WILLOW - 2013 - Annual activity report

WILLOW

WILLOW - 2013

Project-Team Willow

Members

Overall Objectives

Statement
Highlights of the Year

Research Program

3D object and scene modeling, analysis, and retrieval
Category-level object and scene recognition
Image restoration, manipulation and enhancement
Human activity capture and classification

Application Domains

Introduction
Quantitative image analysis in science and humanities
Video Annotation, Interpretation, and Retrieval

Software and Platforms

SPArse Modeling Software (SPAMS)
Local dense and sparse space-time features
Automatic Mining of Visual Architectural Elements
Joint learning of actors and actions in video
Visual Place Recognition with Repetitive Structures

New Results

3D object and scene modeling, analysis, and retrieval
Category-level object and scene recognition
Image restoration, manipulation and enhancement
Human activity capture and classification

Bilateral Contracts and Grants with Industry

EADS (ENS)
MSR-Inria joint lab: Image and video mining for science and humanities (Inria)
Google: Learning to annotate videos from movie scripts (Inria)

Partnerships and Cooperations

National Initiatives
European Initiatives
International Initiatives
International Research Visitors

Dissemination

Scientific Animation
Teaching - Supervision - Juries
Inria/ENS Visual Recognition and Machine Learning Summer School 2013
Invited presentations
Popularization

Bibliography

Publications of the year

Previous |

Home | Next next

Section: Software and Platforms

Automatic Mining of Visual Architectural Elements

The code on automatic mining of visual architectural elements (v4.5) described in (Doersch et al. SIGGRAPH 2012) has been publicly released online in January 2013 (earlier version v4.3 was released in December 2012 and v3.0 was released in September 2012) at http://graphics.cs.cmu.edu/projects/whatMakesParis/paris_sigg_release_v4.5.tar.gz .

Previous |

Home | Next next