This talk addresses several important technical issues in generating graphical representation from heterogeneous unstructured big social multimedia data for delivering to and rendering on consumer mobile devices. We will first present several pressing technical challenges associated with creating a mobile browsing system that can summarize information overloading unstructured big social media data and produce a novel GIST, namely, Graphical Intelligent Semantic Transform, for effective and visually pleasing rendering on a mobile device by the personalized social media users. We will then illustrate possible solutions to solving a suite of interdisciplinary problems associated with developing such a system. Preliminary results will be shown to demonstrate the feasibility of creating such a GIST for graphical rendering of information overloading social media feeds on individual consumer mobile devices.
Chang Wen Chen is an Empire Innovation Professor of Computer Science and Engineering at the University at Buffalo, State University of New York since 2008. He has been Allen Henry Endow Chair Professor at the Florida Institute of Technology from July 2003 to December 2007. He was on the faculty of Electrical and Computer Engineering at the University of Rochester from 1992 to 1996 and on the faculty of Electrical and Computer Engineering at the University of Missouri-Columbia from 1996 to 2003.
He has been the Editor-in-Chief for IEEE Trans. Multimedia since January 2014. He has also served as the Editor-in-Chief for IEEE Trans. Circuits and Systems for Video Technology from 2006 to 2009. He has been an Editor for several other major IEEE Transactions and Journals, including the Proceedings of IEEE, IEEE Journal of Selected Areas in Communications, and IEEE Journal of Journal on Emerging and Selected Topics in Circuits and Systems. He has served as Conference Chair for several major IEEE, ACM and SPIE conferences related to multimedia video communications and signal processing. His research is supported by NSF, DARPA, Air Force, NASA, Whitaker Foundation, Microsoft, Intel, Kodak, Huawei, and Technicolor.
He received his BS from University of Science and Technology of China in 1983, MSEE from University of Southern California in 1986, and Ph.D. from University of Illinois at Urbana-Champaign in 1992. He and his students have received eight (8) Best Paper Awards or Best Student Paper Awards over the past two decades. He has also received several research and professional achievement awards, including the Sigma Xi Excellence in Graduate Research Mentoring Award in 2003, Alexander von Humboldt Research Award in 2009, and the University at Buffalo Exceptional Scholar - Sustained Achievement Award in 2012, and the State University of New York System Chancellor's Award for Excellence in Scholarship and Creative Activities in 2016. He is an IEEE Fellow since 2004 and an SPIE Fellow since 2007.
A city brain is the central decision system in the smart/intelligent city. In most smart city systems in use, the major front-end sensor nodes are surveillance cameras, which are responsible for capturing, compressing and transmitting the compressed videos to the back-end system in cloud. Then the city brain operates for video decompression, feature extraction, object classification, pattern recognition, and scene understanding. Such a system in the smart city can be called as the one-camera-one-stream framework. Nevertheless, it is more suitable for data storage and offline analysis purposes, rather than online applications. This is because using the one-camera-one-stream framework, the smart city system has to face at least two problems, namely, long delay in decision making and low accuracy in pattern recognition. To solve the low accuracy problem, some systems instead make use of multiple classes of cameras. For example, one class of cameras is designed for video data capturing and compression, while the other class is for object detection and/or pattern recognition, such as face detection and vehicle number plate recognition. However, this kind of solution not only increases the system cost, but also leads to more complex issues on software development and system maintenance. To solve the above problems, we thus propose a new framework of camera networks for the smart city, which exploits a single camera to provide two streams, including an image/video compression stream for the traditional usage such as data storage, and a scene descriptor stream extracted from the original image/video signals for object detection, pattern recognition, and scene event understanding. An experimental system in the Hangzhou city of China shows that this framework can improve the road traffic efficiency up to 11%. In this talk, I will introduce the idea of how to adaptively integrate two streams in one camera together, how to use the descriptor stream to detect the traffic jam on the roads for real-time traffic signaling control and planning, and to re-identify people and cars. Moreover, I will also present how this framework is standardized in the IEEE 1857 Standard. Finally, I will discuss how to upgrade the the camera nodes based on machine learning techniques and tools in the city brain.
Wen Gao now is a Boya Chair Professor at Peking university. He also serves as the vice president of National Natural Science Foundation of China (NSFC) from 2013, and the president of China Computer Federation (CCF) from 2016.
He received his Ph.D. degree in electronics engineering from the University of Tokyo in 1991. He joined with Harbin Institute of Technology from 1991 to 1995, and Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS) from 1996 to 2005. He joined the Peking University in 2006.
