Evgeny Myasnikov
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Evgeny Myasnikov has a total of 30 co-authors. Here are the top co-authors by number of shared publications:
- Alexey Borisov
Samara National Research University Samara Russia
3 shared publications M. A. Chicheva
Russian Academy of Sciences
2 shared publicationsM. V. Gashnikov
Russian Academy of Sciences
2 shared publications- N. I. Glumov
Russian Academy of Sciences
2 shared publications V. Konovalov
2 shared publicationsV. V. Sergeev
Russian Academy of Sciences
2 shared publications
Latest Publications
- 26 June 2026
- Published by Allerton Press in Optical Memory and Neural Networks
- Vol. 35 (2) , 403
Erratum to: Human Action Recognition from Motion Capture Data Using Machine Learning Techniques
- 26 June 2026
- Published by Allerton Press in Optical Memory and Neural Networks
- Vol. 35 (2) , 403
Erratum to: Human Action Recognition from Motion Capture Data Using Machine Learning Techniques
- Open Access
Matching of SAR and optical images based on transformation to shared modality
Significant differences in optical images and Synthetic Aperture Radar (SAR) images are caused by fundamental differences in the physical principles underlying their acquisition by Earth remote sensing platforms. These differences make precise image matching (co-registration) of these two types of images difficult. In this paper, we propose a new approach to image matching of optical and SAR images, which is based on transforming the images to a new modality. The new image modality is common to both optical and SAR images and satisfies the following conditions. First, the transformed images must have an equal pre-defined number of channels. Second, the transformed and co-registered images must be as similar as possible. Third, the transformed images must be non-degenerate, meaning they must preserve the significant features of the original images. To further match images transformed to this shared modality, we train the RoMa image matching model, which is one of the leading solutions for matching of regular digital photographs. We evaluated the proposed approach on the publicly available MultiSenGE dataset containing both optical and SAR images. We demonstrated its superiority over alternative approaches based on image translation between original modalities and various feature matching algorithms. The proposed solution not only provides better quality of matching, but is also more versatile. It enables the use of ready-made RoMa and DeDoDe models, pre-trained for regular images, without retraining for a new modality, while maintaining high-quality matching of optical and SAR images.
Open AccessMatching of SAR and optical images based on transformation to shared modality
Significant differences in optical images and Synthetic Aperture Radar (SAR) images are caused by fundamental differences in the physical principles underlying their acquisition by Earth remote sensing platforms. These differences make precise image matching (co-registration) of these two types of images difficult. In this paper, we propose a new approach to image matching of optical and SAR images, which is based on transforming the images to a new modality. The new image modality is common to both optical and SAR images and satisfies the following conditions. First, the transformed images must have an equal pre-defined number of channels. Second, the transformed and co-registered images must be as similar as possible. Third, the transformed images must be non-degenerate, meaning they must preserve the significant features of the original images. To further match images transformed to this shared modality, we train the RoMa image matching model, which is one of the leading solutions for matching of regular digital photographs. We evaluated the proposed approach on the publicly available MultiSenGE dataset containing both optical and SAR images. We demonstrated its superiority over alternative approaches based on image translation between original modalities and various feature matching algorithms. The proposed solution not only provides better quality of matching, but is also more versatile. It enables the use of ready-made RoMa and DeDoDe models, pre-trained for regular images, without retraining for a new modality, while maintaining high-quality matching of optical and SAR images.
- 1 December 2025
- Published by Allerton Press in Optical Memory and Neural Networks
- Vol. 34 (S3) , S402-S409
Human Action Recognition from Motion Capture Data Using Machine Learning Techniques
- 1 December 2025
- Published by Allerton Press in Optical Memory and Neural Networks
- Vol. 34 (S3) , S402-S409
Human Action Recognition from Motion Capture Data Using Machine Learning Techniques
- Open Access
- 4 September 2025
- Published by Copernicus GmbH in The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
- Vol. XLVIII-2/W, 201-206
Human Action Recognition from Motion Capture Data based on Curve Matching
Human action recognition can be used in a wide variety of scenarios in many areas of human activity, such as medicine, public safety, gaming and entertainment, etc. In this paper, we focus on the problem of human action recognition based on data obtained using motion capture systems. To solve this problem, we use an approach based on the transition of original motion capture data to sequences of points in a lower-dimensional subspace and subsequent classification of human actions by matching the trajectories of points in the specified subspace. In particular, to match the trajectories, we explore the Frechet distance and the Dynamic Time Warping distance in both dependent and independent forms. To form a lower-dimensional subspace, we consider two well-proven approaches: the Principal Component Analysis technique and supervised feature selection procedure. We compare obtained results with alternative techniques using open Berkeley Human Action Database.
