报告题目：Learning about Activities and Objects from Video

报告时间：2013年8月11日（星期日）10:00-12:00

报告地点：beat365正版唯一官网报告厅

报 告 人：Tony Cohn（University of Leeds，England）
报告内容简介：In this talk I will present ongoing work at Leeds on building models of video activity. I will present techniques, both supervised and unsupervised, for learning the spatio-temporal structure of tasks and events from video or other sensor data, particularly in the case of scenarios with concurrent activities. In both cases, the representation will exploit qualititive spatio-temporal relations. A novel method for robustly transforming video data to qualitative relations will be presented. I will also show how objects can be "functionally categorised" according to their spatio-temporal behaviour.

Short Bio of the Speaker: Tony Cohn holds a Personal Chair at the University of Leeds, where he is Professor of Automated Reasoning and served a term as Head of the School of Computing August 1999 – July 2004. He is presently Director of the Institute for Artificial Intelligence and Biological Systems. He holds BSc and PhD degrees from the University of Essex where he studied under Pat Hayes. He spent 10 years at the University of Warwick before moving to Leeds in 1990. He now leads a research group working on Knowledge Representation and Reasoning with a particular focus on qualitative spatial/spatio-temporal reasoning, the best known being the well cited Region Connection Calculus (RCC).

His current research interests range from theoretical work on spatial calculi and spatial ontologies, to cognitive vision, modelling spatial information in the hippocampus, andintegrating utility data recording the location of underground assets. Many of the group’s publications concerning spatial reasoning can be found atwww.comp.leeds.ac.uk/qsr/publications.html.

He has received substantial funding from a variety of sources including EPSRC, the DTI, DARPA, the European Union and various industrial sources. Work from the Cogvis project won the British Computer Society Machine Intelligence prize in 2004.He has been Chairman/President of the UK AI Society SSAISB, the European Coordinating Committee on AI  (ECCAI),  KR inc, the IJCAI Board of Trustees and is Editor-in-Chief of the AAAI Press,  Spatial Cognition and Computation,  and Artificial Intelligence. He was elected a founding Fellow of ECCAI, and is also a Fellow of AAAI, AISB, the BCS, and the IET (formerly the IEE).  

He was Programme Chair of the European AI Conference ECAI’94,  KR’98 and COSIT-05,Workshop Chair of IJCAI 1995,  Conference Chair of KR 2000, IJCAI 2003. He was on the judging panel for the British Computer Society Distinguished Dissertation award. Recent invited/keynote talks include AIIA-10, AILog-2010,  MIWAI-10, KSEM 2010,  FLAIRS-10 (spatio-temporal track),CVWW-2010, Commonsense-2009, 21st Australasian Joint Conference on Artificial Intelligence - AI-08 ,  PCAR-08, Cognitive Robotics’08, Spatial Reasoning and Communication/AISB07. He has co-organised four Dagstuhls (05491, 07311, 10131, 10412), been on many programme committees for workshops and conferences, on the editorial board of DAKE, AI Communications (AICOM), and was Review Co-Editor of the journal Artificial Intelligence and on the Policy Committee of Electronic Transactions on AI (ETAI); he is currently on the editorial board of the Applied Ontology Journal,  the Journal of Applied Logic.  He is a member of the UK EPSRC Peer Review College and of the UK Computing Research Committee (UKCRC), and has been a Director of KR Inc. since 2000.  He was an area co-editor for the UK Government FORESIGHT Cognitive Systems project, and advised the FORESIGHT Intelligent Systems Infrastructure project. He has advised a number of overseas funding agencies, having been a member of two CNRS and three SFI programme review panels, a member of a DFG SFB review panel and an FCT panel, and chair of a programme review panel at NICTA. He has also been an expert reviewer at several EU project reviews.