检索结果-内蒙古大学图书馆

International Conference on computer Vision (ICCV)

作者： Yunqian Wen Bo Liu Jingyi Cao Rong Xie Li Song Institute of Image Communication and Network Engineering Shanghai Jiao Tong University School of Computer Science University of Technology Sydney MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University

Face de-identification involves concealing the true identity of a face while retaining other facial characteristics. Current target-generic methods typically disentangle identity features in the latent space, using adversarial training to balance privacy and utility. However, this pattern often leads to a trade-off between privacy and utility, and the latent space remains difficult to explain. To address these issues, we propose IDeudemon, which employs a "divide and conquer" strategy to protect identity and preserve utility step by step while maintaining good explainability. In Step I, we obfuscate the 3D disentangled ID code calculated by a parametric NeRF model to protect identity. In Step II, we incorporate visual similarity assistance and train a GAN with adjusted losses to preserve image utility. Thanks to the powerful 3D prior and delicate generative designs, our approach could protect the identity naturally, produce high quality details and is robust to different poses and expressions. Extensive experiments demonstrate that the proposed IDeudemon outperforms previous state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improvement on Ahn et al.'s RSA P-homomorphic signature scheme

Improvement on Ahn et al.'s RSA P-homomorphic signature sche...

引用

8th International ICST Conference on Security and Privacy in communication networks, SecureComm 2012

作者： Wang, Zhiwei College of Computer Nanjing University of Posts and Telecommunications Nanjing Jiangsu 210003 China State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing 100190 China Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks Nanjing Jiangsu 210003 China Key Lab. of Broadband Wireless Communication and Sensor Network Technology Nanjing University of Posts and Telecommunications Ministry of Education Jiangsu Province Nanjing Jiangsu 210003 China

ISBN: (纸本)9783642368820

P-homomorphic signature is a general framework for computing on authenticated data, which is recently proposed by Ahn et al. With P-homomorphic signature, any third party can derive a signature on the object message m′ from a signature of m, if m′ and m satisfy P(m,m′) = 1 for some predicate P which denotes the authenticatable relationship between m′ and m. Ahn et al. proposed a RSA P-homomorphic signature scheme by using a RSA accumulator, which is very efficient in space. However, the computational cost of verification and derivation is very heavy. We present an improved P-homomorphic signature scheme based on factoring problem. In our construction, the time efficiency of both verification and derivation are much better than Ahn's scheme. © 2013 ICST institute for computer Science, Social Informatics and Telecommunications Engineering.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Research on K-means median filter

引用

Journal of Information and Computational Science 2011年第6期8卷 961-968页

作者： Huang, Ying Xie, Mei Li, Weisheng Zhou, Lifang School of Electronic Engineering University of Electronic Science and Technology of China Chengdu 610054 China Chongqing Key Lab. of Computer Network and Communication Technology Chongqing 400065 China Institute of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing 400065 China

K-means median filter algorithm and recursive K-means median filter algorithm are designed to solve the defects of standard median filter. At first, the sample composed by the current pixel and its neighbors are divided into two classes, and the median of the class which includes the current pixel is computed as the result. The parameters TL and TH are used for the consideration of speed and accuracy, and they are analyzed to reach an optimal result. The standard K-means algorithm is a time-consuming procedure, so the optimization is proposed in this paper. And through the experimental analysis, the algorithm is suitable to the images with obvious foreground and background, especially to binary image. Some examples are given to prove the new algorithm can get better noise reduction effect. © 2011 Binary Information Press.

关键词： Median filters

来源：评论

学校读者我要写书评

暂无评论

A new application with algebraic multigrid method

引用

Journal of Information and Computational Science 2012年第6期9卷 1447-1454页

作者： Huang, Ying Xie, Mei Li, Weisheng Lai, Jun Wang, Kuangsheng School of Electronic Engineering University of Electronic Science and Technology of China Chengdu 610054 China Chongqing Key Lab. of Computer Network and Communication Technology Chongqing 400065 China Institute of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing 400065 China

Algebraic Multi-grid (AMG) method is analyzed and is combined with the graph cut method to extract the texture feature of the image. AMG method can extract more information about the singularities in the image. The data in the coarse grid is utilized to reconstruct the image and the reconstruct result approximates to the original image well. On the basis of the analysis on the AMG method, an energy function is constructed for the texture feature and minimized using max-flow method. Experimental results show that the proposed method can extract more texture details accurately. © 2012 by Binary Information Press.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Better Diffusion Models Further Improve Adversarial Training

arXiv

引用

arXiv 2023年

作者： Wang, Zekai Pang, Tianyu Du, Chao Lin, Min Liu, Weiwei Yan, Shuicheng School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China Sea AI Lab

