Keynote-1: Sep 11, 2019 [8:30 AM – 9:30 AM]Prof. Tat-Seng Chua
National University of Singapore, Singapore
Title: Explainable AI & BigMM
Abstract: AI as a concept has been around since the 1950’s. With the recent advancements in machine learning algorithms, and the availability of big data and large computing resources, the scene is set for AI to be used in many more systems and applications which will profoundly impact society. The current deep learning based AI systems are mostly in black box form and are often non-explainable. Though it has high performance, it is also known to make occasional fatal mistakes. This has limited the applications of AI.
Current approaches towards explainable multimedia AI can be broadly divided into two major directions. The first focuses on deeper understanding of multimedia content, especially video. This includes dense annotation of video content from not just object recognition, but also relation inference. The dense annotation enables us to transform the level of representation of video towards that of language, in the form of relation triples and relation graphs. The second direction focuses on the development of explainable AI models. Key issues are the trade-offs between interpretability and accuracy, and the related issues of quality, fairness, robustness and privacy in model interpretation.
In this talk, I will present the current state-of-the arts in explainable multimedia AI and the future MM research. This is followed by our preliminary research on relation inference in videos, as well as leveraging prior domain knowledge, information theoretic principles, and adversarial algorithms to achieving explainable framework. I will also discuss future research towards quality, fairness and robustness of explainable AI. As the topic is broad and evolving, this talk will evoke more questions than answers.
Profile: Dr. Chua is the KITHCT Chair Professor at the School of Computing, National University of Singapore. He is also the distinguish Visiting Professor of Tsinghua. Dr. Chua was the Founding Dean of the School from 1998-2000. His main interests are in multimedia information retrieval and social media analytics. In particular, his research focuses on the extraction, retrieval and question-answering of text, video and live media arising from the Web and social networks. He is the Director of a joint research Center between NUS and Tsinghua (NExT) to research into big unstructured multi-source multimodal data analytics.
Dr. Chua is active in the international research community. He is the recipient of ACM SIGMM Technical Achievements Award 2015. He has organized and served as program committee member of numerous international conferences in the areas of computer graphics, multimedia and text processing. He is the conference co-chair of ACM Multimedia 2005, ACM CIVR 2005, ACM SIGIR 2008 and ACM Web Science 2015. He serves in the editorial boards of: ACM Transactions of Information Systems (ACM), The Visual Computer (Springer Verlag), and Multimedia Tools and Applications (Kluwer). He is the chair of steering committee of ICMR (International Conference on Multimedia Retrieval) and Multimedia Modeling conference series. Dr Chua co-founded of two technology startup companies based on research in NExT. He holds a PhD from the University of Leeds, UK.
Industry Keynote-1: Sep 11, 2019 [4:40 PM – 5:30 PM]Dr. Leslie Liu
Profile: Dr. Leslie Liu is the Chief Product Officer at Terminus Inc., one of the largest smart-city technology providers in China owned by the Everbright Group, a global fortune 500 company. At Terminus Dr. Liu is responsible for the overall technology roadmap, product strategy as well as the development of a product ecosystem that build around the IoT, AI and bigdata platform that Terminus technology team engineered and perfected over numerous projects.
Dr. Liu, drawing on his years of leadership and extraordinary professional competence, has led his team in making great achievements in many aspects from top-level product design to the implementation of the strategic plans. Managing a group of talents including engineers, product designers and BD staff, Dr. Liu designed a unique ecosystem model that now serves as the corner stone of Terminus’ hype-growth plan.
Dr. Liu used to work for renowned international companies including JD Group and IBM. When serving as the VP of JD Group and the head of JD Cloud Ecosystem.
