检索结果-内蒙古大学图书馆

EmotiEffNet and Temporal Convolutional networks in Video-based Facial Expression Recognition and Action Unit Detection

学校读者我要写书评

暂无评论

EmotiEffNet and Temporal Convolutional Networks in Video-bas...

IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Andrey V. Savchenko Anna P. Sidorova Sber AI Lab Moscow Russia Laboratory of Algorithms and Technologies for Network Analysis HSE University Nizhny Novgorod Russia HSE University Nizhny Novgorod Russia

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

This paper examines the video-based facial expression recognition and action unit detection tasks. We propose to use pre-trained EmotiEffNet models for frame-level facial feature extraction and feed them into the Temporal Convolutional networks to take into account the dynamics of facial expressions. In addition, we study the possibility of combining facial processing with audio feature extraction to improve the accuracy of audio-visual expression recognition. Experimental results for two tasks from the sixth Affective Behavior analysis in-the-Wild challenge demonstrate that our approach lets us significantly improve quality metrics on validation sets compared to existing non-ensemble techniques. As a result, our approach took third place in the action unit detection and fourth place in the expression recognition.

关键词： Measurement Gold Visualization Face recognition Conferences Transformers Feature extraction

Effective face recognition based on anomaly image detection and sequential analysis of neural descriptors

学校读者我要写书评

暂无评论

Effective face recognition based on anomaly image detection ...

Information Technology and Nanotechnology (ITNT), International Conference on

作者： Anastasiia Sokolova Andrey V. Savchenko HSE University Nizhny Novgorod Russia Sber AI Lab Moscow Russia Laboratory of Algorithms and Technologies for Network Analysis HSE University Nizhny Novgorod Russia

In this paper, we explore the possibility to improve efficiency of face recognition using information about anomaly input images. Indeed, modern publicly-available datasets typically contain images of mostly middle-aged and Caucasian people, which cause most algorithms to fail on photos of older people or children, rarer ethnicities, poor-quality images, etc. Detection of such anomaly data and its subsequent rejection helps to improve the classification accuracy. We propose a novel algorithm, at the first stage of which a convolutional neural network is used to detect anomalies in input images. This network is trained on a specially created set of rare data. The second stage is the sequential analysis of neural descriptors extracted from input faces to improve the computational efficiency of classification. An experimental study on the VGGFace2 and MS-Celeb-1M datasets using neural network descriptors, including contemporary InsightFace models, demonstrated the effectiveness of the proposed algorithm.

关键词：

Probabilistic Neural network with Complex Exponential Activation Functions in Image Recognition using Deep Learning Framework

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Savchenko, Andrey V. Laboratory of Algorithms and Technologies for Network Analysis National Research University Higher School of Economics 25/12 Bolshaya Pecherskaya St. Nizhny Novgorod603155 Russia

— If the training dataset is not very large, image recognition is usually implemented with the transfer learning methods. In these methods the features are extracted using a deep convolutional neural network, which was preliminarily trained with an external very-large dataset. In this paper we consider the nonparametric classification of extracted feature vectors with the probabilistic neural network (PNN). The number of neurons at the pattern layer of the PNN is equal to the database size, which causes the low recognition performance and high memory space complexity of this network. We propose to overcome these drawbacks by replacing the exponential activation function in the Gaussian Parzen kernel to the complex exponential functions in the Fejér kernel. We demonstrate that in this case it is possible to implement the network with the number of neurons in the pattern layer proportional to the cubic root of the database size. Thus, the proposed modification of the PNN makes it possible to significantly decrease runtime and memory complexities without loosing its main advantages, namely, extremely fast training procedure and the convergence to the optimal Bayesian decision. An experimental study in visual object category classification and unconstrained face recognition with contemporary deep neural networks have shown, that our approach obtains very efficient and rather accurate decisions for the small training sample in comparison with the well-known classifiers. Copyright © 2017, The Authors. All rights reserved.

