Výsledky vyhledávání - "Konstantin Sozykin"

Canonical Polyadic Tensor Decomposition With Low-Rank Factor Matrices

Autor: Petr Tichavsky, Konstantin Sozykin, Andrzej Cichocki, Anh Huy Phan, Konstantin Sobolev, Dmitry Ermilov

Publikováno v: ICASSP

This paper proposes a constrained canonical polyadic (CP) tensor decomposition method with low-rank factor matrices. In this way, we allow the CP decomposition with high rank while keeping the number of the model parameters small. First, we propose a

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::27fa53fcd6d5083a742e5970c104540e
https://doi.org/10.1109/icassp39728.2021.9414606

Zobrazit plný text záznamu

Using deep features for video scene detection and annotation

Autor: Adil Khan, Konstantin Sozykin, Stanislav Protasov, Muhammad Ahmad

Publikováno v: Signal, Image and Video Processing. 12:991-999

The semantic video indexing problem is still underexplored. Solutions to the problem will significantly enrich the experience of video search, monitoring, and surveillance. This paper concerns scene detection and annotation, and specifically, the tas

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::847b101a0f8a3da4b8d0f2ee749c57ec
https://doi.org/10.1007/s11760-018-1244-6

Zobrazit plný text záznamu

Stable Low-Rank Tensor Decomposition for Compression of Convolutional Neural Network

Autor: Anh Huy Phan, Konstantin Sozykin, Julia Gusak, Dmitry Ermilov, Andrzej Cichocki, Petr Tichavský, Valeriy Glukhov, Konstantin Sobolev, Ivan V. Oseledets

Publikováno v: Computer Vision – ECCV 2020 ISBN: 9783030585259
ECCV (29)

Most state-of-the-art deep neural networks are overparameterized and exhibit a high computational cost. A straightforward approach to this problem is to replace convolutional kernels with its low-rank tensor approximations, whereas the Canonical Poly

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::b147a4f6bfa71e897e90862d8d370e62
https://doi.org/10.1007/978-3-030-58526-6_31

Zobrazit plný text záznamu

Model Predictive Path Integral Control for Car Driving with Autogenerated Cost map Based on Prior Map and Camera Image

Autor: Konstantin Sozykin, Aidar Gabdullin, Alexander Buyval, Alexandr Klimchik

Publikováno v: ITSC

Model Predictive Path Integral (MPPI) algorithm is an efficient approach to control an autonomous car. However, it requires a cost map. Preparing a cost map in advance is a task that can be completed only for a static closed unchanging environment, b

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::174bb8c9109ed99318a2448fdceb839e
https://doi.org/10.1109/itsc.2019.8917227

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání