Project-WILLOW:Introduction

Team WILLOW

Members

Overall Objectives

Scientific Foundations

3D object and scene modeling, analysis, and retrieval
Category-level object and scene recognition
Human activity capture and classification
Machine learning

Application Domains

Introduction
Quantitative image analysis in science and humanities
Film Post-Production and Special Effects
Video Annotation, Interpretation, and Retrieval

Software

SPAMS
Hierarchical kernel learning
Structured variable selection
Confidence regions and multiple tests by resampling

New Results

High-fidelity image- and video-based modeling
Retrieval and modeling of objects and scenes in large image collections
Learning image and object models
Human activity capture and classification
Machine learning for computer vision
Effective learning algorithms and architectures
Learning theory

Contracts and Grants with Industry

Introduction
DGA/Bertin/EADS/SAGEM: 2ACI (ENS)
DGA/E-vitech: ITISECURE (ENS)
EADS (ENS)
MSR-INRIA joint lab: Image and video mining for science and humanities (INRIA)

Other Grants and Activities

Agence Nationale de la Recherche: HFIMBR (INRIA)
Agence Nationale de la Recherche: DETECT (ENS)
Agence Nationale de la Recherche: MGA (INRIA/ENPC)
Agence Nationale de la Recherche: Triangles (ENS)
France-UC Berkeley fund (Ecole des Mines de Paris)
European Research Council (ERC) Starting Investigator Researcher grant

Dissemination

Leadership within the scientific community
Teaching
Invited presentations
Popular science

Bibliography

Publications of the year

Inria / Raweb 2009
Presentation of the Project WILLOW

Section: Application Domains

Introduction

We believe that foundational modeling work should be grounded in applications. This includes (but is not restricted to) the following high-impact domains.

Logo Inria