It has been recognized that the data generated by the denoising diffusion probabilistic model (DDPM) improves adversarial training. After two years of rapid development in diffusion models, a question naturally arises: can better diffusion models further improve adversarial training? This paper gives an affirmative answer by employing the most recent diffusion model (Karras et al., 2022) which has higher efficiency (∼ 20 sampling steps) and image quality (lower FID score) compared with DDPM. Our adversarially trained models achieve state-of-the-art performance on RobustBench using only generated data (no external datasets). Under the ∞norm threat model with ϵ = 8/255, our models achieve 70.69% and 42.67% robust accuracy on CIFAR-10 and CIFAR-100, respectively, i.e. improving upon previous state-of-the-art models by +4.58% and +8.03%. Under the 2-norm threat model with ϵ = 128/255, our models achieve 84.86% on CIFAR-10 (+4.44%). These results also beat previous works that use external data. We also provide compelling results on the SVHN and TinyImageNet datasets. Our code is at https://***/wzekai99/DM-Improves-AT. Copyright © 2023, The Authors. All rights reserved.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

Understanding the Robustness of 3D Object Detection with Bird'View Representations in Autonomous Driving

Understanding the Robustness of 3D Object Detection with Bir...

引用

2023 IEEE/CVF Conference on computer Vision and Pattern Recognition, CVPR 2023

作者： Zhu, Zijian Zhang, Yichi Chen, Hai Dong, Yinpeng Zhao, Shu Ding, Wenbo Zhong, Jiachen Zheng, Shibao Institute of Image Communication and Network Engineering Shanghai Jiao Tong University China Institute for Ai Tsinghua University BNRist Center Thbi Lab Dept. of Comp. Sci. and Tech. China School of Computer Science and Technology Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Information Materials and Intelligent Sensing Laboratory of Anhui Province China Saic Motor Ai Lab Zhongguancun Laboratory China

ISBN: (纸本)9798350301298

3D object detection is an essential perception task in autonomous driving to understand the environments. The Bird's-Eye-View (BEV) representations have significantly improved the performance of 3D detectors with camera inputs on popular benchmarks. However, there still lacks a systematic understanding of the robustness of these vision-dependent BEV models, which is closely related to the safety of autonomous driving systems. In this paper, we evaluate the natural and adversarial robustness of various representative models under extensive settings, to fully understand their behaviors influenced by explicit BEV features compared with those without BEV. In addition to the classic settings, we propose a 3D consistent patch attack by applying adversarial patches in the 3D space to guarantee the spatiotemporal consistency, which is more realistic for the scenario of autonomous driving. With substantial experiments, we draw several findings: 1) BEV models tend to be more stable than previous methods under different natural conditions and common corruptions due to the expressive spatial representations;2) BEV models are more vulnerable to adversarial noises, mainly caused by the redundant BEV features;3) Camera-LiDARfusion models have superior performance under different settings with multi-modal inputs, but BEV fusion model is still vulnerable to adversarial noises of both point cloud and image. These findings alert the safety issue in the applications of BEV detectors and could facilitate the development of more robust models. © 2023 IEEE.

关键词： Autonomous driving

来源：评论

学校读者我要写书评

暂无评论

Anomaly detection of time series with smoothness-inducing sequential variational auto-encoder

arXiv

引用

arXiv 2021年

作者： Li, Longyuan Yan, Junchi Wang, Haiyang Jin, Yaohui State Key Lab of Advanced Optical Communication System and Network MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai200240 China Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai200240 China

Deep generative models have demonstrated their effectiveness in learning latent representation and modeling complex dependencies of time series. In this paper, we present a Smoothness-Inducing Sequential Variational Auto-Encoder (SISVAE) model for robust estimation and anomaly detection of multi-dimensional time series. Our model is based on Variational Auto-Encoder (VAE), and its backbone is fulfilled by a Recurrent Neural network to capture latent temporal structures of time series for both generative model and inference model. Specifically, our model parameterizes mean and variance for each time-stamp with flexible neural networks, resulting in a non-stationary model that can work without the assumption of constant noise as commonly made by existing Markov models. However, such a flexibility may cause the model fragile to anomalies. To achieve robust density estimation which can also benefit detection tasks, we propose a smoothness-inducing prior over possible estimations. The proposed prior works as a regularizer that places penalty at non-smooth reconstructions. Our model is learned efficiently with a novel stochastic gradient variational Bayes estimator. In particular, we study two decision criteria for anomaly detection: reconstruction probability and reconstruction error. We show the effectiveness of our model on both synthetic datasets and public real-world benchmarks. © 2021, CC BY.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning for Fresh Data Collection in UAV-assisted IoT networks

Deep Reinforcement Learning for Fresh Data Collection in UAV...

