutes for Biological Sciences, CAS in 2008. He was elected to be an Academician of the Chinese Academy of Sciences in 2015. Now he is the vice-president of Shanghai Branch, CAS. Dr. ZHANG is mainly interesting in molecular and cellular mechanisms of diseases in nervous system. One hundred and ten papers have been published in the international journals such as Cell and Neuron etc. He was invited to write six chapters of the international books including “Textbook of Pain” and to report his findings more than thirty times in the international meetings. He was awarded the first prize for the progress in science and technology of the PLA in 1992 and 1996 and the second prize for progress in science and technology of Shanghai in 2004. He received the award for young Chinese scientists from the Chinese Association of Sciences in 1998, and the Ho Leung Ho Lee Prize for Science and Technology from the Ho Leung Ho Lee Foundation in 2005. He was awarded the Fund for National Outstanding Young Scientists from the National Natural Science Foundation of China (NNSFC) in 1995 and 1998, and the Fund for Creative Teams from the NNSFC in 2003.
张旭研究员1961年出生于江苏省南京市,1980年8月-1985年7月在第四军医大学空军医学专业学习,毕业后获医学学士学位;1985年9月-1990年9月在第四军医大学神经生物学教研室任助教;1990年10月-1994年7月在瑞典卡罗琳斯卡医学院神经科学系攻读研究生,获医学和哲学博士学位;1994年8月-1999年11月先后在第四军医大学神经科学研究所任讲师、副研究员、研究员和博士生导师、副所长。1999年12月至今在中国科学院上海生命科学研究院神经科学研究所任研究员、感觉系统研究组组长,2005年升任高级研究员。2008年任中共科学院上海生命科学研究院副院长,2010年至今任中国科学院上海分院副院长。张旭博士从事神经科学研究,已发表论文110篇,论文被他人引用5千余次,参编疼痛学经典教科书《Textbook of Pain》等专著。担任国际疼痛研究协会第九届研讨会和第四届亚洲疼痛会议主席。应邀在国际脑研究组织世界大会等国内外学术会议作大会报告和专题报告60余次。兼任Science China Life Sciences、Philosophical Transactions of the Royal Society B和Brain Research等期刊的编委。兼任中国神经科学学会副理事长、中国细胞生物学学会副理事长和上海市神经科学学会理事长等职。他先后主持或承担国家自然科学基金委杰出青年基金、重点项目、创新研究群体科学基金、科技部973项目和中科院战略性先导科技专项(B类)等多项科研项目。他曾获得何梁何利科学与技术进步奖、中国青年科技奖、上海市自然科学牡丹奖、上海市首批“领军人物”、中国细胞生物学学会-CST杰出成就奖、礼莱亚洲科学杰出奖、中国人民解放军科技进步一等奖、上海市科技进步二等奖、中科院教学成果特等奖、中科院优秀研究生指导教师奖、中国科学院大学优秀教师等奖励。

Dr.Steve S. Chen,
Founder and CEO, Third-Brain Research Institute
Third-Brain Research Institute 创始人兼CEO
Title: Integrating Artificial Intelligence and Supercomputing Sciences to Lead in Advanced Brain Research
Bio:Steve S. Chen is founder and CEO of the Third-Brain Research Institute. He is also member of U.S. National Academy of Engineering, and member of American Academy of Arts and Sciences.
Dr. Chen has broad experience in R/D collaboration and technology commercialization with many multinational companies and governments in U.S., Europe , Asia and China. He is recognized throughout the high performance and high productivity computing industry as a leader, visionary, entrepreneur, and premier system architect. In 1980s, he pioneered the world-first parallel-vector supercomputers in Cray Research Inc., where his products generated more than $2 Billion revenue. In 2001, He successfully developed the world's first blade-style supercomputer in United States. In 2003, He successfully developed the world's collaboration middleware in United States. He was referenced in Time Magazine cover story in March, 1988.
Since 2005, Dr. Chen has devoted 10 years in establishing China's national collaborative and patient-centric healthcare cloud platform/service model with 4 clinical trial sites in farming, rural and ethnic minority regions.

