986 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Slovak Academy of SciencesSK20 papers
- Czech Technical University in PragueCZ18 papers
- University of WarsawPL16 papers
- Institute of Physics of the Slovak Academy of SciencesSK8 papers
- Comenius University BratislavaSK7 papers
- Institute of Experimental Physics of the Slovak Academy of SciencesSK6 papers
- University of BelgradeRS6 papers
- University of Pavol Jozef ŠafárikSK6 papers
- Centre National de la Recherche ScientifiqueFR5 papers
- Constantine the Philosopher University in NitraSK4 papers
- Département d'InformatiqueFR4 papers
- École Normale Supérieure - PSLFR4 papers
14 papers · 1 filter
Relationship between auditory and semantic entrainment using Deep Neural Networks (DNN)
Jay Kejriwal, Štefan Beňuš
The tendency of people to engage in similar, matching, or synchronized behaviour when interacting is known as entrainment. Many studies examined linguistic (syntactic and lexical s…
Unsupervised Auditory and Semantic Entrainment Models with Deep Neural Networks
Jay Kejriwal, Stefan Benus, Lina M. Rojas-Barahona
Speakers tend to engage in adaptive behavior, known as entrainment, when they become similar to their interlocutor in various aspects of speaking. We present an unsupervised deep l…
Proximity-enabled control of spin-orbit coupling in phosphorene symmetrically and asymmetrically encapsulated by WSe monolayers
Marko Milivojević, Martin Gmitra, Marcin Kurpas +2
We analyze, using first-principles calculations and the method of invariants, the spin-orbit proximity effects in trilayer heterostructures comprising phosphorene and encapsulating…
Controlling the Output of a Generative Model by Latent Feature Vector Shifting
Róbert Belanec, Peter Lacko, Kristína Malinovská
State-of-the-art generative models (e.g. StyleGAN3 \cite{karras2021alias}) often generate photorealistic images based on vectors sampled from their latent space. However, the abili…
Parameterized algorithms for block-structured integer programs with large entries
Jana Cslovjecsek, Martin Koutecký, Alexandra Lassota +2
We study two classic variants of block-structured integer programming. Two-stage stochastic programs are integer programs of the form $\{A_i \mathbf{x} + D_i \mathbf{y}_i = \mathbf…
Improving Rapidly-exploring Random Trees algorithm for Automated Parking in Real-world Scenarios
Jiri Vlasak, Michal Sojka, Zdeněk Hanzálek
Automated parking is a self-driving feature that has been in cars for several years. Parking assistants in currently sold cars fail to park in more complex real-world scenarios and…
A polynomial bound on the number of minimal separators and potential maximal cliques in -free graphs of bounded clique number
Marcin Pilipczuk, Paweł Rzążewski
In this note we show a polynomial bound on the number of minimal separators and potential maximal cliques in -free graphs of bounded clique number.
Worrisome Properties of Neural Network Controllers and Their Symbolic Representations
Jacek Cyranka, Kevin E M Church, Jean-Philippe Lessard
We raise concerns about controllers' robustness in simple reinforcement learning benchmark problems. We focus on neural network controllers and their low neuron and symbolic abstra…
Combating the Curse of Multilinguality in Cross-Lingual WSD by Aligning Sparse Contextualized Word Representations
Gábor Berend
In this paper, we advocate for using large pre-trained monolingual language models in cross lingual zero-shot word sense disambiguation (WSD) coupled with a contextualized mapping…
Proximity-induced spin-orbit coupling in phosphorene on a WSe monolayer
Marko Milivojević, Martin Gmitra, Marcin Kurpas +2
We investigate, using first-principles methods and effective-model simulations, the spin-orbit coupling proximity effects in a bilayer heterostructure comprising phosphorene and WS…
Communicating human intent to a robotic companion by multi-type gesture sentences
Petr Vanc, Jan Kristof Behrens, Karla Stepanova +1
Human-Robot collaboration in home and industrial workspaces is on the rise. However, the communication between robots and humans is a bottleneck. Although people use a combination…
Practical solutions to the relative pose of three calibrated cameras
Charalambos Tzamos, Viktor Kocur, Yaqing Ding +4
We study the challenging problem of estimating the relative pose of three calibrated cameras from four point correspondences. We propose novel efficient solutions to this problem t…
Context-aware robot control using gesture episodes
Petr Vanc, Jan Kristof Behrens, Karla Stepanova
Collaborative robots became a popular tool for increasing productivity in partly automated manufacturing plants. Intuitive robot teaching methods are required to quickly and flexib…
Large-scale investigation of weakly-supervised deep learning for the fine-grained semantic indexing of biomedical literature
Anastasios Nentidis, Thomas Chatzopoulos, Anastasia Krithara +2
Objective: Semantic indexing of biomedical literature is usually done at the level of MeSH descriptors with several related but distinct biomedical concepts often grouped together…