COMPUTER VISION
The computer vision team conducts research in a wide range of areas, including visual search, scene parsing, human sensing, action recognition, pose estimation and lifelong learning.
- The team has 3 papers accepted at NeurIPS 2020
- Winner of the Koenderink test of time paper award at ECCV 2020
- The team has 4 papers accepted at ECCV 2020
- Grégory Rogez is co-editor of the IJCV Special Issue on Human Pose, Motion, Activities and Shape in 3D
- 1 paper (oral) accepted at CVPR 2020. See Blog.
- Diane Larlus is serving as Area Chair for CVPR 2020 and ECCV 2020
- The paper by César de Souza et al. on “Generating Human Action Videos by Coupling 3D Game Engines and Probabilistic Graphical Models“, was accepted for publication in IJCV.
- Yannis Kalantidis is organizing the Computer Vision for Agriculture (CV4A) workshop at ICLR 2020.
- Diane Larlus is serving as Industrial Liaison Chair for ECCV 2020
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.
Recent Publications:
- Hard negative mixing for contrastive learning, Yannis Kalantidis, Mert Bulent Sariyildiz, Noé Pion, Philippe Weinzaepfel, Diane Larlus,
Thirty-fourth Conference on Neural Information Processing Systems (NeurIPS), virtual-only conference, 6-12 December, 2020 - SuperLoss: a generic loss for robust curriculum learning, Thibault Castells, Philippe Weinzaepfel, Jérome Revaud
Thirty-fourth Conference on Neural Information Processing Systems (NeurIPS), virtual-only conference, 6-12 December, 2020 - DOPE: distillation of part experts for whole-body 3D pose estimation in the wild, Philippe Weinzaepfel, Romain Brégier, Hadrien Combaluzier, Vincent Leroy, Gregory Rogez
European Conference on Computer Vision (ECCV), Glasgow, UK (virtual event), 23-28 August, 2020 - Learning visual representations with caption annotations, Mert Bulent Sariyildiz, Julien Perez, Diane Larlus
European Conference on Computer Vision (ECCV), Glasgow, UK (virtual event), 23-28 August, 2020 - Key protected classification for collaborative learning, Mert Bulent Sariyildiz, Ramazan Gokberk Cinbis, Erman Ayday
Pattern Recognition, Volume 104, August 2020, 107327 - GanHand: predicting human grasp affordances in multi-object scenes, Enric Corona, Albert Pumarola, Guillem Alenyà, Francesc Moreno-Noguer, Gregory Rogez
Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, Washington, USA, 16-18 June, 2020 - Progressive skeletonization: trimming more fat from a network at initialization, Pau De Jorge, Amartya Sanyal, Harkirat Behl, Philip Torr, Gregory Rogez, Puneet Dokania
Published on arXiv.org - Robust image retrieval-based visual localization using kapture, Martin Humenberger, Yohann Cabon, Nicolas Guerin, Julien Morat, Jérome Revaud, Philippe Rerole, Noé Pion, Cesar Roberto De Souza, Vincent Leroy, Gabriela Csurka Khedari
Published on arXiv.org
Computer Vision team:
[ultimatemember form_id=”9347138″]