Prof. Lei Xu,
Shanghai Jiao Tong University and Chinese University of Hong Kong
Title: Deep IA-BI and Five Actions in Circling
Abstract: Deep bidirectional Intelligence (BI) via YIng YAng (IA) system, or shortly Deep IA-BI, is featured by circling A-mapping and I-mapping (or shortly AI circling) that sequentially performs each of five actions. A basic foundation of IA-BI is bidirectional learning that makes the cascading of A-mapping and I-mapping (shortly A-I cascading) approximate an identical mapping, with a nature of layered, topology-preserved, and modularised development. One exemplar is Lmser that improves autoencoder by incremental bidirectional layered development of cognition, featured by two dual natures DPN and DCW. Two typical IA-BI scenarios are further addressed. One considers bidirectional cognition and image thinking, together with a proposal that combines theories of Hubel-Wiesel's versus Chen's. The other considers bidirectional integration of cognition, knowledge accumulation, and abstract thinking for improving implementation of searching, optimising, and reasoning. Particularly, an IA-DSM scheme is proposed for solving a doubly stochastic matrix (DSM) featured combinatorial tasks such as travelling salesman problem, and also a Subtree driven reasoning scheme is proposed for improving production rule based reasoning. In addition, some remarks are made on relations of Deep IA-BI to Hubel and Wiesel theory, Sperry theory, and A5 problem solving paradigm.
Bio:Emeritus Professor, Chinese University of Hong Kong; Zhiyuan Chair Professor, Shanghai Jiao Tong University (SJTU); Chief Scientist, SJTU AI Research Institute; Director of Neural Computation Research Centre in Brain and Intelligence Science-Technology Institute, Shanghai ZhangJiang National Lab; Completed Ph.D thesis at Tsinghua Univ by the end of 1986, joined Peking Univ as postdoc in 1987 and associate professor in 1988, became postdoc and visiting scientist in Finland, Canada and USA (including A.Yuille team in Harvard and M. Jordan team in MIT) during 1989-93. Joined CUHK as senior lecturer in 1993, professor in 1996, chair professor since 2002. Served as EIC and associate editors of several academic journals, e.g., including Neural Networks (1995-2016), IEEE Tr. Neural Networks (1994-98). Taken various roles in academic societies, e.g., INNS Governing Board (2001-2003), the INNS award committee (2002-2003), and the Fellow committee of IEEE Computational Intelligence society (2006-2007), and European Academy of Sciences scientific committee (2014-2017). Received several national and international academic awards, including 1993 National Nature Science Award, 1995 Leadership Award from International Neural Networks Society (INNS) and 2006 Asia Pacific Neural Network Society (APNNS) Outstanding Achievement Award. Elected to Fellow of IEEE in 2001; Fellow of Intl. Association for Pattern Recognition in 2002 and of European Academy of Sciences in 2003.
上海交大致远讲席教授和人工智能研究院首席科学家、张江实验室脑与智能科技研究院神经网络计算研究中心主任。香港中文大学荣休教授。从事智能领域研究逾37年,发表论文四百多篇,有RHT、组合分类器、RPCL、LMSER、BYY学习理论等先驱成果, Web-of-Sci引用量: (最大单篇1340+,前50篇5330+), 而谷歌学术引用量 : (最大单篇2790+,前50篇11600+)。 94起年先后担任九个期刊编委(其一为主编),包括权威期刊Neural Networks编委达22年。01-03年当选国际神经网络学会理事会成员以及评奖委员会成员,07-08年任IEEE计算智能学会Fellow committee委员。03年当选欧洲科学院院士,01年当选IEEE Fellow(从计算智能学会当选之首位中国学者)、02年当选国际模式识别学会 Fellow(最早获选的几个华人之一)。获93年国家自然科学奖、95年国际神经网络学会领袖奖、06年亚太神经网络学会最高奖(首位获奖华人)。

