检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Zhong, Xiaojing Huang, Xinyi Wu, Zhonghua Lin, Guosheng Wu, Qingyao School of Software Engineering South China University of Technology China School of Computer Science and Engineering Nanyang Technological University Singapore Key Laboratory of Big Data and Intelligent Robot Ministry of Education China Peng Cheng Laboratory China SenseTime Research China

Makeup transfer is a process of transferring the makeup style from a reference image to the source image, while preserving the source image’s identity. In addition to achieving fine-grained control over the makeup transfer, incorporating semantic alignment into the transformation is crucial, as the poses of the reference and source images are often inconsistent. We propose a novel Semantic-guided Alignment and Region-Adaptive normalization framework (SARA) to effectively transfer makeup styles under misaligned poses, offering flexible control to meet the demands of real-world applications, such as partial transfer, intensity adjustment, and makeup removal. Specifically, SARA comprises three modules: Firstly, we propose a semantic-guided alignment module to explicitly construct dense correspondence between the reference image and the target semantic map, employing unbalanced optimal transport matching to handle semantic region mismatches. Secondly, a region-adaptive normalization module is responsible for dynamically combining the warped style features with shape-independent style codes obtained by region-wise average pooling, mitigating feature loss during the alignment. Lastly, a makeup fusion module progressively fuses the identity features with the makeup styles to render the final output image. Furthermore, we combine optimal transport with histogram matching to generate the pseudo ground truth, which is used to facilitate the transfer in terms of both spatial alignment and color distribution. Experimental results show that our proposed SARA outperforms existing methods on two public datasets. © 2023, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Semantic-Constraint Matching Transformer for Weakly Supervised Object Localization

arXiv

引用

arXiv 2023年

作者： Cao, Yiwen Su, Yukun Wang, Wenjun Liu, Yanxia Wu, Qingyao The School of Software Engineering South China University of Technology Guangzhou510640 China The Key Laboratory of Big Data and Intelligent Robot Ministry of Education Guangzhou China The School of Computer Science and Engineering Nanyang Technological University Singapore The Pazhou Lab Guangzhou China

Weakly supervised object localization (WSOL) strives to learn to localize objects with only image-level supervision. Due to the local receptive fields generated by convolution operations, previous CNN-based methods suffer from partial activation issues, concentrating on the object's discriminative part instead of the entire entity scope. Benefiting from the capability of the self-attention mechanism to acquire long-range feature dependencies, Vision Transformer has been recently applied to alleviate the local activation drawbacks. However, since the transformer lacks the inductive localization bias that are inherent in CNNs, it may cause a divergent activation problem resulting in an uncertain distinction between foreground and background. In this work, we proposed a novel Semantic-Constraint Matching Network (SCMN) via transformer to converge on the divergent activation. Specifically, we first propose a local patch shuffle strategy to construct the image pairs, disrupting local patches while guaranteeing global consistency. The paired images that contain the common object in spatial are then fed into the Siamese network encoder. We further design a semantic-constraint matching module, which aims to mine the co-object part by matching the coarse class activation maps (CAMs) extracted from the pair images, thus implicitly guiding and calibrating the transformer network to alleviate the divergent activation. Extensive experimental results conducted on two challenging benchmarks including CUB-200-2011 and ILSVRC datasets show that our method can achieve the new state-of-the-art performance and outperform the previous method by a large margin. Copyright © 2023, The Authors. All rights reserved.

关键词： Chemical activation

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous Software Effort Estimation via Cascaded Adversarial Auto-Encoder 1

引用

21st International Conference on Parallel and Distributed Computing, Applications, and Technologies, PDCAT 2020

作者： Qi, Fumin Jing, Xiao-Yuan Zhu, Xiaoke Jia, Xiaodong Cheng, Li Dong, Yichuan Fang, Ziseng Ma, Fei Feng, Shengzhong College of Computer Science and Software Engineering Shenzhen University Shenzhen China School of Computer Wuhan University Wuhan China Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China National Supercomputing Center in Shenzhen Guangzhou Guangdong China School of Computer Science Qufu Normal University Rizhao China

ISBN: (数字)9783030692445

ISBN: (纸本)9783030692438

In Software Effort Estimation (SEE) practice, the data drought problem has been plaguing researchers and practitioners. Leveraging heterogeneous SEE data collected by other companies is a feasible solution to relieve the data drought problem. However, how to make full use of the heterogeneous effort data to conduct SEE, which is called as Heterogeneous Software Effort Estimation (HSEE), has not been well studied. In this paper, we propose a HSEE model, called Dynamic Heterogeneous Software Effort Estimation (i.e., DHSEE), which leverages the adversarial auto-encoder and convolutional neural network techniques. Meanwhile, we have investigated the scenario of conducting HSEE with dynamically increasing effort data. Experiments on ten public datasets indicate that our approach can significantly outperform the state-of-the-art HSEE method and other competing methods on both static and dynamic SEE scenarios. © 2021, Springer Nature Switzerland AG.

