PhD student position in Computational Vision - Video Analysis at KTH in Stockholm Job description The position is in the area of Computational Vision — the science of understanding the computational mechanisms underlying visual perception and of equipping computers with visual perceptual abilities to make them see. The goal of this specific project is to develop new approaches for computing image features in terms of receptive fields for analyzing spatio-temporal image data (video or real-time image streams) in a theoretically well-founded manner for purposes in computer vision and computational modelling of biological vision. The main focus is specifically on developing computational vision methods for video analysis that are based on image operations in terms of time-causal and time-recursive spatio-temporal receptive fields, which only make use of information from the present moment and a compact buffer of what has occurred in the past, for which we have recently developed a novel theoretical scale-space framework at KTH. The main work to be done concerns: (i) extending this framework to different types of spatio-temporal feature detection tasks, (ii) integrating the framework into higher-order visual tasks and (iii) evaluating the performance on benchmark problems as a guide to further developments. There are possibilities of working theoretically (mathematically), algorithmically and experimentally in close collaboration with the supervisor. An overview of the research environment can be found at https://www.kth.se/profile/76171/page/computational-vision-at-csc-kth. Qualifications The candidate should have a strong computationally oriented background. The preference is for a candidate with a Master's degree in Engineering Physics or Computer Science with focus towards applied mathematics, computer science and numerical computations or a MSc/MEng education leading to similar skills. Good knowledge about computer vision and machine learning is a strong merit. The candidate should have good analytical abilities to work individually on problem solving and in good collaboration with the supervisor, specifically of working systematically and with good communication skills being able to present the results in writing and at scientific meetings. Good programming skills are necessary with the ability of working both with algorithm development in Matlab and if necessary complementing by more efficient implementations in C or C++. Applicants must be strongly motivated for doctoral studies, possess the ability to work independently and perform critical analysis and also possess good levels of cooperative and communicative abilities. Department information The position belongs to the Computational Brain Science group in the recently merged departments of Computational Biology and High Performance Computing and Visualization at the School of Computer Science and Communication. For more information visit https://www.kth.se/en/csc/forskning/cb. Additional information For further information and details about how to apply, please see https://www.kth.se/en/om/work-at-kth/lediga-jobb/what:job/jobID:82576/ The deadline for applications is on January 17, 2016. [cid:FD2B374F-C472-4895-ADA7-B3CD5419FD22@csc.kth.se] Tony Lindeberg Professor of Computer Science — Computational Vision KTH Royal Institute of Technology School of Computer Science and Communication Department of Computational Biology SE-100 44 Stockholm, Sweden Phone: +46 8 790 6205 http://www.csc.kth.se/~tony