关键词： Deep neural networks

On -modular integer linear problems in the canonical form and equivalent problems

学校读者我要写书评

暂无评论

Journal of Global Optimization 2022年第3期88卷 591-651页

作者： Gribanov, Dmitry Shumilov, Ivan Malyshev, Dmitry Pardalos, Panos Laboratory of Algorithms and Technologies for Network Analysis HSE University Nizhny Novgorod Russian Federation Lobachevsky State University of Nizhny Novgorod Nizhny Novgorod Russian Federation Department of Industrial and Systems Engineering University of Florida Gainesville USA

Many papers in the field of integer linear programming (ILP, for short) are devoted to problems of the type $$\max \{c^\top x :A x = b,\, x \in {{\,\mathrm{\mathbb {Z}}\,}}^n_{\ge 0}\}$$ , where all the entries of A, b, c are integer, parameterized by the number of rows of A and $$\Vert A\Vert _{\max }$$ . This class of problems is known under the name of ILP problems in the standard form, adding the word ”bounded” if $$x \le u$$ , for some integer vector u. Recently, many new sparsity, proximity, and complexity results were obtained for bounded and unbounded ILP problems in the standard form. In this paper, we consider ILP problems in the canonical form $$\begin{aligned} \max \{c^\top x :b_l \le A x \le b_r,\, x \in {{\,\mathrm{\mathbb {Z}}\,}}^n\}, \end{aligned}$$ where $$b_l$$ and $$b_r$$ are integer vectors. We assume that the integer matrix A has the rank n, $$(n + m)$$ rows, n columns, and parameterize the problem by m and $$\Delta (A)$$ , where $$\Delta (A)$$ is the maximum of $$n \times n$$ sub-determinants of A, taken in the absolute value. We show that any ILP problem in the standard form can be polynomially reduced to some ILP problem in the canonical form, preserving m and $$\Delta (A)$$ , but the reverse reduction is not always possible. More precisely, we define the class of generalized ILP problems in the standard form, which includes an additional group constraint, and prove the equivalence to ILP problems in the canonical form. We generalize known sparsity, proximity, and complexity bounds for ILP problems in the canonical form. Additionally, sometimes, we strengthen previously known results for ILP problems in the canonical form, and, sometimes, we give shorter proofs. Finally, we consider the special cases of $$m \in \{0,1\}$$ . By this way, we give specialised sparsity, proximity, and complexity bounds for the problems on simplices, Knapsack problems and Subset-Sum problems.

关键词：

DEALING WITH SPARSE REWARDS USING GRAPH NEURAL networkS

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Gerasyov, Matvey Makarov, Ilya School of Data Analysis and Artificial Intelligence HSE University Moscow Russia Laboratory of Algorithms and Technologies for Network Analysis HSE University Nizhny Novgorod Russia AI Center NUST MISiS Moscow Russia Moscow Russia

Deep reinforcement learning in partially observable environments is a difficult task in itself and can be further complicated by a sparse reward signal. Most tasks involving navigation in three-dimensional environments provide the agent with minimal information. Typically, the agent receives a visual observation input from the environment and is rewarded once at the end of the episode. A good reward function could substantially improve the convergence of reinforcement learning algorithms for such tasks. The classic approach to increasing the density of the reward signal is to augment it with supplementary rewards. This technique is called reward shaping. In this study, we propose two modifications of one of the recent reward shaping methods based on graph convolutional networks: the first involving advanced aggregation functions, and the second utilizing the attention mechanism. We empirically validate the effectiveness of our solutions for the task of navigation in a 3D environment with sparse rewards. For the solution featuring the attention mechanism, we can also show that the learned attention is concentrated on edges corresponding to important transitions in the 3D environment. © 2022, CC BY-NC-ND.

关键词： Reinforcement learning

Automatic Privacy Detection in Scanned Document Images Based on Deep Neural networks

学校读者我要写书评

暂无评论

Automatic Privacy Detection in Scanned Document Images Based...

International Russian Automation Conference (RusAutoCon)

作者： Lyudmila Kopeykina Andrey V. Savchenko National Research University Higher School of Economics Nizhny Novgorod Russia Laboratory of Algorithms and Technologies for Network Analysis National Research University Higher School of Economics Nizhny Novgorod Russia

The authors consider the problem of automatic detection of private scanned documents based on text recognition with deep neural networks. The paper suggests implementing a two-phase approach with the first stage which includes efficient EAST text detection and recognition using Tesseract OCR Engine. Secondly, the authors classify the privacy of a scanned document by deep neural networks applied to the extracted text. After that, a special dataset is gathered in order to train these networks. The experiments show that using OCR Engine for both text detection and segmentation ends up with relatively poor identification of private documents when compared to preliminary text detection with EAST method. Moreover, conventional keyword spotting using the list of sensitive words is less accurate when compared to neural network-based methods. Finally, it was demonstrated that the classification of a bag of most frequent words outperforms traditional text classification techniques with LSTM and convolutional networks.

