IAPR Invited Speakers
Marcello Pelillo is Full Professor of Computer Science at Ca’ Foscari University in Venice, Italy, where he leads the Computer Vision and Pattern Recognition group. He held visiting research positions at Yale University, McGill University, the University of Vienna, York University (UK), the University College London, and the National ICT Australia (NICTA). He has published more than 150 technical papers in refereed journals, handbooks, and conference proceedings in the areas of pattern recognition, computer vision and machine learning. He is General Chair for ICCV 2017 and has served as Program Chair for several conferences and workshops (EMMCVPR, SIMBAD, S+SSPR, etc.). He serves (has served) on the Editorial Boards of the journals IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), Pattern Recognition, IET Computer Vision, Frontiers in Computer Image Analysis, Brain Informatics, and serves on the Advisory Board of the International Journal of Machine Learning and Cybernetics. Prof. Pelillo is a Fellow of the IEEE and a Fellow of the IAPR. His Erdös number is 2.
Title: Revealing Structure in Large Graphs: Szemerédi's Regularity Lemma and Its Use in Pattern Recognition
Abstract: Introduced in the mid-1970's as an intermediate step in proving a long-standing conjecture on arithmetic progressions, Szemeredi's regularity lemma has emerged over time as a fundamental tool in different branches of discrete mathematics and theoretical computer science. Roughly, it states that every graph can be approximated by the union of a small number of random-like bipartite graphs called regular pairs. In other words, the result provides us a way to obtain a good description of a large graph using a small amount of data, and can be regarded as a manifestation of the all-pervading dichotomy between structure and randomness. In this talk, I will provide an overview of the regularity lemma and variations thereof and will discuss its relevance in the context of structural pattern recognition.
Dr. Xing Xie is currently a senior researcher in Microsoft Research Asia, and a guest Ph.D. advisor for the University of Science and Technology of China. He received his B.S. and Ph.D. degrees in Computer Science from the University of Science and Technology of China in 1996 and 2001, respectively. He joined Microsoft Research Asia in July 2001, working on spatial data mining, location based services, social networks and ubiquitous computing. During the past years, he has published over 140 referred journal and conference papers. He has more than 50 patents filed or granted. He currently serves on the editorial boards of ACM Transactions on Intelligent Systems and Technology, Springer GeoInformatica, Elsevier Pervasive and Mobile Computing, Journal of Location Based Services, and Communications of the China Computer Federation. He has worked as a guest editor of IEEE Transactions on Multimedia and IEEE Intelligent Systems. In recent years, he was involved in the program or organizing committees of over 70 conferences and workshops. Especially, he initiated the LBSN workshop series and served as program co-chair of ACM UbiComp 2011 and program chair of the 8th Chinese Pervasive Computing Conference. In Oct. 2009, he founded the SIGSPATIAL China chapter which was the first regional chapter of ACM SIGSPATIAL. He is a member of Joint Steering Committee of the UbiComp and Pervasive Conference Series. He is a senior member of ACM, the IEEE, and China Computer Federation.
Title: Understanding Users by Connecting Large Scale Social Graphs
Abstract: With the rapid development of positioning, sensor and smart device technologies, large quantities of human behavioral data are now readily available. They reflect various aspects of human mobility and activities in the physical world. The availability of this data presents an unprecedented opportunity to gain a more in depth understanding of users and provide them with personalized online experience while respecting their privacy. In this talk, I will describe a vision toward building a unified user knowledge graph supplemented with knowledge generated from both online and offline user data, such as social posts, check-in trajectories, and mobile communication histories. We proposed a graph node similarity measurement in consideration with both graph structure and descriptive information, and a graph linking/de-anonymization algorithm based on the measurement. The algorithm has been evaluated in social graphs with thousands of nodes from Microsoft Academic Search, LiveJournal, and the Enron email dataset, and a social graph with millions of nodes from Tencent Weibo. Then I will present LifeSpec, a computational framework for exploring and hierarchically categorizing urban lifestyles, based on large scale publicly available heterogeneous behavioral data from multiple social networks.
