WILLOW - 2019 - Annual activity report

WILLOW

WILLOW - 2019

Team Willow

Team, Visitors, External Collaborators

Overall Objectives

Statement

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
Learning embodied representations

Application Domains

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

Highlights of the Year

New Software and Platforms

Pinocchio
VRAnalogy
d2-net
CrossTask
MImE
iReal
Sim2RealAugment
HowTo100M
ObMan

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
Learning embodied representations and robotics

Bilateral Contracts and Grants with Industry

Bilateral Contracts with Industry
Bilateral Grants with Industry

Partnerships and Cooperations

National Initiatives
European Initiatives
International Initiatives
International Research Visitors

Dissemination

Promoting Scientific Activities
Teaching - Supervision - Juries
Popularization

Bibliography

Publications of the year

Previous |

Home | Next next

Section: New Software and Platforms

HowTo100M

HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips

Keywords: Computer vision - Video analysis

Functional Description: Implements the method provides the dataset used in the paper HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips (2019), A. Miech, D. Zhukov, J.-B. Alayrac, M. Tapaswi, I. Laptev and J. Sivic, in Proc. ICCV'19, Seoul, South Korea.

Contact: Ivan Laptev
URL: https://www.di.ens.fr/willow/research/howto100m/

Previous |

Home | Next next