关键词： Text recognition Neural networks Detectors Privacy Task analysis Automation Optical character recognition software

Group-level emotion recognition using transfer learning from face identification

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Rassadin, Alexandr Gruzdev, Alexey Savchenko, Andrey National Research University Higher School of Economics Laboratory of Algorithms and Technologies for Network Analysis Nizhny Novgorod Russia National Research University Higher School of Economics Nizhny Novgorod Russia

In this paper we describe our algorithmic approach, which was used for submissions in the fifth Emotion Recognition in the Wild (EmotiW 2017) group-level emotion recognition sub-challenge. We extracted feature vectors of detected faces using the Convolutional Neural network trained for face identification task, rather than traditional pre-training on emotion recognition problems. In the final pipeline an ensemble of Random Forest classifiers was learned to predict emotion score using available training set. In case when the faces have not been detected, one member of our ensemble extracts features from the whole image. During our experimental study, the proposed approach showed the lowest error rate when compared to other explored techniques. In particular, we achieved 75.4% accuracy on the validation data, which is 20% higher than the handcrafted feature-based baseline. The source code using Keras framework is publicly available.68T10, 68T45 Copyright © 2017, The Authors. All rights reserved.

关键词： Speech recognition

Improving the Accuracy of One-Shot Detectors for Small Objects in X-ray Images

学校读者我要写书评

暂无评论

Improving the Accuracy of One-Shot Detectors for Small Objec...

International Russian Automation Conference (RusAutoCon)

作者： Polina Demochkina Andrey V. Savchenko National Research University Higher School of Economics Nizhny Novgorod Russia Laboratory of Algorithms and Technologies for Network Analysis National Research University Higher School of Economics Nizhny Novgorod Russia

The following topics are dealt with: control engineering computing; control system synthesis; optimisation; process control; electric drives; nonlinear control systems; motion control; machine control; production engi... 详细信息

ISBN: (数字)9781728161303

ISBN: (纸本)9781728161310

关键词： X-ray imaging Detectors Object detection Training Inspection Automation Weapons

A quasi-energy function for Pixton diffeomorphisms defined by generalized Mazur knots

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Medvedev, Timur Pochinka, Olga Laboratory of Algorithms and Technologies for Network Analysis HSE University 136 Rodionova Street Niznhy Novgorod Russia International Laboratory of Dynamical Systems and Applications HSE University 25/12 Bolshaya Pecherckaya Street Niznhy Novgorod Russia

In this paper we give a lower estimate for the number of critical points of the Lyapunov function for Pixton diffeomorphisms (i.e. Morse-Smale diffeomorphisms in dimension 3 whose chain recurrent set consists of four points: one source, one saddle and two sinks). Ch. Bonatti and V. Grines proved that the class of topological equivalence of such diffeomorphism f is completely defined by the equivalency class of the Hopf knot Lf that is the knot in the generating class of the fundamental group of the manifold S2 × S1. They also proved that there are infinitely many such classes and that any Hopf knot can be realized by a Pixton diffeomorphism. D. Pixton proved that diffeomorphisms defined by the standard Hopf knot L0 = {s} × S1 have an energy function (Lyapunov function) whose set of critical points coincide with the chain recurrent set whereas the set of critical points of any Lyapunov function for Pixton diffeomorphism with nontrivial (i.e. non equivalent to the standard) Hopf knot is strictly larger than the chain recurrent set of the diffeomorphism. The Lyapunov function for Pixton diffeomorphism with minimal number of critical points is called the quasi-energy function. In this paper we construct a quasi-energy function for Pixton diffeomorphisms defined by a generalized Mazur *** Codes 37C15, 37D15 © 2023, CC BY.

关键词： Lyapunov functions