检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第9期5卷 4753-4764页

作者： Li, Jun Wang, Huabin Wei, Shicheng Zhou, Jian Shen, Yuankang Tao, Liang Anhui University Anhui Provincial Key Laboratory of Multimodal Cognitive Computation Anhui Hefei230601 China University of Southern Queensland School of Mathematics Physics and Computing Toowoomba4350 Australia

Gabor filters are able to extract texture features from finger vein images from different directions and scales. However, manually crafted Gabor filters have problems such as relatively single direction and scale, and difficulties in parameter adjustment to adapt to specific datasets. To solve these problems, this article proposes a neural network with a learnable variable curvature Gabor (VC-Gabor) convolutional layer. First, the Gabor filter is improved by adding variable curvature to extract information about different curvature degrees in the vein curves. Second, the VC-Gabor filter is designed as a learnable convolutional filter, with parameters updated using neural network back-propagation. This facilitates the enrichment of learned VC-Gabor filter directions, scales, and curvatures, eliminating the need for intricate manual parameter tuning. Finally, we propose adaptive multibranch structures for feature extraction, which are used to enhance the feature extraction capability of the model. Experimental results on publicly available datasets FV-USM and SDUMLA demonstrate that the proposed algorithm improves recognition accuracy and reduces the equal error rate (EER), thereby substantiating the effectiveness of the approach. © 2020 IEEE.

关键词： Gabor filters

来源：评论

学校读者我要写书评

暂无评论

AGDAE: Attention-Gated Denoise Autoencoder for Detecting Imperceptible Adversarial Examples 3rd

AGDAE: Attention-Gated Denoise Autoencoder for Detecting Im...

引用

3rd International Conference on Machine Learning, Cloud computing and Intelligent Mining, MLCCIM 2024

作者： Gao, Shuai Wu, Mengjiang Lv, Wanli Anhui Provincial Key Laboratory of Multimodal Cognitive Computation Anhui University Hefei230000 China

ISBN: (纸本)9789819624676

Deep Neural Networks (DNNs) have shown outstanding performance on a variety of tasks. However, their vulnerability to adversarial examples has become a significant concern in recent years. Of particular concern are imperceptible adversarial examples, which present a latent threat to safety-critical applications. In this work, we introduce an Attention-Gated Denoising Autoencoder model (AGDAE) designed to effectively detect imperceptible adversarial attacks. Our model utilizes innovative Attention-Gated Convolutional Blocks to enhance feature extraction and selection, thereby improving the model’s sensitivity to minute perturbations. By using an autoencoder model, our network is able to remove adversarial noise by reconstructing input images. Additionally, we combine a target-oriented detection framework to verify label consistency between reconstructed and original images, further enhancing adversarial example detection. Experiments on datasets such as CIFAR-10, and ImageNet validate the effectiveness of AGDAE in detecting imperceptible adversarial examples, maintaining a high detection accuracy even against highly sophisticated adversarial attacks. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Purifying Adversarial Perturbations Based on A Text-Guided Diffusion Model 5

Purifying Adversarial Perturbations Based on A Text-Guided D...

引用

5th International Conference on Computer Vision and Computational Intelligence, CVCI 2024

作者： Zhu, Shihan Lyu, Wanli Anhui Provincial Key Laboratory of Multimodal Cognitive Computation Anhui University Hefei China

ISBN: (数字)9781510680067

ISBN: (纸本)9781510680050

Deep neural networks (DNNs) have found wide applications in various domains. However, recent research has revealed the vulnerability of DNNs to adversarial examples. Existing adversarial attack methods can easily mislead the models. Moreover, while traditional denoising techniques effectively deter certain attacks, they have limitations. To address this, We propose Text-guided Diffusion Model Purification (TGDP), an adversarial perturbation purification method based on diffusion *** method preprocesses input images to purify adversarial perturbations. TGDP employs Protogen x3.4 (Photorealism) Official Release as a diffusion model for conditional image generation. During the generation process, text information is incorporated to enhance control over the diffusion model instead of relying entirely on the internal randomness of the model. By iteratively adding Gaussian noise to disrupt the adversarial examples and reversing the noise addition process to restore the image afterward, we can completely eliminate carefully crafted perturbations, achieving the purification objective. Extensive experiments on the ImageNet dataset against common adversarial attacks demonstrate that TGDP outperforms other defense methods applied to the ImageNet dataset. © 2024 SPIE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

An approach for microservices-oriented migration based on business information and GNN

An approach for microservices-oriented migration based on bu...