Prof. Ming-Hsuan Yang,
University of California at Merced
Title: Learning to track and segment objects in videos
Abstract: In this talk, I will present our recent results on visual tracking and video object segmentation. The tracking-by-detection framework typically consists of two stages, i.e., drawing samples around the target object in the first stage and classifying each sample as the target object or as background in the second stage. The performance of existing trackers using deep classification networks is limited by two aspects. First, the positive samples in each frame are highly spatially overlapped, and they fail to capture rich appearance variations. Second, there exists extreme class imbalance between positive and negative samples. This VITAL algorithm aims to address these two problems via adversarial learning. To augment positive samples, we use a generative network to randomly generate masks, which are applied to adaptively dropout input features to capture a variety of appearance changes. With the use of adversarial learning, our network identifies the mask that maintains the most robust features of the target objects over a long temporal span. In addition, to handle the issue of class imbalance, we propose a high-order cost-sensitive loss to decrease the effect of easy negative samples to facilitate training the classification network. Extensive experiments on benchmark datasets demonstrate that the proposed tracker performs favorably against the state-of-the-art approaches.
Online video object segmentation is a challenging task as it entails to process the image sequence timely and accurately. To segment a target object through the video, numerous CNN-based methods have been developed by heavily fine-tuning on the object mask in the first frame, which is time-consuming for online applications. In the second part, we propose a fast and accurate video object segmentation algorithm that can immediately start the segmentation process once receiving the images. We first utilize a part-based tracking method to deal with challenging factors such as large deformation, occlusion, and cluttered background. Based on the tracked bounding boxes of parts, we construct a region-of-interest segmentation network to generate part masks. Finally, a similarity-based scoring function is adopted to refine these object parts by comparing them to the visual information in the first frame. Our method performs favorably against state-of-the-art algorithms in terms of accuracy on the DAVIS benchmark dataset, while achieving much faster runtime performance.
Bio:Ming-Hsuan Yang is a research scientist at Google and a professor in Electrical Engineering and Computer Science at University of California, Merced. He received the PhD degree in Computer Science from the University of Illinois at Urbana-Champaign in 2000. He serves as an area chair for several conferences including IEEE Conference on Computer Vision and Pattern Recognition, IEEE International Conference on Computer Vision, European Conference on Computer Vision, Asian Conference on Computer, and AAAI National Conference on Artificial Intelligence. He serves as a program co-chair for IEEE International Conference on Computer Vision in 2019 as well as Asian Conference on Computer Vision in 2014, and general co-chair for Asian Conference on Computer Vision in 2016. He serves as an associate editor of the IEEE Transactions on Pattern Analysis and Machine Intelligence (2007 to 2011), International Journal of Computer Vision, Computer Vision and Image Understanding, Image and Vision Computing, and Journal of Artificial Intelligence Research. Yang received the Google faculty award in 2009, and the Distinguished Early Career Research Award from the UC Merced senate in 2011, the Faculty Early Career Development (CAREER) award from the National Science Foundation in 2012, and the Distinguished Research Award from UC Merced Senate in 2015. He is an IEEE Fellow.

Prof. Masashi Sugiyama,
The University of Tokyo
Title: Weakly Supervised Classification: Towards Accurate Machine Learning with Low Labeling Costs
Abstract:Machine learning from big labeled data is highly successful in areas such as speech recognition, image understanding and natural language translation. However, there are still various application domains where human labor is involved in the data collection process and thus the use of massive labeled data is prohibited. In this talk, I will introduce our recent advances in machine learning techniques from limited supervision based on empirical risk minimization, including positive-unlabeled learning, positive-confidence learning, unlabeled-unlabeled learning, similar-unlabeled learning, and complementary learning.
Bio:Masashi Sugiyama received the PhD degree in Computer Science from Tokyo Institute of Technology, Japan in 2001. He has been a Professor at the University of Tokyo since 2014 and concurrently appointed as the Director of RIKEN Center for Advanced Intelligence Project in 2016. His research interests include theory, algorithms, and applications of machine learning. He (co)-authored several books such as Density Ratio Estimation in Machine Learning (Cambridge University Press, 2012), Machine Learning in Non-Stationary Environments (MIT Press, 2012), Statistical Reinforcement Learning (Chapman and Hall,2015), Introduction to Statistical Machine Learning (Morgan Kaufmann, 2015), and Variational Bayesian Learning Theory (Cambridge University Press, 2019). He served as a Program co-chair and General co-chair for the Neural Information Processing Systems conference in 2015 and 2016, and as a Program co-chair for the AISTATS conference in 2019. Masashi Sugiyama received the Japan Academy Medal in 2017 for his contribution to machine learning.

