?
MobileEmotiFace: Efficient Facial Image Representations in Video-Based Emotion Recognition on Mobile Devices
P. 266–274.
In this paper, we address the emotion classification problem in videos using a two-stage approach. At the first stage, deep features are extracted from facial regions detected in each video frame using a MobileNet-based image model. This network has been preliminarily trained to identify the age, gender, and identity of a person, and further fine-tuned on the AffectNet dataset to classify emotions in static images. At the second stage, the features of each frame are aggregated using multiple statistical functions (mean, standard deviation, min, max) into a single MobileEmotiFace descriptor of the whole video. The proposed approach is experimentally studied on the AFEW dataset from the EmotiW 2019 challenge. It was shown that our image mining technique leads to more accurate and much faster decision-making in video-based emotion recognition when compared to conventional feature extractors.
Gavrilova E., Novoselova K., Myachykov A. et al., Research in Autism 2026 Vol. 132 Article 202833
Background
Body movements convey crucial insights into emotions. Although autistic individuals may process these cues differently, the specific factors influencing emotion-from-motion perception in autism remain poorly understood. This systematic review synthesizes current research and highlights key findings in this area of study.
Objectives
This systematic review aimed to assess autistic individuals’ ability to recognize emotions through biological motion (operationalized via ...
Added: April 14, 2026
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
Seleznev L. E., Chupakhin A. A., Kostenko V. A. et al., Optical Memory and Neural Networks (Information Optics) 2023 Vol. 32 No. 2 P. 73–85
We analyze a classification problem of mentally pronounced Russian phonemes based on data obtained by means of an electroencephalography device. We describe the data collection method as well as the methods of the obtained data processing. To solve the small sample size problem we present the augmentation techniques that use the time stretching and the ...
Added: October 2, 2025
Zabolotniy A., Chan R. W., Moiseeva V. et al., Frontiers in Neuroscience 2025 Vol. 19 Article 1623380
We demonstrated the feasibility of finger movement decoding with a tailored Convolutional Neural Network. The performance of our approach was comparable to complex deep learning architectures, while providing faster and interpretable outcome. This algorithmic strategy holds high potential for the investigation of the mechanisms underlying non-invasive neurophysiological recordings in cognitive neuroscience. ...
Added: October 2, 2025
Savchenko A., Maslov D., Makarov I., , in: ECAI 2024. 27th European Conference on Artificial Intelligence, October 19 – 24 October 2024, Santiago de Compostela, Spain – Including 13th Conference on Prestigious Applications of Intelligent Systems (PAIS 2024).: IOS Press, 2024. P. 4439–4442.
Added: February 15, 2025
Morozov D., Garipov T., Lyashevskaya O. et al., Journal of Language and Education 2024 Vol. 10 No. 4 P. 71–84
Introduction: Numerous algorithms have been proposed for the task of automatic morpheme segmentation of Russian words. Due to the differences in task formulation and datasets utilized, comparing the quality of these algorithms is challenging. It is unclear whether the errors in the models are due to the ineffectiveness of algorithms themselves or to errors and inconsistencies ...
Added: January 7, 2025
Petrakova A., Лебедева Е. И., Kuzmina Y. et al., Психология. Журнал Высшей школы экономики 2024 Т. 21 № 2 С. 423–431
This article presents a pilot study with the objective to create and test stimulus material, which consists of photographic portraits of adults and children expressing various emotions. The uniqueness of this work is due to the approach to organizing the creation of stimulus material, in which the models demonstrated emotions not according to an established ...
Added: December 26, 2024
Petrakova A., Лебедева Е. И., Anikudimova E., Экспериментальная психология 2024 Т. 17 № 3 С. 4–15
The work is aimed at studying the performance of emotion recognition of people of different sex and age, expressed without specified criteria, in association with «emotional families». The materials of an empirical online research obtained with the help of the crowdsourcing service «Yandex. Toloka», in which 3,590 tes- ters took part. The subjects guessed one ...
Added: December 26, 2024
Teplyakov L., Kaymakov K., Shvets E. et al., SPIE, 2021.
