28 May 2020
Our navigation system enables robots to adapt to specific real-world environments and use cases with only small amounts of human preference data.
2020
27 May 2020
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).
2020
28 April 2020
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.
2020
29 January 2020
Latest release of the popular synthetic image dataset for training and testing. New features include increased photorealism, stereo cameras and additional ground truth.
2020
13 December 2019
This article introduces our recent arxiv preprint on further understanding human actions out of context thanks to the newly introduced Mimetics dataset.
2019
6 December 2019
Workshop on methods and measures for explainability and trustworthiness of machine learning pipelines
2019
4 December 2019
Combining keypoint reliability in an image as part of the keypoint detection problem significantly improves feature matching.
2019
8 November 2019
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.
2019
30 October 2019
Reducing risks and advancing the decision-making process for Natural language Processing Models in production.
2019
25 October 2019
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.
2019
21 October 2019
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.
2019
18 October 2019
Fine-grained action retrieval made possible thanks to a new annotated dataset and part-of-speech embedding.
2019