引用

2024 International Conference on Computer Network Security and Software Engineering, CNSSE 2024

作者： Yang, Yantao Zhang, Cheng School of Computer Science and Technology Anhui University Hefei China Anhui Provincial Key Laboratory of Multimodal Cognitive Computing Hefei China

ISBN: (纸本)9781510680234

Microservices are popular because they have the advantages of loose coupling, low cohesion, and small and autonomous compared to monolithic systems. And when it comes to cloud deployment, it also has a natural advantage. As a result, more practitioners today choose to refactor monolithic applications into one or more microservices, each of which contains a set of partitions composed of components that point to some specific function of the original monolith, so that the entire software system can be represented by a graph, each component can be regarded as a node, and the dependencies between components can be regarded as edges between nodes. In recent years, there has been an approach to using graph neural networks(GNN) to help migrate from monoliths to microservices. However, due to the differences in the research field, some developers rely heavily on the source code of the monolithic system as an important basis for migration, but in the software field, the business information of the project also has a strong symbol for different microservices. Therefore, we will use GNN to comprehensively migrate microservices from the perspectives of business information and source code in the project. The findings indicate that our methodology is superior in efficiency compared to the migration of single features extracted solely from source code. © 2024 SPIE.

关键词： Application programs

来源：评论

学校读者我要写书评

暂无评论

Breaking Modality Gap in RGBT Tracking: Coupled Knowledge Distillation 24

Breaking Modality Gap in RGBT Tracking: Coupled Knowledge Di...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Lu, Andong Zhao, Jiacong Li, Chenglong Xiao, Yun Luo, Bin Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University AnHui HeFei China Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Artificial Intelligence Anhui University Anhui HeFei China Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Artificial Intelligence Anhui University Anhui HeFei China Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Anhui HeFei China

ISBN: (纸本)9798400706868

Modality gap between RGB and thermal infrared (TIR) images is a crucial issue but often overlooked in existing RGBT tracking methods. It can be observed that modality gap mainly lies in the image style difference. In this work, we propose a novel Coupled Knowledge Distillation framework called CKD, which pursues common styles of different modalities to break modality gap, for high performance RGBT tracking. In particular, we introduce two student networks and employ the style distillation loss to make their style features consistent as much as possible. Through alleviating the style difference of two student networks, we can break modality gap of different modalities well. However, the distillation of style features might harm to the content representations of two modalities in student networks. To handle this issue, we take original RGB and TIR networks as the teachers, and distill their content knowledge into two student networks respectively by the style-content orthogonal feature decoupling scheme. We couple the above two distillation processes in an online optimization framework to form new feature representations of RGB and thermal modalities without modality gap. In addition, we design a masked modeling strategy and a multi-modal candidate token elimination strategy into CKD to improve tracking robustness and efficiency respectively. Extensive experiments on five standard RGBT tracking datasets validate the effectiveness of the proposed method against state-of-the-art methods while achieving the fastest tracking speed of 96.4 FPS. © 2024 ACM.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Multi-Query Vehicle Re-Identification: Viewpoint-Conditioned Network, Unified Dataset and New Metric

引用

IEEE Transactions on Image Processing 2023年 32卷 5948-5960页

作者： Zheng, Aihua Zhang, Chaobin Li, Chenglong Tang, Jin Tan, Chang Anhui University Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Artificial Intelligence Hefei230601 China Anhui University Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Hefei230601 China Iflytek Company Ltd. Hefei230088 China

Existing vehicle re-identification methods mainly rely on the single query, which has limited information for vehicle representation and thus significantly hinders the performance of vehicle Re-ID in complicated surveillance networks. In this paper, we propose a more realistic and easily accessible task, called multi-query vehicle Re-ID, which leverages multiple queries to overcome viewpoint limitation of single one. Based on this task, we make three major contributions. First, we design a novel viewpoint-conditioned network (VCNet), which adaptively combines the complementary information from different vehicle viewpoints, for multi-query vehicle Re-ID. Moreover, to deal with the problem of missing vehicle viewpoints, we propose a cross-view feature recovery module which recovers the features of the missing viewpoints by learnt the correlation between the features of available and missing viewpoints. Second, we create a unified benchmark dataset, taken by 6142 cameras from a real-life transportation surveillance system, with comprehensive viewpoints and large number of crossed scenes of each vehicle for multi-query vehicle Re-ID evaluation. Finally, we design a new evaluation metric, called mean cross-scene precision (mCSP), which measures the ability of cross-scene recognition by suppressing the positive samples with similar viewpoints from the same camera. Comprehensive experiments validate the superiority of the proposed method against other methods, as well as the effectiveness of the designed metric in the evaluation of multi-query vehicle Re-ID. The codes and dataset are available at: https://***/zhangchaobin001/VCNet © 1992-2012 IEEE.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

Transformer-based Multi-level Feature Extraction for Finger Vein Identification 23

Transformer-based Multi-level Feature Extraction for Finger ...

引用

15th International Conference on Digital Image Processing, ICDIP 2023

作者： Zhang, Junwei Wang, Huabin Wen, Yumeng Tao, Liang Anhui University Anhui Provincial Key Laboratory of Multimodal Cognitive Computation China

ISBN: (纸本)9798400708237

Currently, deep learning methods are being used to good effect in implementing finger vein (FV) recognition algorithms. However, increasingly large volumes of data can lead to problems in which FV recognition based on lightweight neural networks are unable to fit the data well, causing accuracy degradation. Therefore, this paper proposes a transformer-based network model for FV recognition. First, a spatially information-enhanced Image-to-Tokens (SeI2T) module is proposed, which enhances the information of FV textures and extracts patches embedding from generated low-level features, instead of directly from the original image. Secondly, a feedforward neural network structure formed by the combination of channel and spatially enhanced feedforward neural networks was designed, which enhances local information extraction in two dimensions. Finally, the use of Layer-wise Class-token Attention (LCA) in the FV network structure allows the integration of class-token information from different layers. To evaluate the model performance and generality, four publicly available FV datasets are used in the experiments. The experiments show that the method proposed in this paper is highly competitive. © 2023 ACM.

