Персона: Тихомирова, Дарья Валерьевна
Загружается...
Email Address
Birth Date
Научные группы
Организационные подразделения
Организационная единица
Институт интеллектуальных кибернетических систем
Цель ИИКС и стратегия развития - это подготовка кадров, способных противостоять современным угрозам и вызовам, обладающих знаниями и компетенциями в области кибернетики, информационной и финансовой безопасности для решения задач разработки базового программного обеспечения, повышения защищенности критически важных информационных систем и противодействия отмыванию денег, полученных преступным путем, и финансированию терроризма.
Статус
Фамилия
Тихомирова
Имя
Дарья Валерьевна
Имя
12 results
Результаты поиска
Теперь показываю 1 - 10 из 12
- ПубликацияОткрытый доступRecognition of emotions in verbal messages based on neural networks(2021) Malova, I. S.; Tikhomirova, D. V.; Тихомирова, Дарья Валерьевна© 2020 Elsevier B.V.. All rights reserved.Emotion detection and recognition by text is an under-researched area of natural language processing (NLP), which can provide valuable input in various fields. Speech and Emotion Recognition (Speech Emotion Recognition SER) has potentially wide applications, such as interaction with robots, banking, call centers, car onboard systems, computer games, etc.
- ПубликацияОткрытый доступVisualization and Classification of Human Movements Based on Skeletal Structure: A Neural Network Approach to Sport Exercise Analysis and Comparison of Methodologies(2024) Kuzevanov, V. O.; Tikhomirova, D. V.; Тихомирова, Дарья ВалерьевнаThe authors of the paper review and compare different existing approaches to Human Action Recognition (HAR), analyze the advantages and disadvantages of platforms for extracting human skeletal structure from video stream, and evaluate the importance of visual representation in the motion analysis process. This paper presents an example implementation of one of the approaches to HAR based on the use of interpretability and visual expressiveness inherent in skeletal structures. In this work, an ad hoc network with Long Short-Term Memory (LSTM) for human activity classification is designed and implemented, which has been trained and tested in the domain of sports exercises. LSTM incorporation of memory cells and gating mechanisms not only mitigates the vanishing gradient problem but also enables LSTMs to selectively retain and utilize relevant information over extended sequences, making them highly effective in tasks with complex temporal dependencies. The problem with a fading gradient is quite common in deep neural networks and is that if the error is back propagated during the training of the network, the gradient can decrease strongly as it travels through the layers of the network to the initial layers. This can lead to the fact that the weights in the initial layers are practically not updated, which makes training of these layers impossible or slows down its process. The resulting solution can be used to create a real-time virtual fitness assistant. The resulting solution can be used to create a real-time virtual fitness assistant. In addition, this approach will make it possible to create interactive training applications with visualization of human skeletal structure, motion analysis and monitoring systems in the field of medicine and rehabilitation, as well as for the development of security systems with access control based on the analysis of visual data on the movement of human body parts.
- ПубликацияТолько метаданныеMapping Action Units to Valence and Arousal Space Using Machine Learning(2024) Gadzhiev, I. M.; Makarov, A. S.; Tikhomirova, D. V.; Dolenko, S. A.; Samsonovich, A. V.; Гаджиев, Исмаил Маратович; Тихомирова, Дарья Валерьевна; Самсонович, Алексей Владимир
- ПубликацияТолько метаданныеSocial–Emotional Conversational Agents Based on Cognitive Architectures and Machine Learning(2024) Dolgikh,A.A.; Samsonovich,A.V.; Tikhomirova,D.V.; Долгих, Анатолий Андреевич; Самсонович, Алексей Владимир; Тихомирова, Дарья Валерьевна
- ПубликацияОткрытый доступVirtual Listener: A Turing-like test for behavioral believability(2020) Chubarov, A. A.; Tikhomirova, D. V.; Shirshova, A. V.; Veselov, N. O.; Samsonovich, A. V.; Тихомирова, Дарья Валерьевна; Самсонович, Алексей Владимир© 2020 The Authors. Published by Elsevier B.V.Virtual Listener (VL) is a generalized prototype of a virtual character based on the principles of cognitive architecture eBICA, which uses facial expressions and body language (eyes movements, head rotation) to keep social and emotional contact with the user. Such contact also implies that VL needs to perceive user's facial expression and gaze, and in the long term- A lso intonation of the user's voice, the sentiment and content of user's speech. In this work, we present an approach to modeling a perceptive 3D virtual listener with emotional capabilities. The virtual character has a 3D face that performs real-time, realistic and believable facial expression dynamics. Our primary goal in this study was to evaluate the concept: E.g., to find out whether a virtual-agent-generated behavior can engender feelings of rapport in human speakers comparable to those that a real human listener can cause? At the same time, this article serves a limited purpose and only describes our current progress so far in addressing this question.
- ПубликацияТолько метаданныеToward a general believable model of human-analogous intelligent socially emotional behavior(2020) Samsonovich, A. V.; Chubarov, A. A.; Tikhomirova, D. V.; Eidln, A. A.; Самсонович, Алексей Владимир; Тихомирова, Дарья Валерьевна© Springer Nature Switzerland AG 2020.Social virtual actors need to interact with users emotionally, convincing them in their ability to understand human minds. For this to happen, an artificial emotional intelligence is needed, capable of believable behavior in real-life situations. Summarizing recent work of the authors, the present paper extends the general state-of-the-art framework of emotional AGI, using the emotional Biologically Inspired Cognitive Architecture (eBICA) as a basis. In addition to appraisals, other kinds of fluents are added to the model: somatic markers, feelings, emotional biases, moods, etc. Their integration is achieved on the basis of semantic maps and moral schemas. It is anticipated that this new level of artificial general socially emotional intelligence will complement the next-generation AGI, helping it to merge into the human society on equal with its human members.
