LOCALIZATION DATASETS IN
CROWDED INDOOR SPACES
Seminar: Local-metrics for multi-object tracking
Seminar: Going from task to class-incremental learning
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2021
LeBenchmark: a reproducible framework for assessing self-supervised representation learning from speech
Learning in a changing environment: memory strategies for streaming learning under distributional shifts.
NAVER LABS releases world's biggest visual localization dataset of indoor spaces with over 130K images. Dataset built with NAVER LABS mapping robots M1X & COMET and available in unified data format kapture.
Using a novel algorithm we explore how effectively a single policy, learned by reinforcement learning, can modulate robot behaviour from risk-averse to risk-neutral, so that robots can safely navigate everyday environments like homes and shops.
A novel framework for controlled NLG called 'Generation with Distributional Control', achieves great generality on the types of constraints that can be imposed and has a large potential to remedy the problem of bias in language models.
GLOBAL AI R&D BELT
ACADEMIA – EU/GOVT – ENTREPRENEURS
Our partnerships range from long-term fundamental research to investment in products and services.