关键词： Drought

来源：评论

学校读者我要写书评

暂无评论

A Fast Matrix Completion Method Based on Matrix Bifactorization and QR Decomposition

引用

Wireless Communications and Mobile Computing 2023年第1期2023卷

作者： Liu, Qing Peng, Chen Yang, Pei Zhou, Xiancun Liu, Zhengyu School of Electronic and Information Engineering West Anhui University Anhui Lu'an237012 China School of Mathematics and Big Data Anhui University of Science and Technology Anhui Huainan232001 China Department of Computer Technology and Application Qinghai University Qinghai Xining810016 China

The problem of recovering the missing values in an incomplete matrix, i.e., matrix completion, has attracted a great deal of interests in the fields of machine learning and signal processing. A matrix bifactorization method, which is abbreviated as MBF, is a fast method of matrix completion that has a better speed than the traditional nuclear norm minimization methods. However, it may become inaccurate and slow when solving matrices of not low rank. In this paper, an improved fast and accurate MBF method based on Qatar Riyal (QR) decomposition is proposed, which can be called FMBF-QR. On one side, the optimization problem of MBF is improved to be an iteratively reweighted L2,1 norm minimization problem to enhance the accuracy of MBF. On the other side, the minimization problem of FMBF-QR is optimized very efficiently by using QR decomposition for improving the speed of MBF. Sufficient experimental results verify that FMBF-QR can converge with a higher accuracy and a faster speed than the traditional matrix completion methods. © 2023 Qing Liu et al.

关键词： Signal processing

来源：评论

学校读者我要写书评

暂无评论

Classification of Real and Deepfakes Visual Samples with Pre-trained Deep Learning Models 7th

Classification of Real and Deepfakes Visual Samples with Pre...

引用

Proceedings of the 7th International Conference on Advances in Computing and data sciences, ICACDS 2023

作者： Nawaz, Marriam Javed, Ali Nazir, Tahira Khan, Muhammad Attique Rajinikanth, Venkatesan Kadry, Seifedine Department of Software Engineering UET Taxila Taxila47050 Pakistan Department of Computing Riphah International University Islamabad Pakistan Department of Computer Science HITEC University Taxila Pakistan Department of Computer Science and Engineering Division of Research and Innovation Saveetha School of Engineering SIMATS Chennai602105 India Department of Applied Data Science Noroff University College Kristiansand4612 Norway Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon

ISBN: (纸本)9783031379390

Serious security and privacy problems have arisen as a result of significant advancements in the creation of deepfakes. Attackers can easily replace a person’s face with the target person’s face in an image using sophisticated Deep learning (DL) algorithms to spoof their identity. Deepfakes detection algorithms have been proposed in response to the growing concerns about the potential harm caused by deepfakes. However, a reliable deepfakes detector that can keep up with contemporary deepfakes creation techniques is required. In this work, we have proposed an end-to-end methodology for detecting manipulated visual content. We used multiple CNN models i.e., ResNet18, ResNet50, DenseNet65, DenseNet77, and DenseNet100 along with the SVM classifier to compute effective cues from the input facial faces to distinguish between actual and altered content. We have also applied the concept of transfer learning to solve the issue of model over-fitting and improve generalizability against different manipulation algorithms. A comparison study is carried out to evaluate the performance of several feature extractors. Through thorough experiments performed using the Deepfakes Detection Challenge dataset, our results demonstrated that DenseNet100 surpasses the other CNN models by better recognizing deepfakes. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Are Deep Point Cloud Classifiers Suffer From Out-of-distribution Overconfidence Issue?