Prof. Jingyi Yu,
ShanghaiTech University
Title:Learning to Build a New Reality
Abstract: There have been tremendous advances on applying deep learning techniques for 2d image understanding. In contrast, very little work has focused on employing deep learning for modeling datasets beyond 2D such as 3D geometry and 4D light fields. In this talk, I present several latest works from our group on in this exciting new arena, with a focus on their applications to virtual and augmented reality and computational photography. I first present a novel deep surface light field (DSLF) technique. A surface light field represents the radiance of rays originating from any points on the surface in any directions. Traditional approaches require ultra-dense sampling to ensure the rendering quality. Our DSLF works on sparse data and automatically filling in the missing data by leveraging different sampling patterns across the vertices and at the same time eliminates redundancies due to the network's prediction capability. For real data, we address the image registration problem as well as conduct texture-aware remeshing for aligning texture edges with vertices to avoid blurring. Next, I present an end-to-end deep learning scheme to establish dense shape correspondences and subsequently compress 3d dynamic human bodies. Our approach uses sparse set of “panoramic” depth maps or PDMs, each emulating an inward-viewing concentric mosaics (CM). We then develop a learning-based technique to learn pixel-wise feature descriptors on PDMs. The results are fed into an autoencoder-based network to achieve ultra-high compression ratio.
Bio: Jingyi Yu is currently Professor and Executive Dean of the School of Information Science and Technology at the ShanghaiTech University. He is also affiliated with the Department of Computer and Information Sciences at University of Delaware. He received B.S. from Caltech in 2000 and Ph.D. from MIT in 2005. He has published over 130 papers at highly refereed conferences and journals, and holds over 10 international patents on computational imaging. His research interests span a range of topics in computer vision and computer graphics, especially on computational photography and non-conventional optics and camera designs. He is a recipient of the NSF CAREER Award and the AFOSR YIP Award, and has served as an area chair of many international conferences including CVPR, ICCV, ECCV, ICCP and NIPS. He is currently an Associate Editor of IEEE TPAMI, IEEE TIP, and Elsevier CVIU, and will be program chair of ICPR 2020 and IEEE CVPR 2021.

Prof. Dong Xu,
The University of Sydney
Title: visual domain adaptation
ABSTRACT: In some vision applications, the domain of interest (i.e., the target domain) contains very few or even no labelled samples, while an existing domain (i.e., the auxiliary/source domain) is often available with a large number of labelled examples. For example, millions of loosely labelled Flickr photos or YouTube videos can be readily obtained by using keywords based search. On the other hand, users may be interested in retrieving and organizing their own multimedia collections of images and videos at the semantic level, but may be reluctant to put forth the effort to annotate their photos and videos by themselves. This problem becomes furthermore challenging because the feature distributions of training samples from the web domain and consumer domain may differ tremendously in statistical properties. To explicitly cope with the feature distribution mismatch for the samples from different domains, in this talk I will describe our newly proposed approaches for domain adaptation under different settings as well as their interesting applications in computer vision.
Bio:Dong Xu current research interests include computer vision, multimedia and machine learning. He has published more than 100 papers in IEEE Transactions and top tier conferences including CVPR, ICCV, ECCV, ICML, ACM MM and MICCAI. His co-authored work (with his former PhD student Lixin Duan) received the Best Student Paper Award in IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) in 2010. His co-authored work (with his former PhD student Lin Chen) won the IEEE Transactions on Multimedia Prize Paper Award in 2014. He has been awarded the IEEE Computational Intelligence Society Outstanding Early Career Award for 2017. He is/was on the editorial boards of T-PAMI, T-IP, T-NNLS, T-MM and T-CSVT. He also served as a guest editor of seven special issues in T-NNLS, T-CYB, T-CSVT, IJCV, ACM TOMM, CVIU and IEEE Multimedia. He is a Fellow of IEEE and IAPR.

Prof. Kun Zhang,
Carnegie Mellon University
Title: Learning Causality and Learning with Causality: The Road to Intelligence
Abstract: Does smoking cause cancer? Can we find the causal direction between two variables by analyzing their observed values? In our daily life and science, people often attempt to answer such causal questions, for the purpose of understanding and manipulating systems properly. In the past decades, interesting advances were made in fields including machine learning, statistics, and philosophy in order to answer such questions. Furthermore, we are also often concerned with how to do machine learning in complex environments. For instance, how can we make optimal predictions in non-stationary environments? Interestingly, it has recently been shown that causal information can facilitate understanding and solving various machine learning problems, including transfer learning and semi-supervised learning. This talk reviews essential concepts in causality studies and is focused on how to learn causal relations from observation data and why and how the causal perspective helps in machine learning and other tasks. Finally, I will discuss why causal representations matter in order to achieve general-purpose artificial intelligence.
Bio: Kun Zhang is an assistant professor in the philosophy department and an affiliate faculty member in the machine learning department at Carnegie Mellon University. His research interests lie in machine learning and artificial intelligence, especially in causal discovery, causality-based learning, and general-purpose artificial intelligence. He develops methods for automated causal discovery from various kinds of data, investigate learning problems, especially transfer learning, concept learning, and deep learning, from a causal view, and study philosophical foundations of causation and various machine learning tasks. He has served as an area chair or senior program committee member for major conferences in machine learning or artificial intelligence, including NeurIPS, UAI, ICML, AISTATS, AAAI, and IJCAI. He has organized various academic activities to foster interdisciplinary research in causality.

IScIDE 2019 Organizing Committee All rights reserved.