检索结果-内蒙古大学图书馆

EmotiEffNets for Facial Processing in Video-based Valence-Arousal Prediction, Expression Classification and Action Unit Detection

学校读者我要写书评

暂无评论

EmotiEffNets for Facial Processing in Video-based Valence-Ar...

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

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

In this article, the pre-trained convolutional networks from the EmotiEffNet family for frame-level feature extraction are used for downstream emotion analysis tasks from the fifth Affective Behavior analysis in-the-wild (ABAW) competition. In particular, we propose an ensemble of a multi-layered perceptron and the LightAutoML-based classifier. The post-processing by smoothing the results for sequential frames is implemented. Experimental results for the large-scale Aff-Wild2 database demonstrate that our model is much better than the baseline facial processing using VGGFace And ResNet. For example, our macro-averaged F1-scores of facial expression recognition and action unit detection on the testing set are 11-13% greater. Moreover, the concordance correlation coefficients for valence/arousal estimation are up to 30% higher when compared to the baseline.

关键词：

Detection of sensitive textual information in user photo albums on mobile devices

学校读者我要写书评

暂无评论

Detection of sensitive textual information in user photo alb...

2019 International Multi-Conference on Engineering, Computer and Information Sciences, SIBIRCON 2019

作者： Myasnikov, Evgeny Savchenko, Andrey Samara University Geoinformatics and Information Security Department Samara Russia Samsung-PDMI Joint AI Center St. Petersburg Department of Steklov Institute of Mathematics Russia Laboratory of Algorithms and Technologies for Network Analysis National Research University Higher School of Economics Nizhny Novgorod Russia

ISBN: (纸本)9781728144016

The need to identify and delete sensitive textual information in images arises in many areas. In this paper, we propose a two-step method in order to detect sensitive textual information in images or video. This method consists of text detection and recognition in an input image with the subsequent identification of sensitive words. We propose to include lexical information in the final decision to provide more stable performance in unconstrained environments. The method is implemented in a mobile application. An experimental study of several text recognition libraries is provided for well-known datasets (ICDAR 2003, KAIST, SVT, CBDAR 2011, DIQA and MIDV-500). © 2019 IEEE.

关键词： Data privacy

Pattern-based heuristic for the cell formation problem in group technology

学校读者我要写书评

暂无评论

Pattern-based heuristic for the cell formation problem in gr...

作者： Batsyn, Mikhail Bychkov, Ilya Goldengorin, Boris Pardalos, Panos Sukhov, Pavel Laboratory of Algorithms and Technologies for Network Analysis The National Research University Higher School of Economics 136 Rodionova Street Nizhny Novgorod Russian Federation 603093 Russia Center of Applied Optimization University of Florida 401 Weil Hall 116595 Gainesville FL 32611-6595 United States

ISBN: (纸本)9781461455738

In this chapter we introduce a new pattern-based approach within the linear assignment model with the purpose to design heuristics for a combinatorial optimization problem (COP). We assume that the COP has an additive (separable) objective function and the structure of a feasible (optimal) solution to the COP is predefined by a collection of cells (positions) in an input file. We define a pattern as a collection of positions in an instance problem represented by its input file (matrix). We illustrate the notion of pattern by means of some well-known problems in COP, among them are the linear ordering problem (LOP) and cell formation problem (CFP), just to mention a couple. The CFP is defined on a Boolean input matrix, the rows of which represent machines and columns - parts. The CFP consists in finding three optimal objects: a block-diagonal collection of rectangles, a row (machines) permutation, and a column (parts) permutation such that the grouping efficacy is maximized. The suggested heuristic combines two procedures: the pattern-based procedure to build an initial solution and an improvement procedure to obtain a final solution with high grouping efficacy for the CFP. Our computational experiments with the most popular set of 35 benchmark instances show that our heuristic outperforms all well-known heuristics and returns either the best known or improved solutions to the CFP. © Springer Science+Business Media New York 2013.

关键词： Cytology

An efficient exact model for the cell formation problem with a variable number of production cells

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Bychkov, Ilya Batsyn, Mikhail Laboratory of Algorithms and Technologies for Network Analysis National Research University Higher School of Economics 136 Rodionova Nizhniy Novgorod603093 Russia

The Cell Formation Problem has been studied as an optimization problem in manufacturing for more than 90 years. It consists of grouping machines and parts into manufacturing cells in order to maximize loading of cells and minimize movement of parts from one cell to another. Many heuristic algorithms have been proposed which are doing well even for large-sized instances. However, only a few authors have aimed to develop exact methods and most of these methods have some major restrictions such as a fixed number of production cells for example. In this paper we suggest a new mixed-integer linear programming model for solving the cell formation problem with a variable number of manufacturing cells. The popular grouping efficacy measure is used as an objective function. To deal with its fractional nature we apply the Dinkelbach approach. Our computational experiments are performed on two testsets: The first consists of 35 well-known instances from the literature and the second contains 32 instances less popular. We solve these instances using CPLEX software. Optimal solutions have been found for 63 of the 67 considered problem instances and several new solutions unknown before have been obtained. The computational times are greatly decreased comparing to the state-of-Art approaches. Copyright © 2017, The Authors. All rights reserved.

