Abstract--In this paper we introduce a probabilistic approach of building extraction in remotely sensed images. To cope with data heterogeneity we construct a flexible hierarchical...
This paper presents interim results from an ongoing project on aerial image reconstruction. One important task in image interpretation is the process of understanding and identifyi...
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...
We present an active learning framework to simultaneously learn appearance and contextual models for scene understanding tasks (multi-class classification). Existing multi-class a...
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 ...