Dr. Liu’s main focus was on the development and strategy of the JD Cloud ecosystem’s cross-industry and cross-department technical services capabilities. Under his guidance, JD Cloud Ecosystem successfully implemented full spectrum digital services in the fields of EdTech (education technology), MedTech (medical and health technology), MarTech (marketing technology), AIoT (AI+IoT). From traditional intelligence to cloud intelligence, Dr. Liu has upgraded the digital transformation and digital solutions of traditional industries and thus, helped to change the basic logic of enterprise value creation.
In October 2018, Dr. Liu was awarded by Harvard Business Review and Tencent Marketing Institute as one of the “Great Innovators in Business Model,” among the honour list of “The Top-30 New Growth Innovators in China.”
When he worked at the IBM Thomas J. Watson Research Centre in Yorktown Heights, New York, as a researcher and later at IBM’s GMU Research Headquarters in Shanghai where he led the research and development of IBM’s Big Data and Mobile divisions and simultaneously acted as chief architect, he led his team to contribute several notable developments. He is also the author of nine application patents and received the IBM Invention Achievement Award in both 2010 and 2011.
Dr. Leslie Liu graduated from the USC Viterbi School of Engineering with a Ph.D. in Computer Science and a Masters degree in Electronics Engineering.
Keynote-2: Sep 12, 2019 [8:30 AM – 9:30 AM]
Prof. Cyrus Shahabi
University of Southern California, USA
Title: Enabling Spatial-Visual Search for Geospatial Image Databases
Abstract: Due to the ubiquity of GPS-equipped cameras, captured photos are automatically tagged with camera location (referred to as geo-tagged images) at the acquisition time. Subsequently, web and mobile applications are emerging that provide search capabilities for images that are similar to a given query image and within a given geographical region (referred to as spatial-visual search).
In this talk, I focus on two research challenges to enable spatial-visual search. First, I will discuss the need for new index structures to expedite image search based on both spatial and visual relevance. Hence, I present a generic index structure which supports organizing the images using their spatial and visual properties, and also supports an adaptive distribution of images based on different local partitioning either spatially or visually.
Second, I discuss the challenge of inferring a location for the legacy images that are collected without spatial metadata. To utilize and support spatial-visual search for such images, there is a need for an accurate image localization technique for non-geo-tagged images. Moreover, even for geo-tagged images, the camera location of an image can be different from the location of the scene depicted in the image (referred to as scene location) rendering its native localization inaccurate. To address this problem, I present a framework for image scene localization using a CNN-based classification.
I conclude by showing how spatial-visual search can be used for retrieving images to be analyzed for various smart-city applications in Los Angeles (e.g., street cleanliness and graffiti recognition).
Profile: Cyrus Shahabi is a Professor of Computer Science, Electrical Engineering and Spatial Sciences; the chair of the Computer Science Department; and the director of the Integrated Media Systems Center (IMSC) at USC’s Viterbi School of Engineering.He was co-founder of two USC spin-offs, Geosemble Technologies and Tallygo, which both were acquired, in July 2012 and March 2019, respectively. He received his B.S. in Computer Engineering from Sharif University of Technology in 1989 and then his M.S. and Ph.D. Degrees in Computer Science from the University of Southern California in May 1993 and August 1996, respectively. He authored two books and more than three hundred research papers in databases, GIS and multimedia with more than 12 US Patents.
Dr. Shahabi has received funding from several agencies such as NSF, NIJ, NASA, NIH, DARPA, AFRL, NGA and DHS as well as several industries such as Chevron, Google, HP, Intel, Microsoft, NCR, NGC and Oracle. He was an Associate Editor of IEEE Transactions on Parallel and Distributed Systems (TPDS) from 2004 to 2009, IEEE Transactions on Knowledge and Data Engineering (TKDE) from 2010-2013 and VLDB Journal from 2009-2015. He is currently the chair of ACM SIGSPATIAL for the 2017-2020 term and also on the editorial board of the ACM Transactions on Spatial Algorithms and Systems (TSAS) and ACM Computers in Entertainment. He is the founding chair of IEEE NetDB workshop and also the general co-chair of SSTD’15, ACM GIS 2007, 2008 and 2009. He chaired the founding nomination committee of ACM SIGSPATIAL for its first term (2011-2014 term). He has been PC co-chair of several conferences such as APWeb+WAIM’2017, BigComp’2016, MDM’2016, DASFAA 2015, IEEE MDM 2013 and IEEE BigData 2013, and regularly serves on the program committee of major conferences such as VLDB, SIGMOD, IEEE ICDE, ACM SIGKDD, IEEE ICDM, and ACM Multimedia.
