?
Кластеризация видеопоследовательностей в системах видеонаблюдения на основе сверточных нейронных сетей
С. 870–875.
Соколова А. Д., Savchenko A.
Lebedev O. B., Черкасов Р. И., Известия ЮФУ. Технические науки 2025 № 5(247) С. 254–276
This paper considers the application of artificial intelligence technologies, in particular computer vision, in visual information processing systems. A comprehensive analysis of neural network approaches to solving computer vision problems is carried out, including systematization of key types of problems: image classification, object detection and semantic segmentation. The architectural principles of convolutional neural networks are ...
Added: September 10, 2026
Starodubov K., Гвасалия Г. В., Карасев П. И., Нано-био-технологии. Тепло- и электроэнергетика. Математическое моделирование: сборник статей III международной научно-практической конференции (Липецкий государственный технический университет, Липецк, Россия) 2025 С. 219–223
This paper discusses the concept of neural networks, convolutional neural networks, their architecture and their operation principle. The main attention is paid to testing the reliability of storing images of people as embeddings, which are considered to be unrecoverable in the original image. In the course of the research an experiment is carried out: the ...
Added: September 6, 2026
Shadrina E. V., Мохова В. О., Загоскин В. А. et al., Нижегородский психологический альманах 2024 № 2
The article considers the problem of learning of recognizing emotions from pictures. A review and analysis of domestic and foreign works of scientists dealing with the problem of emotional intelligence was carried out. Its formation, influence on human activity and existing variants of its structure were considered, and common features in the understanding of emotional ...
Added: April 9, 2026
Городничев М. Г., Саксонов Е. А., Кулагин В. П. et al., Вестник Рязанского государственного радиотехнического университета, Российская Федерация 2025 № 94 С. 59–67
The article is devoted to the development and experimental evaluation of a decentralized architecture for an intelligent transport system (ITS) based on the Raft consensus protocol and the network distance metric (RTT) server clustering method. It is shown that existing solutions either require manual configuration and centralized coordination, or are not optimized for latency with ...
Added: March 25, 2026
Morychev G., Sizykh D., Sizykh N., IEEE Access 2025 Vol. 13 P. 213194–213210
One of the main tools for analyzing large volumes of financial data is the use of clustering methods and models, which allow the identification of various patterns. This study examines the problem of clustering time series that reflect the behavior of prices, yields, modes, trends, and a number of related stock indicators. The relevance and ...
Added: February 3, 2026
Rubchinskiy A., Chubarova D., Technology and Investment 2025 Vol. 16 No. 4 P. 211–240
The article considers one of the most famous examples of socio-economic systems characterized by significant uncertainty—the S&P-500 stock market, where shares of 500 largest US companies are traded. The flexible algorithm for daily trading has been developed. It is based on known fixed data about cost of shares in previous days as well as on ...
Added: December 19, 2025
Pikul A. S., В кн.: Альманах научных работ молодых ученых университета ИТМО. Материалы Пятьдесят третьей (LIII) научной и учебно-методической конференции Том 1.: СПб.: Университет ИТМО, 2024. С. 338–342.
Предложен новый подход для улучшения распознавания атак презентации на биометрическую систему распознавания лиц с помощью сверточной сети с механизмом внимания. Проверена центральная гипотеза, которая заключалась в том, что с помощью механизма внимания возможно улучшить результаты работы исходной сверточной нейронной сети. В ходе экспериментов гипотеза была подтверждена. Наибольший прирост по качеству был достигнут на наборе данных ...
Added: December 13, 2025
Pikul A. S., Лепендин А. А., Труды молодых ученых Алтайского государственного университета 2023 № 20 С. 190–193
Представлен новый подход для выявления атак презентации на системы распознавания по лицу. Он основан на использовании механизма графового внимания, применяемого к промежуточным картам характеристик изображений лица, вычисленным сверточной сетью ResNet18. Показано, что предложенный подход позволил добиться высокого качества распознавания поддельных изображений при лицевой биометрической верификации, сравнимого с имеющимися в настоящее время альтернативными решениями. ...
