Keynote Speakers: Thomas Pock and Alois Ferscha
We are really honoured to welcome Thomas Pock from Graz University of Technology.
Thomas Pock, born 1978 in Graz, received his MSc (1998-2004) and his PhD (2005-2008) in Computer Engineering (Telematik) from Graz University of Technology. After a Post-doc position at the University of Bonn, he moved back to Graz University of Technology where he has been an Assistant Professor at the Institute for Computer Graphics and Vision. In 2013 Thomas Pock received the START price of the Austrian Science Fund (FWF) and the German Pattern recognition award of the German association for pattern recognition (DAGM) and in 2014, Thomas Pock received an starting grant from the European Research Council (ERC). Since June 2014, Thomas Pock is a Professor of Computer Science at Graz University of Technology (AIT Stiftungsprofessur "Mobile Computer Vision") and a principal scientist at the Department of Digital Safety and Security at the Austrian Institute of Technology (AIT). The focus of his research is the development of mathematical models for computer vision and image processing in mobile scenarios as well as the development of efficient algorithms to compute these models. Thomas will give his keynote on On learning reaction diffusion models In this work, we study the propblem of learning nonlinear reaction-diffusion models for image restoration. We extend conventional nonlinear reaction diffusion models by several parametrized linear filters as well as several parametrized influence functions. We propose to train the parameters of the filters and the influence functions through a loss based approach. Experiments show that our trained nonlinear reaction-diffusion models largely benefit from the training of the parameters and finally lead to the best reported performance on common test datasets for image restoration.
Alois Ferscha, was with the Department of Applied Computer Science at the University of Vienna at the levels of assistant and associate professor (1986-1999). In 2000 he joined the University of Linz as full professor where he heads the Excellence Initiative “Pervasive Computing”, the department of Pervasive Computing, and the Research Studio Pervasive Computing Applications. Currently he is focused on Pervasive and Ubiquitous Computing, Networked Embedded Systems, Embedded Software Systems, Wireless Communication, Multiuser Cooperation, Distributed Interaction and Distributed Interactive Simulation. He has lead international EU funded projects (EU FP7, FET: SAPERE, HC2, PANORAMA, SOCIONICAL, OPPORTUNITY; EU FP6, FET: BeyondTheHorizon, InterLink, CRUISE), but also national projects (DISPLAYS, SPECTACLES, PowerSaver, WirelessCampus, MobiLearn) research, and holds tight cooperation with industrial stakeholders (SIEMENS Project FACT, IBM Project VRIO). SPECTACLES (Autonomous Wearable Display Systems) in cooperation with Silhouette International, INSTAR (Information and Navigation Systems Through Augmented Reality) (2001-2003), Siemens München, AG, CT-SE-1, BISANTE, EU/IST, Broadband Integrated Satellite Network Traffic Evaluation (1999-2001), Peer-to-Peer Coordination (2001– ), Siemens München, AG, CT-SE-2, Context Framework for Mobile User Applications (2001– ), Siemens München, AG, CT-SE-2, WebWall, Communication via Public Community Displays, Connect Austria (2001-2002), VRIO, Virtual Reality I/O, with GUP JKU, IBM Upper Austria (2002-2003), MobiLearn, Computer Science Any-Time Any-Where, (2002-2004), Mobile Sports Community Services, (SMS Real Time Notification at Vienna City Marathon 1999, 2000, 2001, 2002; Berlin Marathon 2000, 2001, 2002), etc. Ferscha has published more than 150 technical papers on topics related to pervasive and distributed computing. He has served on editorial boards of renowned international scientific journals (e.g. Pervasive and Mobile Computing (Elsevier), Transactions of the Society for Computer Simulation), on steering and programme committees of several conferences like PERVASIVE, UMBICOMP, ISWC, WWW, PADS, DIS-RT, SIGMETRICS, MASCOTS, MSWiM, MobiWac, TOOLS, Euro-Par, PNPM, ICS, etc. to name a few. His activities and recognition in the Pervasive Computing and Wearable Computing research communities is expressed by e.g. his chairing PERVASIVE 2004 (Programme Chair), and ISWC’09 (General Chair). In the parallel and distributed simulation community he e.g. served as the General Chair of the IEEE/ACM/SCS 11th Workshop on Parallel and Distributed Simulation (PADS’97), as Program Committee chair for the PADS’98, Program Chair for the Seventh International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems (MASCOTS’99), the 12-th IEEE International Symposium on Distributed Simulation and Real Time Applications (DS-RT 2008), or the 13th International Symposium on Wearable Computers (2009) in Linz, Austria. He has been involved in the program committees of the major related research and FET conferences /e.g. FET11 in Budapest), and chairing DOA-SVI 12. Alois Ferscha is an active consultant to the IST FET group within the Commission of the European Communities, Information Society and Media Directorate-General, and to the Austrian bm-wf and bm-vit. He is Austria’s representative in IFIP TC-10 (International Federation for Information Processing, TC10 - Computer Systems Technology). As an invited researcher or guest professor he was visiting the Dipartimento di Informatica, Universita di Torino, Italy, at the Dipartimento di Informatica, Universita di Genoa, Italy, at the Computer Science Department, University of Maryland at College Park, College Park, Maryland, U.S.A., and at the Department of Computer and Information Sciences, University of Oregon, Eugene, Oregon, U.S.A. Alois Ferscha is member of the OCG, GI, ACM, IEEE and holds the Heinz-Zemanek Award for distinguished contributions in Computer Science, the Cross Border Award 2009, the “Innovationspreis 2009” and the "Innovationspreis" of the "Multimedia Staatspreis 2011". Alois will give his keynote on Attentive Things In today’s information-rich world, where people are overflooded with signals and messages at all levels of perception and modalities (visual, auditory, tactile, olfactory), the need to allocate attention efficiently among the overabundance of information sources appears to be among the most demanding challenges for ICT mediated communication. For the design and implementation of novel, future ICT systems, it is of high interest to understand how spontaneous, local, individual attention to novel information items occurs, propagates and eventually blends into a global awareness of the whole society. Some two decades of HCI and pervasive/ubiquitous computing research have clearly revealed that out of the many indicative design factors for modern ICT, human attention is the first source of perception, consequently also awareness towards information and other individuals. In this presentation i will address the foundational basis for an attention-aware ICT, i.e. looking at computational models of human attention along with multisensory recognition architectures and reasoning algorithms to estimate and assess levels of human attention, together with their embedding into objects of everyday use ("Attentive Things"). On the formal models and methods side, I will look at established theories of individual attention (Capacity Theory, Multiple Resource Theory, Feature Integration Theory) and the respective attention models (Broadbent, Kahneman, Wickens), attempting to characterize aspects of attention of a single individual. On the recognition architecture and embedded ICT side, i will draw from recent cases in our work: (i) Attention-aware machines for future factory scenarios, attempting for manufacturing systems with cognitive control modalities and up-to-the minute adaption of the level of assistive support provided to human workers during the manufacturing process. (ii) Attention-aware aware surgeon assistance systems for live minimal invasive surgery, attempting to avoid suboptimal surgical outcomes in patient safety measures which are typically correlated with the cognitive load / level of attention of the operating surgeon, the frequency and degree of disruptions to the surgical workflow, and the misalignment of visual and motor axes in laparoscopic equipment (eye-hand coordination).