Our keynote speakers are:

Simon Colton, Goldsmiths College, University of London

Simon Colton is Professor of Computational Creativity. He previously led a research group  of the same name at Imperial College, London in the position of Reader. He graduated from the University of Durham with a degree in Mathematics, gained a MSc. in Pure Mathematics at the University of Liverpool, and finally a PhD in Artificial Intelligence from the University of Edinburgh, under the supervision of Professor Alan Bundy.
Simon is the driving force behind thepaintingfool.com, an artificial intelligence tool that he hopes will one day be accepted as an artist in its own right. His work, along with that of Maja Pantic and Michel Valstar, won the British Computing Society Machine Intelligence Award in 2007. The work has also been the subject of some media attention.
Prior to his work on The Painting Fool, Simon worked on the HR tool, a reasoning tool that was applied to discover mathematical concepts. The system successfully discovered theorems and conjectures, some of which were novel enough to become published works. (source: Wikipedia)

Simon Colton: Computational Creativity: Practice, Principles and Perceptions
Computational Creativity is a rapidly growing sub-field of AI research where we investigate how to engineer software which can take on creative responsibilities in arts and science projects. There is a strong practical element to the field, with an emphasis on building AI systems that are taken seriously as being creative in their own right. I will highlight this practical side with demonstrations from creative software, including The Painting Fool, the HR system for mathematical discovery, the ANGELINA automated videogame designer, and The WhatIfMachine which produces fictional ideas. In recent years, based on experiments and outreach activities with such software, we have begun to extract some general principles about what behaviours software needs to perform in order to be seen as creative, and ways in which we can measure progress towards creativity in software, with respect to both objective measures and in the perceptions of stakeholders including the public and fellow creatives. I will outline some of the more theoretical work coming from the field, with an emphasis on how to handle the perception of software being creative or not. Further details of our work can be found here.

Marc Pollefeys, ETH Zurich

Marc Pollefeys is a full professor in the Dept. of Computer Science of ETH Zurich since 2007. Before that he was on the faculty at the University of North Carolina at Chapel Hill. He obtained his PhD from the KU Leuven in Belgium in 1999. His main area of research is computer vision, but he is also active in robotics, machine learning and computer graphics. Dr. Pollefeys has received several prizes for his research, including a Marr prize, an NSF CAREER award, a Packard Fellowship and a European Research Council Starting Grant. He is the author or co-author of more than 240 peer-reviewed publications. He was the general chair of ECCV 2014 and a program chair for CVPR 2009 and is a fellow of the IEEE.

Marc Pollefeys: Joint 3D reconstruction and recognition
The two main goals of computer vision are to recognize the different elements of a scene and to reconstruct their 3D shape and spatial arrangement from images. In the past the reconstruction and recognition problems have mostly been approached separately. In recent years a few approaches have been proposed that use recognition to help reconstruction or vice-versa. In this talk we present our approach that jointly performs 3D scene reconstruction and recognition. Our approach is formulated as a volumetric multi-class segmentation problem and solved using a convex relaxation method. A key element of our approach is that the interface between classes (e.g. building, ground, vegetation, air) have different anisotropic smoothness priors. We will show how our joint approach significantly improves the results.