Are Deep Point Cloud Classifiers Suffer From Out-of-distribu...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Xu He Keke Tang Yawen Shi Yin Li Weilong Peng Peican Zhu Cyberspace Institute of Advanced Technology Guangzhou University Guangzhou China School of Data Science Fudan University Shanghai China School of Computer Science and Cyber Engineering Guangzhou University Guangzhou China School of Artificial Intelligence Optics and Electronics (iOPEN) Northwestern Polytechnical University Xi'an China

3D point cloud perception using deep neural networks (DNNs) has been a trend for various application scenarios. However, the black-box nature of DNNs will bring many hidden risks as in the 2D image field. In this paper, we present a preliminary evaluation on the out-of-distribution (OOD) overconfidence issue of deep point cloud classifiers, which has been proven to exist in deep 2D image classifiers, i.e., OOD inputs will lead to overconfident predictions on predefined categories. We also investigate whether a simple thresholding baseline and two modern OOD detection solutions can handle the issue by detecting OOD samples. Extensive experiments with four representative deep point cloud classifiers train/evaluate on different in/out-of-distribution point clouds validate the severity and knottiness of the OOD overconfidence issue. Our investigation will provide the groundwork for future studies on handling the OOD overconfidence issue of DNN classifiers for 3D point clouds.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Generative adversarial networks enhanced location privacy in 5G networks

引用

science China(Information sciences) 2020年第12期63卷 41-52页

作者： Youyang QU Jingwen ZHANG Ruidong LI Xiaoning ZHANG Xuemeng ZHAI Shui YU School of Information Technology Deakin University School of Computer Science University of Technology Sydney National Institute of Information and Communications Technology (NICT) School of Information and Communication Engineering University of Electronic Science and Technology of China Center of AI and Big Data Southeast Digital Economic Development Institute

5G networks, as the up-to-date communication platforms, are experiencing fast booming. Meanwhile, increasing volumes of sensitive data, especially location information, are being generated and shared using 5G networks for various purposes ceaselessly. Location and trajectory information in the published data has always been and will keep courting risks and attacks by malicious adversaries. Therefore, there are still privacy leakage threats by simply sharing the original data, especially data with location information, due to the short cover range of 5G signal tower. To better address these issues, we proposed a generative adversarial networks(GAN) enhanced location privacy protection model to cloak the location and even trajectory information. We use posterior sampling to generate a subset of data, which is proved complying with differential privacy requirements from the end device side. After that, a data augmentation algorithm modified from classic GAN is devised to generate a series of privacy-preserving full-sized synthetic data from the central server side. With the synthetic data generated from a real-world dataset, we demonstrate the superiority of the proposed model in terms of location privacy protection, data utility, and prediction accuracy.

关键词： 5G privacy preservation generative adversarial nets differential privacy

来源：评论

学校读者我要写书评

暂无评论

Geometric Distortion Guided Transformer for Omnidirectional Image Super-Resolution

arXiv

引用

arXiv 2024年

作者： Yang, Cuixin Dong, Rongkang Xiao, Jun Zhang, Cong Lam, Kin-Man Zhou, Fei Qiu, Guoping Department of Electrical and Electronic Engineering The Hong Kong Polytechnic University Hong Kong College of Electronic and Information Engineering Shenzhen University Shenzhen518060 China Guangdong-Hong Kong Joint Laboratory for Big Data Imaging and Communication Shenzhen518060 China School of Computer Science University of Nottingham NottinghamNG8 1BB United Kingdom School of Computer Science University of Nottingham Ningbo315100 China

As virtual and augmented reality applications gain popularity, omnidirectional image (ODI) super-resolution has become increasingly important. Unlike 2D plain images that are formed on a plane, ODIs are projected onto spherical surfaces. Applying established image super-resolution methods to ODIs, therefore, requires performing equirectangular projection (ERP) to map the ODIs onto a plane. ODI super-resolution needs to take into account geometric distortion resulting from ERP. However, without considering such geometric distortion of ERP images, previous methods only utilize a limited range of pixels and may easily miss self-similar textures for reconstruction. In this paper, we introduce a novel Geometric Distortion Guided Transformer for Omnidirectional image Super-Resolution (GDGT-OSR). Specifically, a distortion modulated rectangle-window self-attention mechanism, integrated with deformable self-attention, is proposed to better perceive the distortion and thus involve more self-similar textures. Distortion modulation is achieved through a newly devised distortion guidance generator that produces guidance for the rectangular windows by exploiting the variability of distortion across latitudes. Furthermore, we propose a dynamic feature aggregation scheme to adaptively fuse the features from different self-attention modules. We present extensive experimental results on public datasets and show that the new GDGT-OSR outperforms methods in existing literature. Copyright © 2024, The Authors. All rights reserved.

