NAVER LABS Europe Blog
loader image

BLOG

28 May 2020

Fast Adaptation of Reinforcement-Learned Robot Navigation Skills to Human Preferences

Our navigation system enables robots to adapt to specific real-world environments and use cases with only small amounts of human preference data.
27 May 2020

A machine translation model for Covid-19 research

We're releasing a state-of-the-art multilingual and multi-domain neural machine translation model specialised for biomedical data that enables translation into English from five languages (French, German, Italian, Spanish and Korean).
28 April 2020

Vital Records and Deep Learning are helping us uncover the past from historical handwritten records

A new platform based on deep-learning approaches to handwritten-text recognition and information extraction enables data from century-old documents to be parsed and analysed, making it possible to explore epidemics and the evolution of populations over time.
29 January 2020

Announcing Virtual KITTI 2

Latest release of the popular synthetic image dataset for training and testing. New features include increased photorealism, stereo cameras and additional ground truth.
13 December 2019

Towards understanding human actions out of context with the Mimetics dataset

This article introduces our recent arxiv preprint on further understanding human actions out of context thanks to the newly introduced Mimetics dataset.
6 December 2019

Explainability Matters in Machine Learning Pipelines

Workshop on methods and measures for explainability and trustworthiness of machine learning pipelines
4 December 2019

R2D2: Repeatable and Reliable Detector and Descriptor

Combining keypoint reliability in an image as part of the keypoint detection problem significantly improves feature matching.
8 November 2019

EMNLP2019 – what we saw and liked

EMNLP 2019 was in Hong Kong and received a record-breaking number of submissions, but here is a very biased selection of what we liked from the things we saw.
30 October 2019

Predicting when Machine Learning Models Fail in Production

Reducing risks and advancing the decision-making process for Natural language Processing Models in production.
25 October 2019

SLAMANTIC – Leveraging Semantics to Improve VSLAM in Dynamic Environments

Evaluating our method on public datasets, we show that it can successfully solve challenging situations in dynamic environments which cause state-of-the-art baseline VSLAM algorithms to fail and that it maintains performance on static scenes.
21 October 2019

Moulding Humans

A new double depth-map representation of the human shape allows to recover 3D details from a single image. Using 2 depth maps (visible and hidden) makes representations more efficient and easier to handle.
18 October 2019

Fine-Grained Action Retrieval from Video

Fine-grained action retrieval made possible thanks to a new annotated dataset and part-of-speech embedding.