关键词： Cellular manufacturing

Reliability of MST identification in correlation-based market networks

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Kalyagin, Valeriy A. Koldanov, A.P. Koldanov, P.A. National Research University Higher School of Economics Laboratory of Algorithms and Technologies for Network Analysis 136 Rodionova street Nizhny Novgorod603093 Russia

Maximum spanning tree (MST) is a popular tool in market network analysis. Large number of publications are devoted to the MST calculation and it's interpretation for particular stock markets. However, much less attention is payed in the literature to the analysis of uncertainty of obtained results. In the present paper we suggest a general framework to measure uncertainty of MST identification. We study uncertainty in the framework of the concept of random variable network (RVN). We consider different correlation based networks in the large class of elliptical distributions. We show that true MST is the same in three networks: Pearson correlation network, Fechner correlation network, and Kendall correlation network. We argue that among different measures of uncertainty the FDR (False Discovery Rate) is the most appropriated for MST identification. We investigate FDR of Kruskal algorithm for MST identification and show that reliability of MST identification is different in these three networks. In particular, for Pearson correlation network the FDR essentially depends on distribution of stock returns. We prove that for market network with Fechner correlation the FDR is non sensitive to the assumption on stock's return distribution. Some interesting phenomena are discovered for Kendall correlation network. Our experiments show that FDR of Kruskal algorithm for MST identification in Kendall correlation network weakly depend on distribution and at the same time the value of FDR is almost the best in comparison with MST identification in other networks. These facts are important in practical *** Codes 68T37, 62-07, C44 © 2021, CC BY.

关键词： Random variables

Heuristic for maximizing grouping efficiency in the cell formation problem 1

学校读者我要写书评

暂无评论

6th International Conference on network analysis, NET 2016

作者： Bychkov, Ilya Batsyn, Mikhail Pardalos, Panos M. Laboratory of Algorithms and Technologies for Network Analysis National Research University Higher School of Economics 136 Rodionova Street Nizhny Novgorod603093 Russia Center for Applied Optimization University of Florida 401 Weil Hall P.O. Box 116595 Gainesville32611-6595 United States

ISBN: (数字)9783319568294

ISBN: (纸本)9783319568287

In our paper, we consider the Cell Formation Problem in Group Technology with grouping efficiency as an objective function. We present a heuristic approach for obtaining high-quality solutions of the CFP. The suggested heuristic applies an improvement procedure to obtain solutions with high grouping efficiency. This procedure is repeated many times for randomly generated cell configurations. Our computational experiments are performed for popular benchmark instances taken from the literature with sizes from 10×20 to 50×150. Better solutions unknown before are found for 23 instances of the 24 considered. The preliminary results for this paper are available in Bychkov et al. (Models, algorithms, and technologies for network analysis, Springer, NY, vol. 59, pp. 43–69, 2013, [7]). © Springer International Publishing AG 2017.

关键词： Benchmarking

Detection of Sensitive Textual Information in User Photo Albums on Mobile Devices

学校读者我要写书评

暂无评论

Detection of Sensitive Textual Information in User Photo Alb...

IEEE Region 8 International Conference on Computational technologies in Electrical and Electronics Engineering, SIBIRCON

作者： Evgeny Myasnikov Andrey Savchenko Samara University Samara Russia Laboratory of Algorithms and Technologies for Network Analysis National Research University Higher School of Economics Nizhny Novgorod Russia

关键词：

Using modular decomposition technique to solve the maximum clique problem

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Utkina, Irina Laboratory of Algorithms and Technologies for Network Analysis Higher School of Economics in Nizhni Novgorod 136 Rodionova Str. N.Novgorod Russia

In this article we use the modular decomposition technique for exact solving the weighted maximum clique problem. Our algorithm takes the modular decomposition tree from the paper of Tedder et. al. and finds solution recursively. Also, we propose algorithms to construct graphs with modules. We show some interesting results, comparing our solution with Ostergards algorithm on DIMACS benchmarks and on generated graphs Copyright © 2017, The Authors. All rights reserved.

关键词： Trees (mathematics)

Comparison of statistical procedures for Gaussian graphical model selection

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Grechikhin, Ivan S. National Research University Higher School of Economics Laboratory of Algorithms and Technologies for Network Analysis 136 Rodionova St Nizhny Novgorod603093 Russia

Graphical models are used in a variety of problems to uncover hidden structures. There is a huge number of different identification procedures, constructed for different purposes. However, it is important to research different properties of such procedures and compare them in order to find out the best procedure or the best use case for some specific procedure. In this paper, some statistical identification procedures are compared using different measures, such as Type I and Type II errors, ROC AUC. Copyright © 2017, The Authors. All rights reserved.

关键词： Statistical methods