Given an image, we propose a hierarchical generative
model that classifies the overall scene, recognizes and segments
each object component, as well as annotates the image
with ...
The slow speed of conventional execution-driven architecture simulators is a serious impediment to obtaining desirable research productivity. This paper proposes and evaluates a f...
The digital world enables the creation of personalized documents. In this paper we are interested in describing a computer mediated activity by a person throughout a semi-automati...
In this paper, we present an integration framework for heterogeneous motion generators. The objective is to outline issues that are currently easily solved in professional post-pr...
Luc Emering, Ronan Boulic, Tom Molet, Daniel Thalm...
In this paper we present a framework for spoken recommendation systems. To provide reliable recommendations to users, we incorporate a review summarization technique which extract...