With the Object-Reference (ORef) approach, the traditional object-oriented model is extended with references to act as a canonical model. Our ORef model facilitates the storage of ...
We propose an aspect-model-based reference speaker weighting. The main idea of the approach is that the adapted model is a linear combination of a set of reference speakers like r...
We present a data-driven approach to learn user-adaptive referring expression generation (REG) policies for spoken dialogue systems. Referring expressions can be difficult to unde...
We present new results from a real-user evaluation of a data-driven approach to learning user-adaptive referring expression generation (REG) policies for spoken dialogue systems. ...
This paper introduces a video object segmentation algorithm developed in the context of the European project Art.live1 where constraints on the quality of segmentation and the pro...
Alice Caplier, Laurent Bonnaud, Jean-Marc Chassery