- ПубликацияТолько метаданныеPsychological portrait of a virtual agent in the teleport game paradigm(2020) Tikhomirova, D. V.; Zavrajnova, M. V.; Rodkina, E. A.; Musayeva, Y.; Samsonovich, A. V.; Тихомирова, Дарья Валерьевна; Мусаева, Ясамин; Самсонович, Алексей Владимир© Springer Nature Switzerland AG 2020.The videogame platform Teleport created earlier allows us to study anonymous social interactions among actors of various nature: human and virtual actor, ensuring their indistinguishability, which implies believable behavior of a virtual actor. The present study found a connection between the human player behavior in the Teleport game and her psychological portrait constructed using the sixteen-factor Catell personality test for empathy. Assuming that this connection is extendable to perception of virtual actor behavior, the game sessions data was analyzed to infer behavioral characteristics of virtual actors. Based on this data analysis, we constructed psychological characteristics of models of a virtual actor (a bot). Partner and emotional characteristics of bots were defined, and their psychological portrait was constructed based on the registered bot behavior. Personal characteristics such as courage, sociability, calmness, balance, and loyalty were attributed to bots and compared to analogous characteristics of human players.
- ПубликацияТолько метаданныеEmpirical and modeling study of emotional state dynamics in social videogame paradigms(2020) Tikhomirova, D. V.; Chubarov, A. A.; Samsonovich, A. V.; Тихомирова, Дарья Валерьевна; Самсонович, Алексей Владимир© 2019The objective of this work was to study the dynamics of human emotional states in the process of social interaction in a virtual environment. The previously developed for this purpose prototypes of the virtual actor (NPC) and its virtual environment simulator “Teleport” underwent significant re-design and modification. The experimental platform was re-implemented and used in experiments with college student participants, combining electromyography, emotion recognition in facial recordings and model-based game log analysis in a social videogame paradigm. Participants interacted with two virtual actors implemented based on the eBICA cognitive architecture (Samsonovich, 2013, 2018). Positive correlations were found between eBICA model predictions and participant affects extracted from their facial expressions and facial muscle activity. Affective dynamics of social phenomena, such as the establishment of partnership or an act of betrayal, were characterized and found consistent with the model predictions. Other findings include a gradually developing emotional reaction, possibly due to the integration of appraisals of game events. Overall, obtained results confirm the eBICA model, suggesting its further extension and refinement.
- ПубликацияТолько метаданныеThe Loop of Nonverbal Communication Between Human and Virtual Actor: Mapping Between Spaces(2021) Vladimirov, R. D.; Dolenko, S. A.; Shirokiy, V. R.; Tikhomirova, D. V.; Samsonovich, A. V.; Широкий, Владимир Романович; Тихомирова, Дарья Валерьевна; Самсонович, Алексей Владимир© 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.There is a question about the appropriate emotional and expressive language of a virtual actor. In this paper we study facial expressions. We investigate the transformations between the space of Action Units and the standard affective space in the loop of nonverbal communication between a person and a virtual actor using facial expressions [1]. We are mapping both dimensions into each other using various machine learning algorithms. Action Units space was mapped into emotional space directly using artificial neural networks. Emotional space was mapped into Action Units space with help of dimensionality reduction followed by clusterization of the latter. After the final synthesis, the facial expression of virtual actor can be determined.
- ПубликацияОткрытый доступVisualization and Classification of Human Movements Based on Skeletal Structure: A Neural Network Approach to Sport Exercise Analysis and Comparison of Methodologies(НИЯУ МИФИ, 2024) Kuzevanov, V. O.; Tikhomirova, D. V.; Тихомирова, Дарья ВалерьевнаThe authors of the paper review and compare different existing approaches to Human Action Recognition (HAR), analyze the advantages and disadvantages of platforms for extracting human skeletal structure from video stream, and evaluate the importance of visual representation in the motion analysis process. This paper presents an example implementation of one of the approaches to HAR based on the use of interpretability and visual expressiveness inherent in skeletal structures. In this work, an ad hoc network with Long Short-Term Memory (LSTM) for human activity classification is designed and implemented, which has been trained and tested in the domain of sports exercises. LSTM incorporation of memory cells and gating mechanisms not only mitigates the vanishing gradient problem but also enables LSTMs to selectively retain and utilize relevant information over extended sequences, making them highly effective in tasks with complex temporal dependencies. The problem with a fading gradient is quite common in deep neural networks and is that if the error is back propagated during the training of the network, the gradient can decrease strongly as it travels through the layers of the network to the initial layers. This can lead to the fact that the weights in the initial layers are practically not updated, which makes training of these layers impossible or slows down its process. The resulting solution can be used to create a real-time virtual fitness assistant. The resulting solution can be used to create a real-time virtual fitness assistant. In addition, this approach will make it possible to create interactive training applications with visualization of human skeletal structure, motion analysis and monitoring systems in the field of medicine and rehabilitation, as well as for the development of security systems with access control based on the analysis of visual data on the movement of human body parts.