Added: December 12, 2025
Pikul A. S., Безопасность информационных технологий 2024 Т. 31 № 4 С. 116–127
This article explores the potential use of modern computer vision architectures for the task of deepfake detection. The following architectures are considered: EfficientNet, Vision Transformer (ViT), VisionLSTM (ViL), Vision KAN, and Mamba Vision. The novelty of the approach lies in the application and comparison of these architectures, as well as their combination into paired ensembles ...
Added: December 12, 2025
Voytenkov V., Urazbaeva A., Demidova O., Регион: Экономика и Социология 2026 № 2 С. 56–79
Данное исследование направлено на выделение групп регионов России по уровню санкционного риска до введения санкций и проверке подверженности санкциям полученных групп после 2022 года. Применение кластеризации методом k-средних позволило выделить три кластера регионов по уровню санкционного риска на данных 2021 года: регионы с высоким, средним и низким санкционным риском. Данные о числе санкций, наложенных на ...
Added: December 7, 2025
Zverev S., Соколова Е. Н., Grigoreva M. et al., Медиалингвистика 2026 Т. 2 № 13
The article presents a comprehensive methodology for analysing value orientations within the Russian segment of social networks, validated on a corpus exceeding two million posts. All research stages are described, from data collection using the Brand Analytics monitoring system and lexical preprocessing of texts (normalisation and cleaning) to topic modelling with Latent Dirichlet Allocation (LDA), ...
Added: November 19, 2025
Rubchinskiy A., Chubarova D., / Series WP7 "Математические методы анализа решений в экономике, бизнесе и политике". 2025. No. WP7/2025/01.
The article examines one of the most famous examples of socio-economic systems, characterized by significant uncertainty – the S&P-500 stock market, where shares of 500 largest US companies are traded. No assumptions are made about the probabilistic characteristics of the stock market. A flexible algorithm for daily trading has been developed, based on both known fixed data ...
Added: November 9, 2025
Khomenko A., Komratova A., Isakov D. et al., , in: Computational linguistics and intellectual technologies. Papers from the Annual International Conference "Dialogue" (2025)Vol. 23.: [б.и.], 2025. P. 147–157.
The integration of automated speech analysis in diagnosing mental health disorders is becoming increasingly significant in both clinical and computational linguistics. This study aims to construct linguistic profiles for individuals with neurocognitive and affective mental disorders. Using speech transcriptions and relevant to the study computational techniques like lexical clustering and stylostatistical analysis, this research looks ...
Added: October 19, 2025
Индаков Г. С., Казначеев П. А., Майбук З. Я. et al., Геофизические исследования 2025 Т. 26 № 2 С. 99–124
The paper studies the clusterability of acoustic emission pulses during high-temperature heating of sandstone sample preliminarily subjected to mechanical loading. Mechanical loading was applied in uniaxial mode up to load close to destructive with appearance of signs of large cracks on the surface. After that, samples were subjected to thermal treatment up to 650 °C ...
Added: September 19, 2025
Shchankina A., Вопросы экономики 2026 № 1 С. 80–98
The article shows the structural changes in the relationship between the mortgage rate and MIACR, identified in the analysis of the dynamics of weighted average mortgage rates (published on the website of the Bank of Russia) in Russian regions for 2022-2025. The rates of residential mortgage loans and MIACR were multidirectional, and fluctuations in mortgage ...
Added: September 3, 2025
Sherstinova T., Вепринцева Д. А., Человек: образ и сущность. Гуманитарные аспекты 2025 № 2(62) С. 89–108
В статье рассматриваются три разных подхода к изучению тематики повседневных разговоров: экспертная тематическая разметка и два автоматических метода (тематическое моделирование и кластеризация). Материалом для исследования послужили расшифровки русской устной повседневной речи из корпуса ОРД, подготовленные на основе звукозаписей спонтанных разговоров, выполненных в естественных коммуникативных ситуациях (дома, на работе, в учебном заведении, в магазине, в поликлинике ...
Added: September 3, 2025
Maksimov A. G., Telezhkina M., / NRU Higher School of Economics. Series EC "Economics". 2024. No. 271.
The paper examines similarity of models with structural changes among heterogeneous panel data units. We propose applying a cosine metric to compare angles between vectors of weighted coefficients as a measure of closeness of economic models. Testing whether the cosine metric value is zero against nonzero, positive, and negative alternatives enriches traditional testing results. The ...
Added: March 10, 2025