-
Weakly supervised methods for learning actions and objects
Modern Computer Vision systems learn visual concepts through examples (i.e. images) which have been manually annotated by humans. While this paradigm allowed the field... -
Semantic Description of Humans in Images
In the present thesis we are interested in semantic description of humans in images. We propose to describe humans with the help of (i) semantic attributes e.g. male... -
Representation, Segmentation and Matching of 3D Visual Shapes using Graph Lap...
3D shape analysis is an extremely active research topic in both computer graphics and computer vision. In computer vision, 3D shape acquisition and modeling are... -
Adaptive Structure from Motion with a contrario model estimation
International audience -
Unordered feature tracking made fast and easy
International audience -
Surgical Tools Recognition and Pupil Segmentation for Cataract Surgical Proce...
International audience -
High precision camera calibration
The thesis focuses on precision aspects of 3D reconstruction with a particular emphasis on camera distortion correction. The causes of imprecisions in stereoscopy can... -
Pedestrian Localization: Literature Review and Illustration of a Monocular Vi...
International audience -
2D and 2D+t descriptors of points of interest for robust matching
Pas de résumé disponible -
A generic framework for video understanding applied to group behavior recogni...
International audience -
A Theory of Shape Identification
What are shapes? Although shape recognition has long been one of the most important topics in computer vision, it is still hard to answer this question in a few words.... -
Hyperfeatures - Multilevel Local Coding for Visual Recognition
Histograms of local appearance descriptors are a popular representation for visual recognition. They are highly discriminant and they have good resistance to local... -
Fusion of Multi-View Silhouette Cues Using a Space Occupancy Grid
In this report, we investigate what can be inferred from several silhouette probability maps, in multi-camera environments. To this aim, we propose a new framework for... -
Learning Methods for Recovering 3D Human Pose from Monocular Images
We describe a learning based method for recovering 3D human body pose from single images and monocular image sequences. Our approach requires neither an explicit body... -
Hovering quad-rotor control: A comparison of nonlinear controllers using visu...
International audience -
Structured Models for Action Recognition in Real-word Videos
This dissertation introduces novel models to recognize broad action categories --- like "opening a door" and "running" --- in real-world video data such as movies and... -
Theory of evidence for face detection and tracking
International audience -
Estimation of meteorologic visibility by highway cameras
The measurement of the meteorological visibility is an important element for the safety of road and air transport. We propose in this thesis a meteorological... -
Visual words for pose computation
We address the problem of establishing point correspondences in images for computing camera pose through Perspective-n-Point (PnP) algorithm. We compute the 3D map... -
A few applications of augmented reality : New modes of information and commun...
After a first introduction in the aim to better define the new general public domain of augmented reality, we describe our augmented reality contributions to increase...
