检索结果-内蒙古大学图书馆

A New Sequential Image Prediction Method Based on LSTM and DCGAN

computers, Materials & Continua 2020年第7期64卷 217-231页

作者： Wei Fang Feihong Zhang Yewen Ding Jack Sheng School of Computer&Software Jiangsu Engineering Center of Network MonitoringNanjing University of Information Science&TechnologyNanjing210044China State Key Laboratory for Novel Software Technology Nanjing UniversityNanjing210023China Department of Economics FinanceInsurance and Risk Management University of Central ArkansasConway72035USA

Image recognition technology is an important field of artificial *** with the development of machine learning technology in recent years,it has great researches value and commercial *** a matter of fact,a single recognition function can no longer meet people’s needs,and accurate image prediction is the trend that people *** paper is based on Long Short-Term Memory(LSTM)and Deep Convolution Generative Adversarial networks(DCGAN),studies and implements a prediction model by using radar image *** adopt a stack cascading strategy in designing network connection which can control of parameter convergence *** new method enables effective learning of image features and makes predictive models to have greater generalization *** demonstrate that our network model is more robust and efficient in terms of timing prediction than 3DCNN and traditional *** sequential image prediction model architecture proposed in this paper is theoretically applicable to all sequential images.

关键词： Image prediction LSTM DCGAN

来源：评论

学校读者我要写书评

暂无评论

Individualization of Head Related Impulse Responses Using Division Analysis

引用

China Communications 2018年第5期15卷 92-103页

作者： Wei Chen Ruimin Hu Xiaochen Wang Cheng Yang Lian Meng National Engineering Research Center for Multimedia Software School of Computer Science.Wuhan UniversityWuhan 430072China Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan UniversityWuhan 430072China Collaborative Innovation Center of Geospatial Technology Wuhan 430079China School of Physics and Electronic Science Guizhou Normal UniversityGuiyang 550001China

For Virtual Reality(VR) to be truly immersive, it needs convincing sound to match. Due to the diversity of individual's anthropometric measurements, the individualized customization technology is needed to get convincing sound. In this paper, we proposed a simple and effective method for modeling relationships between anthropometric measurements and Head-related Impulse Response(HRIR). Considering the relationship between anthropometric measurements and different HRIR parts is complicated, we divided the HRIRs into small segments and carried out regression analysis between anthropometric measurements and each segment to establish relationship model. The results of objective simulation and subjective test indicate that the model can generate individualize HRIRs from a series of anthropometric measurements. With the individualized HRIRs, we can get more accurate acoustic localization sense than using non-individualized HRIRs.

关键词： HRIR Individualization Division analysis

来源：评论

学校读者我要写书评

暂无评论

A Provable Decision Rule for Out-of-Distribution Detection 41

A Provable Decision Rule for Out-of-Distribution Detection

引用

41st International Conference on Machine Learning, ICML 2024

作者： Ma, Xinsong Zou, Xin Liu, Weiwei 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 Wuhan China

Out-of-distribution (OOD) detection task plays the key role in reliable and safety-critical applications. Existing researches mainly devote to designing or training the powerful score function but overlook investigating the decision rule based on the proposed score function. Different from previous work, this paper aims to design a decision rule with rigorous theoretical guarantee and well empirical performance. Specifically, we provide a new insight for the OOD detection task from a hypothesis testing perspective and propose a novel generalized Benjamini Hochberg (g-BH) procedure with empirical p-values to solve the testing problem. Theoretically, the g-BH procedure controls false discovery rate (FDR) at pre-specified level. Furthermore, we derive an upper bound of the expectation of false positive rate (FPR) for the g-BH procedure based on the tailed generalized Gaussian distribution family, indicating that the FPR of g-BH procedure converges to zero in probability. Finally, the extensive experimental results verify the superiority of g-BH procedure over the traditional threshold-based decision rule on several OOD detection benchmarks. Copyright 2024 by the author(s)

