TUTORIAL 3 - Visual information retrieval-- From computer vision to human computation

on .


Ebroul Izquierdo, University of London, UK.


4 hours


Media information capturing, processing and communication have grown exponentially over the last decade. This trend has originated a critical demand for technology to automatically structure, annotate and retrieve specific media information from the vast libraries of available multimedia content. This in turn has fuelled significant industrial interest in technological developments related to multimedia search engines and systems. Key examples of such industry-driven technological developments can be found in the complex systems underpinning Google, Yahoo, and MS-Bing search engines. Actually, the dramatic growth of related tools and the pervasive use and importance of such search engines gives a solid justification of the critical role visual information retrieval is playing in any modern technological development, cultural trends and everyday life of society as a whole. Indeed, visual information retrieval, management and search engine design is becoming a pillar of modern artistic and informative structure of human thinking and communications.

This tutorial is intended to provide an overview of the most important technological developments related to visual information retrieval and to discuss current trends in the field. It will present and discuss the fundamentals of visual information retrieval from the early development in content-based media search to the current trends on human computation and social networking as important aspects of current technology for advanced media structuring, indexing and retrieval. The tutorial will also cover important aspects related to semantic based media classification and annotation.

Biography of the lecturer

Ebroul Izquierdo, PhD, MSc, CEng, FIET, SMIEEE, MBMVA, is Chair of Multimedia and Computer Vision and head of the Multimedia and Vision Group in the school of Electronic Engineering and Computer Science at Queen Mary, University of London, UK. For his thesis on the numerical approximation of algebraic-differential equations, he received the Dr. Rerum Naturalium (PhD) from the Humboldt University, Berlin, Germany. He has been a senior researcher at the Heinrich-Hertz Institute for Communication Technology (HHI), Berlin, Germany, and the Department of Electronic Systems Engineering of the University of Essex.
Prof. Izquierdo is a Chartered Engineer, a Fellow member of the The Institution of Engineering and Technology (IET), a senior member of the IEEE, a member of the British Machine Vision Association, past chairman of the IET professional network on Information Engineering, member of the Visual Signal Processing and Communication Technical Committee of the IEEE Circuits and Systems Society and member of the Multimedia Signal Processing technical committee of the IEEE.

Prof. Izquierdo is or has been associated and guest editor of several relevant journals in the field including the IEEE Transactions on Circuits and Systems for Video Technology, the IEEE Transactions on Multimedia, the EURASIP Journal on Image and Video processing, the Elsevier journal Signal Processing: Image Communication, The EURASIP Journal on Applied Signal Processing, the IEE Proceedings on Vision, Image & Signal Processing, the Journal of Multimedia Tools and Applications and the Journal of Multimedia. He has been member of the organizing committee of several conferences and workshops in the field of visual information retrieval. He has chaired special sessions and workshops in ICIP, ICASSP and ISCAS. He has been the general chair of the European Workshop on Image Analysis for Multimedia Interactive Services, London 2003 and Seoul 2006, the European Workshop for the integration of Knowledge, Semantics and Content, London 2004 and 2005, the Mobile Multimedia Communications Conference MobiMedia, Algero2006, the International Conference on Content Based Multimedia Indexing, London 2008 and the IET Conference on Visual Information Engineering, Xian 2008.

Prof. Izquierdo has been involved in many EU funded projects dealing with the development of technologies for Multimedia indexing and retrieval including, Panorama, Cost211, SCHEMA, Sambits, aceMedia, MESH, Papyrus, RUSHES, PetaMedia, Sala+, SARACEN, NextMedia, Eternal, VideoSense, Reverie, Cubrik, Advise, etc. He has coordinated several other large cooperative projects including Cost292, BUSMAN, K-Space and 3DLife.

Prof. Izquierdo currently head one of the largest research groups in Multimedia Signal Processing in the UK and over the last decade has made important contribution in the field of visual information retrieval.

Prof. Izquierdo holds several patents in the area of multimedia signal processing and has published over 500 technical papers including chapters in books.