检索结果-内蒙古大学图书馆

7th International Conference on network analysis, NET 2017

作者： Koldanov, Petr A. Laboratory of Algorithms and Technologies for Network Analysis National Research University Higher School of Economics Bolshaya Pecherskaya 25/12 Nizhny Novgorod603155 Russia

Invariance properties of statistical procedures for threshold graph identification are considered. An optimal procedure in the class of invariant multiple decision procedures is constructed. © Springer Internatio... 详细信息

ISBN: (纸本)9783319962467

关键词： Random variables

来源：评论

学校读者我要写书评

暂无评论

Compressing deep convolutional neural networks in visual emotion recognition

Compressing deep convolutional neural networks in visual emo...

引用

2017 International Conference Information Technology and Nanotechnology. Session Image Processing, Geoinformation Technology and Information Security, IPGTIS-ITNT 2017

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

In this paper, we consider the problem of insufficient runtime and memory-space complexities of deep convolutional neural networks for visual emotion recognition. A survey of recent compression methods and efficient neural networks architectures is provided. We experimentally compare the computational speed and memory consumption during the training and the inference stages of such methods as the weights matrix decomposition, binarization and hashing. It is shown that the most efficient optimization can be achieved with the matrices decomposition and hashing. Finally, we explore the possibility to distill the knowledge from the large neural network, if only large unlabeled sample of facial images is available.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Fuzzy analysis and Deep Convolution Neural networks in Still-to-video Recognition

引用

Optical Memory and Neural networks (Information Optics) 2018年第1期27卷 23-31页

作者： Savchenko, A.V. Belova, N.S. Savchenko, L.V. 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 Moscow Russia Nizhny Novgorod State Linguistic University Nizhny Novgorod Russia

We discuss the video classification problem with the matching of feature vectors extracted using deep convolutional neural networks from each frame. We propose the novel recognition method based on representation of each frame as a sequence of fuzzy sets of reference classes whose degrees of membership are defined based on asymptotic distribution of the Kullback–Leibler information divergence and its relation with the maximum likelihood method. In order to increase the classification accuracy, we perform the fuzzy intersection (product triangular norms) of these sets. Experimental study with YTF (YouTube Faces) and IJB-A (IARPA Janus Benchmark A) video datasets and VGGFace, ResFace and LightCNN descriptors shows that the proposed approach allows us to increase the accuracy of recognition by 2–6% comparing with the known classification methods. © 2018, Allerton Press, Inc.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

Effective face recognition based on anomaly image detection and sequential analysis of neural descriptors 9

Effective face recognition based on anomaly image detection ...

引用

9th IEEE International Conference on Information Technology and Nanotechnology, ITNT 2023

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

ISBN: (纸本)9798350397338

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. © 2023 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Improved Credit Scoring Model with Hyperparameter Optimization 23rd

Improved Credit Scoring Model with Hyperparameter Optimizati...

引用

23rd International Conference on Mathematical Optimization Theory and Operations Research, MOTOR 2024

作者： Marciano, Chiara Guarracino, Mario Rosario Bernhardt, Brian Daniel University of Cassino and Southern Lazio Cassino Italy Laboratory of Algorithms and Technologies for Network Analysis National Research University Higher School of Economics - Nizhny Novgorod Nizhny Novgorod Russia

ISBN: (纸本)9783031733642

This article investigates the application of machine learning techniques for predicting corporate default risk. In the credit scoring domain, the class imbalance problem is prevalent, with defaulted cases typically being much less numerous than non-defaulted ones. To address challenges posed by unbalanced datasets, various calibration methodologies, including data sampling strategies and Synthetic Minority Oversampling Technique (SMOTE), are explored to identify the most effective strategy for the specific case. Additionally, hyperparameter tuning plays a crucial role in enhancing machine learning model performance. Therefore, we employ hyperparameter optimization techniques such as Grid Search, Random Search, Bayesian Optimization, and Adaptive Particle Swarm Optimization. The primary objective is to compare these techniques and determine the optimal strategy for predicting company default events. Our evaluation incorporates standard parameters such as accuracy, balanced accuracy, specificity, sensitivity, and F1 score. Another factor to consider to discriminate the various approaches is the execution time, to be able to develop models that can be implemented in market products. The experimental results reveal which approaches result in significantly improved classification performance. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Photo privacy detection based on text classification and face clustering 6

Photo privacy detection based on text classification and fac...