关键词： Image resolution

来源：评论

学校读者我要写书评

暂无评论

Amplitude-Varying Perturbation for Balancing Privacy and Utility in Federated Learning

arXiv

引用

arXiv 2023年

作者： Yuan, Xin Ni, Wei Ding, Ming Wei, Kang Li, Jun Poor, H. Vincent Data61 CSIRO Sydney Australia The School of Electrical and Optical Engineering Nanjing University of Science and Technology Nanjing210094 China The Department of Electrical and Computer Engineering Princeton University PrincetonNJ08544 United States

While preserving the privacy of federated learning (FL), differential privacy (DP) inevitably degrades the utility (i.e., accuracy) of FL due to model perturbations caused by DP noise added to model updates. Existing studies have considered exclusively noise with persistent root-mean-square amplitude and overlooked an opportunity of adjusting the amplitudes to alleviate the adverse effects of the noise. This paper presents a new DP perturbation mechanism with a time-varying noise amplitude to protect the privacy of FL and retain the capability of adjusting the learning performance. Specifically, we propose a geometric series form for the noise amplitude and reveal analytically the dependence of the series on the number of global aggregations and the (∊, δ)-DP requirement. We derive an online refinement of the series to prevent FL from premature convergence resulting from excessive perturbation noise. Another important aspect is an upper bound developed for the loss function of a multi-layer perceptron (MLP) trained by FL running the new DP mechanism. Accordingly, the optimal number of global aggregations is obtained, balancing the learning and privacy. Extensive experiments are conducted using MLP, supporting vector machine, and convolutional neural network models on four public datasets. The contribution of the new DP mechanism to the convergence and accuracy of privacy-preserving FL is corroborated, compared to the state-of-the-art Gaussian noise mechanism with a persistent noise amplitude. Copyright © 2023, The Authors. All rights reserved.

关键词： Balancing

来源：评论

学校读者我要写书评

暂无评论

Automated Injury Detection and Alert Systems in Public Transportation Integrating IoT with Convolutional Neural Networks

Automated Injury Detection and Alert Systems in Public Trans...

引用

Self Sustainable Artificial Intelligence Systems (ICSSAS), International Conference on

作者： S P Vimal John Benito Jesudasan Peter U. Kavitha G. Bhuvaneswari G. Manikandan R Thamizhamuthu Department of Electronics and Communication Engineering Sri Ramakrishna Engineering College Coimbatore Tamil Nadu India Cyber | Data Science & Engineering Capital One Services LLC Richmond Virginia USA School of Commerce Vel Tech RangarajanDr.Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of Computer Science and Engineering Saveetha Engineering College Chennai Tamil Nadu India Department of Artificial Intelligence and Data Science RMK Engineering College Chennai Tamil Nadu India Department of Computing Technologies SRM Institute of Science and Technology Kattankulathur Campus-Chengalpattu Chennai Tamil Nadu India

ISBN: (数字)9798350368413

ISBN: (纸本)9798350368420

Innovative methods to improve public transportation safety and response mechanisms have emerged due to Internet of Things (IoT) and artificial intelligence (AI) technologies. IoT devices and Convolutional Neural Networks (CNNs), a class of deep learning algorithms analyzing visual imagery, are used to create an innovative Automated Injury Detection and Alert System (AIDAS) for public transportation. The proposed AIDAS architecture employs IoT sensors and cameras in buses and trains to monitor and evaluate passengers’ physical health in real time. These sensors can detect unexpected impacts, odd motions, and distressing noises. A strong CNN model trained to detect passenger injury or bodily damage receives live images from the onboard cameras. An automatic alarm process is activated immediately upon injury detection. The closest emergency response teams and transportation system operators get complete event reports, including time, position (by GPS coordinates), and injury type. A quick reaction to accidents with this real-time alarm system might save lives and reduce public transportation injuries. AIDAS’ use of IoT and CNN technology is innovative in public transportation safety. The technology significantly improved emergency response times and reduced unattended injuries in public transport networks. The system’s excellent damage detection accuracy is due to CNNs’ advanced image processing and pattern recognition skills and IoT devices’ sensory inputs. It also addresses privacy issues and the necessity for strong data encryption and proposes solutions. Finally, it analyzes how AIDAS affects public transportation safety and future research and development in this critical field.

关键词： Visualization Emergency services Real-time systems Convolutional neural networks Internet of Things Reliability Artificial intelligence Injuries Public transportation Monitoring

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：