COMPUTER VISION
The computer vision team conducts research in a wide range of areas, including visual search, scene parsing, action recognition, 3D reconstruction, and embedded deep vision.
Highlights
2019
- Diane Larlus and Naila Murray to serve as area chairs for ICCV 2019.
- 3 papers from NLE accepted at CVPR 2019.
- Diane Larlus is co-organizing the FFSS-USAD workshop at CVPR 2019.
- Jon Almazán, Claudine Combe, Diane Larlus, and Rafael Sampaio de Rezende conducted a lecture and practical session on visual search as part of the Mathématiques / Vision / Apprentissage (MVA) master programme at ENS.
2018
- Accepted paper for publication in IEEE TPAMI: David Novotny, Diane Larlus and Andrea Vedaldi: Capturing the Geometry of Object Categories from Video Supervision.
- Accepted paper at ECCV 2018: David Novotny, Samuel Albanie, Diane Larlus, Andrea Vedaldi. Semi-Convolutional Operators for Instance Segmentation.
- Demo accepted at ECCV 2018: Philippe Weinzaepfel and Gregory Rogez. LCR-Net++: Multi-person 2D and 3D Pose Detection in Natural Images.
- PAISS, Artificial Intelligence Summer School NAVER LABS Europe speaker from the Computer Vision team: Diane Larlus
- Naila Murray to serve as area chair for ICLR 2019.
- We have 2 papers accepted at CVPR 2018
- Diane Larlus was recognized as an outstanding reviewer for CVPR 2018.
2017
- “Domain Adaptation in Computer Vision Applications” book in the Springer Series Advances in Computer Vision and Pattern Recognition (editor: Gabriela Csurka)
- We have 3 papers accepted at ICCV 2017.
- We won the MediaEval 2017 Retrieving Diverse Social Images Task challenge.
- We have 4 papers accepted at CVPR 2017.
- CVPR Outstanding Reviewer Award for Diane Larlus and Jérôme Revaud.
- Florent Perronnin is co-organizing, with Adrien Gaidon and Antonio Lopez, an IJCV special issue on “synthetic visual data”. This special issue follows the workshop on Virtual/Augmented Reality for Visual Artificial Intelligence (VARVAI) which was held in conjunction with ECCV 2016.
Related Content
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.
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.
“MEET UP’ SEMINAR” AT STATION F – DIANE LARLUS: “VISUAL SEARCH IN LARGE IMAGE COLLECTIONS” (VIDEO)