关键词： Feedforward neural networks

来源：评论

学校读者我要写书评

暂无评论

Efficient and High-Quality Black-Box Face Reconstruction Attack 23

Efficient and High-Quality Black-Box Face Reconstruction Att...

引用

15th International Conference on Digital Image Processing, ICDIP 2023

作者： Liang, Yu Wang, Huabin Cao, Shuo Wang, Junwu Tao, Liang Zhang, Jianyu Anhui Provincial Key Laboratory of Multimodal Cognitive Computation Anhui University China

ISBN: (纸本)9798400708237

Recent studies have shown that machine learning as a service is susceptible to reconstruction attacks that would expose users' privacy. When it comes to face recognition systems, privacy leakage could incur unpredictable effects on confidential or financial matters. This paper focuses on black-box reconstruction attacks on face recognition systems, including face verification and face identification applications. Considering a face recognition system in the real world, the adversary only has access to the similarity score of a query compared to a certain ID. We build our method based on a pretrained StyleGAN face generator and optimize its latent code to obtain a face image that maximizes the similarity score. Given the similarity score alone, we adopt zeroth-order optimization to estimate the gradients faithfully. Our method can attack 1:1 verification system with efficient and high-quality. To validate the effectiveness of the proposed method, we perform extensive experiments on face recognition systems, and reveal their risks of privacy leakage. © 2023 ACM.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Multiscale spatio-temporal hypergraph convolutional networks for 3D human pose estimation 16

Multiscale spatio-temporal hypergraph convolutional networks...

引用

16th International Conference on Digital Image Processing, ICDIP 2024

作者： Chen, Xiuning Wang, Huabin Dai, Shulin Yuan, Hongrui Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Anhui Hefei230601 China

ISBN: (数字)9781510682917

ISBN: (纸本)9781510682900

In the domain of human pose estimation, graph convolutional networks have exhibited notable performance enhancements owing to their adeptness in naturally modeling the representation of human poses through graph structures. However, prevailing methods predominantly concentrate on the local physical connections between joints, overlooking higher-order neighboring nodes. This limitation curtails their ability to effectively exploit relationships between distant joints. This article introduces a Multiscale Spatio-Temporal Hypergraph Convolutional Network (MST-HCN) designed to capture spatio-temporal information and higher-order dependencies. MST-HCN encompasses two pivotal modules: Multiscale Hypergraph Convolution (MHCN) and Multiscale Temporal Convolution (MTCN). The MHCN module represents human poses as hypergraphs in various forms, enabling the comprehensive extraction of both local and global structural information. In contrast to traditional stride convolutions, MTCN leverages multiple branches to learn important frames based on their significance, thereby filtering out redundant frames. Experimental results underscore that MST-HCN surpasses state-of-the-art methods in benchmark tests such as Human3.6M and *** particular, our proposed MST-HCN method boosts performance by 1.5% and 0.9%, compared to the closest latest method, using detected 2D poses and ground truth 2D settings respectively. © 2024 SPIE.

关键词： Human form models

来源：评论

学校读者我要写书评

暂无评论

Enhancing Video Quality Assessment through Semantic Guidance 4

Enhancing Video Quality Assessment through Semantic Guidance

引用

4th International Symposium on Artificial Intelligence and Intelligent Manufacturing, AIIM 2024

作者： Wang, Futian Li, Zeyu School of Computer Science and Technology Anhui University Hefei China Anhui Provincial Key Laboratory of Multimodal Cognitive Computation Hefei China

ISBN: (纸本)9798331541729

With the rapid advancement of network and information technologies, user-generated content (UGC) platforms like TikTok have become essential mainstream media channels. However, video quality often varies significantly due to factors during shooting, compression, and transmission, inconveniencing users. While existing methods assess video quality using objective standards, human subjective perception remains crucial. This paper introduces a simple and effective no-reference video quality assessment model that integrates human perception into the complex video generation process to enhance UGC quality evaluation. We develop a trainable FastVQA branch to extract technical features and incorporate a ConvNeXt branch to capture semantic features. These features are combined and processed through a multi-layer perceptron (MLP) network to predict video quality scores. Our findings demonstrate that incorporating semantic features allows the network to better leverage human perception of video content quality, thereby improving the accuracy of technical assessments. This method not only optimizes traditional quality assessment models but also offers a new research direction, highlighting the importance of human perception in automated video quality evaluation. © 2024 IEEE.

关键词： Semantic Guidance UGC Video Quality Assessment

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：