This paper presents the person identification system developed at Athens Information Technology and its performance in the CLEAR 2007 evaluations. The system operates on the audiov...
Andreas Stergiou, Aristodemos Pnevmatikakis, Lazar...
Abstract This paper presents an approach to designing and implementing extensible computational models for perceiving systems based on a knowledge-driven joint inference approach. ...
In this paper we face the problem of partitioning the news videos into stories, and of their classification according to a predefined set of categories. In particular, we propose ...
Francesco Colace, Pasquale Foggia, Gennaro Percann...
We consider the problem of computing the likelihood of a gesture from regular, unaided video sequences, without relying on perfect segmentation of the scene. Instead of requiring ...
This paper proposes an incremental multiple-object recognition and localization (IMORL) method. The objective of IMORL is to adaptively learn multiple interesting objects in an ima...