Dr. Shahabi is a fellow of IEEE, and a recipient of the ACM Distinguished Scientist award in 2009, the 2003 U.S. Presidential Early Career Awards for Scientists and Engineers (PECASE), the NSF CAREER award in 2002, and the 2001 Okawa Foundation Research Grant for Information and Telecommunications. He was also a recipient of the US Vietnam Education Foundation (VEF) faculty fellowship award in 2011 and 2012, an organizer of the 2011 National Academy of Engineering “Japan-America Frontiers of Engineering” program, an invited speaker in the 2010 National Research Council (of the National Academies) Committee on New Research Directions for the National Geospatial-Intelligence Agency, and a participant in the 2005 National Academy of Engineering “Frontiers of Engineering” program.
Keynote-3: Sep 13, 2019 [8:30 AM – 9:30 AM]
Prof. Ralf Steinmetz
Technische Universität Darmstadt, Germany
Title: Adaptivity through Transitions in Multimedia Systems
Abstract: The vast body of research on Dynamic Adaptive Streaming over HTTP (DASH) provides a strong evidence of the need for adaptivity in multimedia systems. In contrast to the focused view on quality adaptation in DASH we discuss adaptivity in multimedia systems in a broader sense, i.e., through the concept of transitions. In a nutshell, transitions enable adaptivity in communication systems at runtime through exchanging communication mechanisms in a running system to optimize the communication quality. The formalization of transitions is built upon: 1) capturing the features and relations within a communication system, (2) expressing and optimizing individual and global quality metrics of such a system. As shown in https://en.wikipedia.org/wiki/Transition_(computer_science) – for some further readings – we introduce transitions in the context of multimedia. An instantiation of a transition-based 360-degree video streaming system is the challenging example in the multimedia networking context. Transitions between sensor- and content-based predictive mechanisms allow to significantly optimize objective Quality-of-Experience (QoE) metrics.
Profile: Prof. Dr.-Ing. Ralf Steinmetz is a full professor at the Department of Electrical Engineering and
Information Technology as well as at the Dept. of Computer Science at the Techn. Univ. Darmstadt, Germany, see www.kom.tu-darmstadt.de Since 1996, there he is managing director of the “Multimedia Communications Lab”; until end of 2001, he directed a Fraunhofer Institute. In 1999, he founded the Hessian Telemedia Technology Competence Center httc; there he holds a chair position.
For more than 10 years he has served as Hessian’s advisor for information and communications technology. He is a member of the Scientific Council and president of the Board of Trustees of the international research institute IMDEA Networks, Madrid, Spain. He was awarded with a Chair of Excellence at the Univ. Carlos III de Madrid. In 2016 he was awarded with the first Athene Award for Knowledge and Technology Transfer at the TU Darmstadt for his visionary and successful establishment of start-up activities.
Together with more than 30 researchers, he works towards his vision of “seamless adaptive multimedia communications”. With his team, he has contributed to over 900 refereed publications. He has edited and co-authored a set of multimedia books which reflected the major issues; the initial version was the worldwide first in-depth technical book on multimedia technology. He has served as editor-in-chief, editor of various IEEE, ACM, and other journals.
Since 2019 he is a member of the Academia Europaea. In 2017 he was among the first three scientists being awarded a fellowship of the VDE ITG and he is a fellow of the GI. As first German scientist, he was awarded the honors of Fellow of both, the IEEE and the ACM.