引用

6th International Conference Information Technology and Nanotechnology. Session Image Processing and Earth Remote Sensing, ITNT-IPERS 2020

作者： Kopeykina, Lyudmila Savchenko, Andrey 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

Nowadays, the photo privacy detection is becoming an acute task due to a wide spread of mobile devices with photos published on social networks. As a photo might contain private or sensitive data, there is an urgent need to accurately determine them and impose restrictions on their processing. In this paper we focus on the task of personal data detection in a photo gallery. A novel two-stage approach is proposed. At first, text of scanned documents is processed based on an EAST text detector, and extracted text is recognized using Tesseract and neural network classifier. At the second stage, face clustering is implemented for the remaining photos to identify large groups of people (friends, relatives) whose photos also refer to personal data and must be processed directly on a mobile device. The remaining images can be sent to a remote server for processing with higher accuracy. The experimental results of text recognition and face clustering methods using various convolutional networks for facial features extraction are presented. Copyright © 2020 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0)

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

The video-based age and gender recognition with convolution neural networks 7th

The video-based age and gender recognition with convolution ...

引用

7th International Conference on network analysis, NET 2017

作者： Kharchevnikova, Angelina S. Savchenko, Andrey V. National Research University Higher School of Economics Nizhniy Novgorod Russia Laboratory of Algorithms and Technologies for Network Analysis National Research University Higher School of Economics Nizhny Novgorod Russia

ISBN: (纸本)9783319962467

The paper reviews the problem of age and gender recognition methods for video data using modern deep convolutional neural networks. We present the comparative analysis of classifier fusion algorithms to aggregate decisions for individual frames. We implemented the video-based recognition system with several aggregation methods to improve the age and gender identification accuracy. The experimental comparison of the proposed approach with traditional simple voting using IJB-A, Indian Movies, and Kinect datasets is provided. It is demonstrated that themost accurate decisions are obtained using the geometricmean and mathematical expectation of the outputs at softmax layers of the convolutional neural networks for gender recognition and age prediction, respectively. © Springer International Publishing AG, part of Springer Nature 2018.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

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

Automatic Privacy Detection in Scanned Document Images Based...

引用

2019 International Russian Automation Conference, RusAutoCon 2019

作者： Kopeykina, Lyudmila Savchenko, Andrey V. 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

ISBN: (纸本)9781728102658

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. © 2019 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

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

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

引用

2020 International Russian Automation Conference, RusAutoCon 2020

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

ISBN: (纸本)9781728161303

In this paper, we address the problem of detecting small objects on high-quality X-ray imagesusing deep neural networks. We propose to implement the two-stage approach, in which, firstly, input image issplit into partially overlapping blocks to make small objects more discriminative for detection. Secondly, the small blocks are fed into conventional single-shot detectors. These detectors are trained using the blocks of the training images extracted by the same *** datasets of X-ray images from the customs inspection complex are examined in the experimental study. It was shown thatthe proposed algorithm with data augmentationleads tomore precise results when compared to the conventional technique:ourmethod outperforms the traditional approach by 5.4 - 25.7% depending on the type of used backbone convolutional neural network. © 2020 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Sport teams logo detection based on deep local features

Sport teams logo detection based on deep local features

引用

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

作者： Kuznetsov, Andrey Savchenko, Andrey Geoinformatics and Information Security Department Samara National Research University Samara Russia Laboratory of Algorithms and Technologies for Network Analysis National Research University Higher School of Economics Nizhny Novgorod Russia

ISBN: (纸本)9781728144016

Logo detection in an unconstrained environment is a challenging task. The problem lies in the small size of logos that are to be detected and different representations of logos due to the view angle, rotation angle and perspective distortions. We provide a part of a new labelled SportLogo dataset for research. In this work we also propose a solution to the task of sport logos detection for the whole range of MLB, NBA and HNL teams. Ambiguity appears when developing the detection algorithm because of a huge number of occlusions and logo view changes due to wrinkle uniform during hockey games. Another problem is logo style changes for some teams. First, we propose an approach based on local descriptors calculation (SIFT, SURF, ORB, BRISK, FREAK, AKAZE) and provide the results of conducted experiments. Second, we propose an approach based on deep local features (DELF), which are pre-Trained on Google Landmarks dataset, and compare them with classic local features. Experimental research showed that BRISK features provide the highest quality values on the labelled NHL teams dataset. © 2019 IEEE.

关键词： Sports

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：