Research

The computer vision team conducts research in a wide range of areas, including visual search, scene parsing, object tracking, action recognition and 3D reconstruction. Our work covers the spectrum from unsupervised to supervised approaches, and from very deep architectures to very compact ones. We’re excited about the promise of big data to bring big performance gains to our algorithms but also passionate about the challenge of working in data-scarce and low-power scenarios. Our driving goal is to use our research to deliver ambient visual intelligence to our users in autonomous driving, robotics, via phone cameras and any other visual means to reach people wherever they may be.

​Our research combines skills in machine learning, pattern recognition and computer vision, and we work on multi-disciplinary problems with teams specialised in natural language processing, user experience, ethnography, design and more. Our research efforts may be either long-term in focus, or may tackle problems with concrete and immediate relevance to NAVER products and services. We’re very active in the computer vision community and our research is often pursued in collaboration with external partners from government and academia.

2018 Highlights

  • We have 2 papers accepted at CVPR 2018
  • Diane Larlus was recognized as an outstanding reviewer for CVPR 2018.

2017 Highlights

Improving deep neural nets for person Re-ID - A new approach that outperforms current best methods by more than just a little. Blog article by Diane Larlus and Jon Almazan.

Improving deep neural nets for person Re-ID - A new approach that outperforms current best methods by more than just a little. Blog article by Diane Larlus and Jon Almazan.

END-TO-END LEARNING 

CONTINUOUS GENERATOR

"Meet up' seminar" at Station F - Diane Larlus:  “VISUAL SEARCH IN LARGE IMAGE COLLECTIONS” (video)

 

 

 

 

 

 

 

 

 PAISS, Artificial Intelligence Summer School, 2-6 July 2018 - NAVER LABS Europe speaker from the Computer Vision team: Diane Larlus