Prof. Gao works in the areas of multimedia and computer vision, topics including video coding, video analysis, multimedia retrieval, face recognition, multimodal interfaces, and virtual reality. His most cited contributions are model-based video coding and face recognition. He published seven books, over 220 papers in refereed journals, and over 600 papers in selected international conferences. He earned many awards including six State Awards in Science and Technology Achievements. He has been featured by IEEE Spectrum in June 2005 as one of the "Ten-To-Watch" among China's leading technologists. He is a fellow of IEEE, a fellow of ACM, and a member of Chinese Academy of Engineering.
A person’s health is the result of her genetics, lifestyle, and environment. Cybernetic approach may help people manage lifestyle and environment for many chronic conditions, such as Diabetes. Advances in smart phones, sensors, and wearable technology are now making it possible to analyze and understand an individual’s life style from mostly passively collected objective data streams to build her model and predict important health events in her life. Wearable/mobile sensors, smart homes, social networks, e-mail, calendar systems, and environmental sensors continuously generate data streams that can be used as lifestyle data. By assimilating and aggregating these multi-sensory data streams, we may create an accurate chronicle of a person’s life. By correlating life events with other events, and using a novel causality exploration framework, one can build model of the person. Such a model is the objective characterization of a person’s health, lifestyle, social life, and other aspects. We illustrate how to build an objective personal model for a person. It is possible to build a model of the person that could result in actionable insights and alerts in everyday life as well as provide predictive and preventive guidance for serious health events. We are studying this cybernetic approach considering Type 2 Diabetes as a concrete example.
Ramesh Jain is an entrepreneur, researcher, and educator.
He is a Donald Bren Professor in Information & Computer Sciences at University of California, Irvine where he is doing research in Event Web and experiential computing. Earlier he served on faculty of Georgia Tech, University of California at San Diego, The university of Michigan, Ann Arbor, Wayne State University, and Indian Institute of Technology, Kharagpur. He is a Fellow of AAAS, ACM, IEEE, AAAI, IAPR, and SPIE. His current research interests are in processing massive number of geo-spatial heterogeneous data streams for building Smart Social System, particularly systems for Future Health of people. He is the recipient of several awards including the ACM SIGMM Technical Achievement Award 2010.
Ramesh co-founded several companies, managed them in initial stages, and then turned them over to professional management. These companies include PRAJA, Virage, and ImageWare. Currently he is working with Krumbs, a situation aware computing company. He has also been advisor to several other companies including some of the largest companies in media and search space.
Deep neural networks (DNNs) have fundamentally changed the landscape of speech recognition and image/video understanding in recent years, enabled by the advances of big data, big computing, and innovations in deep architectures and learning methods. In this talk, I will discuss the key ideas and the cutting edge advances in deep learning technologies in the quest for visual intelligences. I will particularly focus on the latest work (classification, object detection/tracking, semantic segmentation, human pose estimation, action recognition/detection, captioning, etc.) developed for both image and video understanding, and discuss open issues. I will also shed some light on the go-to-market aspect of this exciting field.
Wenjun (Kevin) Zeng is a Principal Research Manager and a member of the senior leadership team at Microsoft Research Asia. He has been leading the video analytics research empowering the Microsoft Cognitive Services and Azure Media Analytics Services since 2014. He was with Univ. of Missouri (MU) from 2003 to 2016, most recently as a Full Professor. Prior to that, he had worked for PacketVideo Corp., Sharp Labs of America, Bell Labs, and Panasonic Technology. Wenjun has contributed significantly to the development of international standards (ISO MPEG, JPEG2000, and OMA). He received his B.E., M.S., and Ph.D. degrees from Tsinghua Univ., the Univ. of Notre Dame, and Princeton Univ., respectively. His current research interest includes mobile-cloud media computing, computer vision, social network/media analysis, and multimedia communications and security.
He is an Associate Editor-in-Chief of IEEE Multimedia Magazine, and was an AE of IEEE Trans. on Circuits & Systems for Video Technology (TCSVT), IEEE Trans. on Info. Forensics & Security, and IEEE Trans. on Multimedia (TMM). He was a Special Issue Guest Editor for the Proceedings of the IEEE, TMM, ACM TOMCCAP, TCSVT, and IEEE Communications Magazine. He was on the Steering Committee of IEEE Trans. on Mobile Computing and IEEE TMM. He served as the Steering Committee Chair of IEEE ICME in 2010 and 2011, and is serving or has served as the General Chair or TPC Chair for several IEEE conferences (e.g., ICME’2018, ICIP’2017). He was the recipient of several best paper awards (e.g., IEEE VCIP’2016, IEEE ComSoC MMTC 2015 Best Journal Paper, ACM ICMCS’2012). He is a Fellow of the IEEE.