The objective of this paper is to estimate 2D human pose as a spatial configuration of body parts in TV and movie video shots. Such video material is uncontrolled and extremely ch...
This paper presents a content-based approach for understanding handball videos. Tracked players are characterized by their 2D trajectories in the court plane. The trajectories and...
Alexandre Hervieu, Patrick Bouthemy, Jean-Pierre L...
Shape is an important cue for generic object recognition but can be insufficient without other cues such as object appearance. We explore a number of ways in which the geometric a...
In this demonstration, we present the Automatic Linguistic Indexing of Pictures (ALIP) system. The system annotates images with linguistic terms, chosen among hundreds of such ter...
The application architecture of Newton, a technology for supporting Personal Digital Assistants (PDAs), is described. It combines a dynamic, object-oriented language called Newton...