203 citations
- National Research University Higher School of EconomicsRU9 papers
- Lomonosov Moscow State UniversityRU7 papers
- Skolkovo Institute of Science and TechnologyRU7 papers
- Moscow Institute of Physics and TechnologyRU4 papers
- Moscow State UniversityTJ2 papers
- Russian Quantum CenterRU2 papers
- Samsung (United States)US2 papers
- Steklov Mathematical InstituteRU2 papers
- AIRI - Artificial Intelligence Research InstituteRU1 paper
- École Polytechnique Fédérale de LausanneCH1 paper
- Heidelberg UniversityDE1 paper
- Kazan Federal UniversityRU1 paper
7 papers · 1 filter
Self-supervised Depth Denoising Using Lower- and Higher-quality RGB-D sensors
Akhmedkhan Shabanov, Ilya Krotov, Nikolay Chinaev +7
Consumer-level depth cameras and depth sensors embedded in mobile devices enable numerous applications, such as AR games and face identification. However, the quality of the captur…
Combining Neural Language Models for WordSense Induction
Nikolay Arefyev, Boris Sheludko, Tatiana Aleksashina
Word sense induction (WSI) is the problem of grouping occurrences of an ambiguous word according to the expressed sense of this word. Recently a new approach to this task was propo…
Improving unsupervised neural aspect extraction for online discussions using out-of-domain classification
Anton Alekseev, Elena Tutubalina, Valentin Malykh +1
Deep learning architectures based on self-attention have recently achieved and surpassed state of the art results in the task of unsupervised aspect extraction and topic modeling.…
Controlling Overestimation Bias with Truncated Mixture of Continuous Distributional Quantile Critics
Arsenii Kuznetsov, Pavel Shvechikov, Alexander Grishin +1
The overestimation bias is one of the major impediments to accurate off-policy learning. This paper investigates a novel way to alleviate the overestimation bias in a continuous co…
Neural Head Reenactment with Latent Pose Descriptors
Egor Burkov, Igor Pasechnik, Artur Grigorev +1
We propose a neural head reenactment system, which is driven by a latent pose representation and is capable of predicting the foreground segmentation alongside the RGB image. The l…
High-Resolution Daytime Translation Without Domain Labels
Ivan Anokhin, Pavel Solovev, Denis Korzhenkov +6
Modeling daytime changes in high resolution photographs, e.g., re-rendering the same scene under different illuminations typical for day, night, or dawn, is a challenging image man…