Line detection is an important computer vision task traditionally solved by Hough Transform. With the advance of deep learning, however, trainable approaches to line detection became popular. In this paper we propose a lightweight CNN for line detection with an embedded parameter-free Hough layer, which allows the network neurons to have global strip-like receptive fields. ...
Added: November 5, 2024
Sysoeva T., Айрапетян Е. А., Психологические исследования: электронный научный журнал 2023 Т. 16 № 92 Статья 1
The current study is aimed to investigate the differences in emotion recognition among representatives of Armenian and Russian cultures. A preliminary study demonstrated that Armenians, unlike Russians, tend to control the expression of anger towards in-group members in greater extent. One hypothesis explaining the cultural influence on emotion recognition suggests that expression norms, which require ...
Added: January 29, 2024
Kartasheva A., Технологос 2020 № 2 С. 15–24
The article examines approaches to emotion recognition in intelligent systems from the point of view of methodological grounds. In interdisciplinary research, where it is necessary to combine approaches from different fields, we face terminological uncertainty, since the problem of describing the emotional sphere is solved by different researchers in line with several main approaches.
First, the ...
Added: October 20, 2023
Demidovskij A., Artyom Tugaryov, Aleksei Trutnev et al., Mathematics 2023 Vol. 14 No. 11 Article 3120
Due to industrial demands to handle increasing amounts of training data, lower the cost of computing one model at a time, and lessen the ecological effects of intensive computing resource consumption, the job of speeding the training of deep neural networks becomes exceedingly challenging. Adaptive Online Importance Sampling and IDS are two brand-new methods for ...
Added: September 12, 2023
Savchenko A., Savchenko L., Makarov I., IEEE Access 2023 Vol. 11 P. 65977–65990
This paper addresses the face recognition task for offline mobile applications. Using AutoML techniques, a novel technological framework is proposed to develop a fast neural network-based facial feature extractor for a concrete device. First, the Once-for-All SuperNet is trained on a large facial dataset. Each device is characterized by its lookup table, which contains the ...
Added: August 28, 2023
Churaev E., Savchenko A., Software Impacts 2023 Vol. 16 Article 100507
Nowadays, many meetings, lessons, conferences, and presentations are organized online, where it is complicated to communicate with an audience and control their engagement and emotions. In this article, we present a novel C++ application that is led to help estimate facial identities and expressions. It captures a screen with a window of an arbitrary online ...
Added: May 18, 2023
Mezentseva A. A., Rostovtseva V. V., Ananyeva K. I. et al., Frontiers in Psychology 2022 Vol. 13 Article 924486
Prior studies have reported that women outperform men in nonverbal communication, including the recognition of emotions through static facial expressions. In this experimental study, we investigated sex differences in the estimation of states of happiness, anger, fear, and disgust through static photographs using a two-culture approach. This study was conducted among the Tuvans and Mongolian ...
Added: October 31, 2022
Borisova M. D., Tomchuk K. K., A. M. Turlikov, , in: 2020 Wave Electronics and its Application in Information and Telecommunication Systems (WECONF).: IEEE, 2020. Ch. 9131479 P. 1–4.
The work considers a method for determining average relative difference in the length of the left and right legs' steps when walking on straight even surface. This value indirectly characterizes the degree of a number of diseases of the musculoskeletal and central nervous systems. The measurement interval for the difference in duration by the proposed ...
Added: October 31, 2022
Churaev E., Andrey V. Savchenko, , in: 2022 VIII International Conference on Information Technology and Nanotechnology (ITNT).: IEEE, 2022. P. 1–5.
In this paper, the multi-user video-based facial emotion recognition is examined in the presence of a small data set with the emotions of end users. By using the idea of speaker-dependent speech recognition, we propose a novel approach to solve this task if labeled video data from end users is available. During the training stage, ...
Added: September 25, 2022
Savchenko A., , in: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).: IEEE, 2022. P. 2358–2365.
In this paper, we consider the problem of real-time video-based facial emotion analytics, namely, facial expression recognition, prediction of valence and arousal and detection of action unit points. We propose the novel frame-level emotion recognition algorithm by extracting facial features with the single EfficientNet model pre-trained on Affect-Net. The predictions for sequential frames are smoothed ...
Added: August 29, 2022