引用

IEEE Conference on computer communications Workshops, INFOCOM Wksps

作者： Mengjie Yi Xijun Wang Juan Liu Yan Zhang Bo Bai Science and Technology on Communication Network Laboratory Shijiazhuang Hebei China Key Laboratory of Wireless Sensor Network & Communication Shanghai Institute of Microsystem and Information Technology Chinese Academy of Sciences 865 Changning Road Shanghai China School of Electrical Engineering and Computer Science Ningbo University Zhejiang China Theory Lab (FKA Future Network Theory Lab) 2012 Labs Huawei Technologies Co. Ltd. Hong Kong

ISBN: (数字)9781728186955

ISBN: (纸本)9781728186962

Due to the flexibility and low operational cost, dispatching unmanned aerial vehicles (UAVs) to collect information from distributed sensors is expected to be a promising solution in Internet of Things (IoT), especially for time-critical applications. How to maintain the information freshness is a challenging issue. In this paper, we investigate the fresh data collection problem in UAV-assisted IoT networks. Particularly, the UAV flies towards the sensors to collect status update packets within a given duration while maintaining a non-negative residual energy. We formulate a Markov Decision Process (MDP) to find the optimal flight trajectory of the UAV and transmission scheduling of the sensors that minimizes the weighted sum of the age of information (AoI). A UAV-assisted data collection algorithm based on deep reinforcement learning (DRL) is further proposed to overcome the curse of dimensionality. Extensive simulation results demonstrate that the proposed DRL-based algorithm can significantly reduce the weighted sum of the AoI compared to other baseline algorithms.

关键词： Sensors Trajectory Data collection Unmanned aerial vehicles Internet of Things Wireless sensor networks Energy consumption

来源：评论

学校读者我要写书评

暂无评论

Frequency-Aware Physics-Inspired Degradation Model for Real-World Image Super-Resolution

arXiv

引用

arXiv 2021年

作者： Dong, Zhenxing Cao, Hong Shen, Wang Gan, Yu Ling, Yuye Zhai, Guangtao Su, Yikai John Hopcroft Center for Computer Science Shanghai Jiao Tong University China Institute of Image Communication and Network Engineering Shanghai Jiao Tong University China Department of Electrical and Computer Engineering University of Alabama TuscaloosaAL35401 United States State Key Lab of Advanced Optical Communication Systems and Networks Shanghai Jiao Tong University China

Current learning-based single image super-resolution (SISR) algorithms underperform on real data due to the deviation in the assumed degradation process from that in the real-world scenario. Conventional degradation processes consider applying blur, noise, and downsampling (typically bicubic downsampling) on high-resolution (HR) images to synthesize low-resolution (LR) counterparts. However, few works on degradation modelling have taken the physical aspects of the optical imaging system into consideration. In this paper, we analyze the imaging system optically and exploit the characteristics of the real-world LR-HR pairs in the spatial frequency domain. We formulate a real-world physics-inspired degradation model by considering both optics and sensor degradation;The physical degradation of an imaging system is modelled as a low-pass filter, whose cut-off frequency is dictated by the object distance, the focal length of the lens, and the pixel size of the image sensor. In particular, we propose to use a convolutional neural network (CNN) to learn the cutoff frequency of real-world degradation process. The learned network is then applied to synthesize LR images from unpaired HR images. The synthetic HR-LR image pairs are later used to train an SISR network. We evaluate the effectiveness and generalization capability of the proposed degradation model on real-world images captured by different imaging systems. Experimental results showcase that the SISR network trained by using our synthetic data performs favorably against the network using the traditional degradation model. Moreover, our results are comparable to that obtained by the same network trained by using real-world LR-HR pairs, which are challenging to obtain in real scenes. © 2021, CC BY.

关键词： Cutoff frequency

来源：评论

学校读者我要写书评

暂无评论

Perfect Power Visualization-Performance Optimization with Java

Perfect Power Visualization-Performance Optimization with Ja...

引用

2014 IEEE 5th International Conference on Software Engineering and Service Science

作者： Chenqi Bao Alexander Flueck Jianmin Bao Xuan Shen Computer of Engineering Illinois Institute of Technology (College of IOTNanjing University of Posts and Telecommunications)Ministry of Education Key Lab of Broadband Wireless Communication and Sensor Network Technology (College of IOT Nanjing University of Posts and Telecommunications)Ministry of Education

Visualization is critical in power systems engineering since the gigantic amount of data generated by power systems is difficult,and at times impossible,to be analyzed numerically. Therefore,the need for powerful visualization software has been increasingly acute due to the growth in size of power system models. To improve PPV’s performance in order to accompany larger systems,this paper focuses on the development of PPV (Perfect Power Visualization),a 2-D power system visualization software program that processes and conver ts numerical data to graphic symbols based on their types,positions and states. The goal of PPV is to let operators visualize and interact with large-scale power systems in a consumer lever personal computer in real time. Also,it was optimized again with smarter data management systems,refinement of overall structure,and a newer platform that enables GPU acceleration,all of which further increased the performance of PPV by a factor of ten times that of its initial capabilities.

关键词： PPV,Power System Visualization,Java FX,GPU acceleration,Performance Optimization

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：