2013

Friday 08 March 2013

Seminar: "Human action recognition: recent progress, open questions and future challenges"

Friday, March 8th , 2013 at 11:00

Ivan Laptev, researcher at Willow team, INRIA Roquencourt - ENS Ulm , Paris, France: Action recognition is a vivid research area with many potential applications. In this talk I will briefly review the history of action recognition and will highlight a few of the currently best performing methods. I will then try to take a critical view and will discuss the problem definition as well as the relation of action recognition to other visual recognition tasks. Learn more

Monday 11 February 2013

Seminar: "Designing for contested collective intelligence"

February 11th, 2013 at 11:00 AM
Simon Buckingham Shum associate director, Knowledge Media Institute , Milton Keynes, U.K.. and Anna De Liddo , research associate.

We propose the concept of Contested Collective Intelligence (CCI) as a distinctive subset of the broader Collective Intelligence design space. CCI is relevant to the many organizational contexts in which it is important to work with contested knowledge, for instance, due to different intellectual traditions, competing organizational objectives, information overload or ambiguous environmental signals. Read more...

Monday 14 January 2013

Seminar: "Tractable market making in combinatorial prediction markets"; January 14th, 2013 at 11:00

Miro Dudík , Researcher at Microsoft Research, New-York, NY, U.S.A., will give a talk on joint work with Sebastien Lahaie and David Pennock: We present a new automated market maker for providing liquidity across multiple logically interrelated securities. More information

Friday 15 March 2013

Seminar: Moses SMT toolkit and a 'Mixed Syntax Model'. Thursday February 28th at 2.00pm

Hieu Hoang, University of Edinburgh, UK
This seminar has 2 parts:
1: Improvements to the Statistical Machine Translation toolkit called Moses which is now 7 years old. This toolkit dominates the open source SMT space, is the de-facto standard for phrase-based model and widely adopted by academia. 2: Mixed-syntax model to improve machine translation. Combining the specificity of syntactic models and the generality of the hierarchical phrase-based model.

Seminar: "A framework for automatic sports video annotation with anomaly detection and transfer learning"; January 31st, 2013 at 11:00

Teofilo de Campos , research fellow at University of Surrey , Guilford, U.K

A system that can automatically annotate videos illustrated in an application on tennis matches followed by work on using transductive transfer learning methods to enhance the system's adaptability to new domains. For more information and demos, visit http://cvssp.org/acasva/ .