Keynote 1: Multimedia Analytics: From Data to Insight.
Speaker: Marcel Worring, University of Amsterdam, Netherlands
Wednesday January 4, at 9:00 in room V101
Abstract: Today’s visual collections contain a wealth of information. For media companies, news agencies, and marketing managers alike, social media is a crucial resource in which visual data plays an ever-increasing role. In social science, biology, astrophysics, or medicine, images are a valuable source of scientific knowledge. Visual information is also becoming a prime carrier of evidence and clues in forensics and security. In all these application domains, the deluge of visual collections holds tremendous value, but how do we gain insight in such a collection? In this talk we will report on a novel multimedia analytics model based on our extensive survey of over eight hundred papers, of which hundred papers were identified as being most relevant for the topic. In the analytics model, the need for semantic navigation of the collection is emphasized and multimedia analytics tasks are placed on an exploration-search axis. Categorization is then proposed as a suitable umbrella task for realizing the exploration-search axis in the model. Finally, the pragmatic gap, defined as the difference between the tight machine categorization model and the flexible human categorization model is identified as a crucial multimedia analytics ingredient. Multimedia Pivot Tables are introduced as a first implementation of this model, providing a flexible and highly interactive methodology for creating insightful summaries. We end by considering the scalability of the model to collections of 100 million images, moving towards methods which truly support interactive insight gain in huge collections.
Biography: Marcel Worring received the M.Sc. degree (Hons.) in computer science from VU University Amsterdam, Amsterdam, The Netherlands, in 1988, and the Ph.D. degree in computer science from the University of Amsterdam, Amsterdam, The Netherlands, in 1993. He is currently an Associate Professor within the Informatics Institute, University of Amsterdam, of which he is the director, and a Full Professor on Data Science for Business Analytics with the Amsterdam Business School, University of Amsterdam. He has (co-)authored over 170 scientific papers covering a broad range of topics. His research interest is the integration of multimedia analysis, multimedia mining, information visualization, and multimedia interaction into a coherent framework yielding more than its constituent components. Prof. Worring was an Associate Editor of the IEEE Transactions on Multimedia and is currently an Associate Editor of the ACM Transactions on Multimedia. He was Program Chair for ICMR 2013 and ACM Multimedia 2013, and general chair for ACM Multimedia 2016.