- 4 September 2025
- Published by Copernicus GmbH in The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
- Vol. XLVIII-2/W, 201-206
Open AccessHuman Action Recognition from Motion Capture Data based on Curve Matching
Human action recognition can be used in a wide variety of scenarios in many areas of human activity, such as medicine, public safety, gaming and entertainment, etc. In this paper, we focus on the problem of human action recognition based on data obtained using motion capture systems. To solve this problem, we use an approach based on the transition of original motion capture data to sequences of points in a lower-dimensional subspace and subsequent classification of human actions by matching the trajectories of points in the specified subspace. In particular, to match the trajectories, we explore the Frechet distance and the Dynamic Time Warping distance in both dependent and independent forms. To form a lower-dimensional subspace, we consider two well-proven approaches: the Principal Component Analysis technique and supervised feature selection procedure. We compare obtained results with alternative techniques using open Berkeley Human Action Database.
- 10 May 2025
- Published by Springer Nature
- p. 274-284
Generation of Compact Representations of Hyperspectral Images Using Neural Network and Spectral Features
- 10 May 2025
- Published by Springer Nature
- p. 274-284
Generation of Compact Representations of Hyperspectral Images Using Neural Network and Spectral Features
- 1 December 2024
- Published by Pleiades Publishing Ltd in Pattern Recognition and Image Analysis
- Vol. 34 (4) , 1021-1025
Compact Representations of Hyperspectral Images Based on the Fusion of Neural Network and Spectral Features
In this paper, we propose a method for generating compact representations of hyperspectral images. The method is based on the distance-based fusion procedure, which merges spatial features extracted using convolutional neural networks and spectral features, followed by dimensionality reduction. The paper shows that the compact representations formed in this way allow solving the classification problem with a quality comparable to modern hyperspectral image classification techniques. The study was carried out using the Wuhan hyperspectral image dataset.
- 1 December 2024
- Published by Pleiades Publishing Ltd in Pattern Recognition and Image Analysis
- Vol. 34 (4) , 1021-1025
Compact Representations of Hyperspectral Images Based on the Fusion of Neural Network and Spectral Features
In this paper, we propose a method for generating compact representations of hyperspectral images. The method is based on the distance-based fusion procedure, which merges spatial features extracted using convolutional neural networks and spectral features, followed by dimensionality reduction. The paper shows that the compact representations formed in this way allow solving the classification problem with a quality comparable to modern hyperspectral image classification techniques. The study was carried out using the Wuhan hyperspectral image dataset.
- Open Access
HyperKAN: Kolmogorov–Arnold Networks Make Hyperspectral Image Classifiers Smarter
In traditional neural network designs, a multilayer perceptron (MLP) is typically employed as a classification block following the feature extraction stage. However, the Kolmogorov–Arnold Network (KAN) presents a promising alternative to MLP, offering the potential to enhance prediction accuracy. In this paper, we studied KAN-based networks for pixel-wise classification of hyperspectral images. Initially, we compared baseline MLP and KAN networks with varying numbers of neurons in their hidden layers. Subsequently, we replaced the linear, convolutional, and attention layers of traditional neural networks with their KAN-based counterparts. Specifically, six cutting-edge neural networks were modified, including 1D (1DCNN), 2D (2DCNN), and 3D convolutional networks (two different 3DCNNs, NM3DCNN), as well as transformer (SSFTT). Experiments conducted using seven publicly available hyperspectral datasets demonstrated a substantial improvement in classification accuracy across all the networks. The best classification quality was achieved using a KAN-based transformer architecture.
Open AccessHyperKAN: Kolmogorov–Arnold Networks Make Hyperspectral Image Classifiers Smarter
In traditional neural network designs, a multilayer perceptron (MLP) is typically employed as a classification block following the feature extraction stage. However, the Kolmogorov–Arnold Network (KAN) presents a promising alternative to MLP, offering the potential to enhance prediction accuracy. In this paper, we studied KAN-based networks for pixel-wise classification of hyperspectral images. Initially, we compared baseline MLP and KAN networks with varying numbers of neurons in their hidden layers. Subsequently, we replaced the linear, convolutional, and attention layers of traditional neural networks with their KAN-based counterparts. Specifically, six cutting-edge neural networks were modified, including 1D (1DCNN), 2D (2DCNN), and 3D convolutional networks (two different 3DCNNs, NM3DCNN), as well as transformer (SSFTT). Experiments conducted using seven publicly available hyperspectral datasets demonstrated a substantial improvement in classification accuracy across all the networks. The best classification quality was achieved using a KAN-based transformer architecture.
- 1 October 2024
- Published by Springer Nature in Journal of Mathematical Sciences
- Vol. 285 (1) , 126-141
Blending of Predictions Boosts Understanding for Multimodal Advertisements
- 1 October 2024
- Published by Springer Nature in Journal of Mathematical Sciences
- Vol. 285 (1) , 126-141
Blending of Predictions Boosts Understanding for Multimodal Advertisements
- 2 August 2023
- Published by Springer Nature
- p. 509-518
A Framework for Feature Fusion with Application to Hyperspectral Images
- 2 August 2023
- Published by Springer Nature
- p. 509-518
A Framework for Feature Fusion with Application to Hyperspectral Images
- 2 November 2022
- Published by Springer Nature
- p. 190-198
Data Dimensionality Reduction Technique Based on Preservation of Hellinger Divergence
- 2 November 2022
- Published by Springer Nature
- p. 190-198
Data Dimensionality Reduction Technique Based on Preservation of Hellinger Divergence