关键词：

来源：评论

学校读者我要写书评

暂无评论

Devil is in Details: Locality-Aware 3D Abdominal CT Volume Generation for Self-Supervised Organ Segmentation 24

Devil is in Details: Locality-Aware 3D Abdominal CT Volume G...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Wang, Yuran Wan, Zhijing Qiu, Yansheng Wang, Zheng National Engineering Research Center for Multimedia Software Hubei Key Laboratory of Multimedia and Network Communication Engineering Institute of Artificial Intelligence School of Computer Science Wuhan University Wuhan China

ISBN: (纸本)9798400706868

In the realm of medical image analysis, self-supervised learning (SSL) techniques have emerged to alleviate labeling demands, while still facing the challenge of training data scarcity owing to escalating resource requirements and privacy constraints. Numerous efforts employ generative models to generate high-fidelity, unlabeled 3D volumes across diverse modalities and anatomical regions. However, the intricate and indistinguishable anatomical structures within the abdomen pose a unique challenge to abdominal CT volume generation compared to other anatomical regions. To address the overlooked challenge, we introduce the Locality-Aware Diffusion (Lad), a novel method tailored for exquisite 3D abdominal CT volume generation. We design a locality loss to refine crucial anatomical regions and devise a condition extractor to integrate abdominal priori into generation, thereby enabling the generation of large quantities of high-quality abdominal CT volumes essential for SSL tasks without the need for additional data such as labels or radiology reports. Volumes generated through our method demonstrate remarkable fidelity in reproducing abdominal structures, achieving a decrease in FID score from 0.0034 to 0.0002 on AbdomenCT-1K dataset, closely mirroring authentic data and surpassing current methods. Extensive experiments demonstrate the effectiveness of our method in self-supervised organ segmentation tasks, resulting in an improvement in mean Dice scores on two abdominal datasets effectively. These results underscore the potential of synthetic data to advance self-supervised learning in medical image analysis. © 2024 ACM.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Sequential Kernel Goodness-of-fit Testing 41

Sequential Kernel Goodness-of-fit Testing

引用

41st International Conference on Machine Learning, ICML 2024

作者： Zhou, Zhengyu Liu, Weiwei 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 Wuhan China

Goodness-of-fit testing, a classical statistical tool, has been extensively explored in the batch setting, where the sample size is ***, practitioners often prefer methods that adapt to the complexity of a problem rather than fixing the sample size *** batch tests are generally unsuitable for streaming data, as valid inference after data peeking requires multiple testing corrections, resulting in reduced statistical *** address this issue, we delve into the design of consistent sequential goodness-of-fit *** the principle of testing by betting, we reframe this task as selecting a sequence of payoff functions that maximize the wealth of a fictitious bettor, betting against the null in a repeated *** conduct experiments to demonstrate the adaptability of our sequential test across varying difficulty levels of problems while maintaining control over type-I errors. Copyright 2024 by the author(s)

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cloth-aware Augmentation for Cloth-generalized Person Re-identification 24

Cloth-aware Augmentation for Cloth-generalized Person Re-ide...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Liu, Fangyi Ye, Mang Du, Bo National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence School of Computer Science Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan China

ISBN: (纸本)9798400706868

Person re-identification (ReID) is crucial in video surveillance, aiming to match individuals across different camera views while cloth-changing person re-identification (CC-ReID) focuses on pedestrians changing attire. Many existing CC-ReID methods overlook generalization, crucial for universality across cloth-consistent and cloth-changing scenarios. This paper pioneers exploring the cloth-generalized person re-identification (CG-ReID) task and introduces the Cloth-aware Augmentation (CaAug) strategy. Comprising domain augmentation and feature augmentation, CaAug aims to learn identity-relevant features adaptable to both scenarios. Domain augmentation involves creating diverse fictitious domains and simulating various clothing scenarios. Supervising features from different cloth domains enhances robustness and generalization against clothing changes. Additionally, for feature augmentation, element exchange introduces diversity concerning clothing changes. Regularizing the model with these augmented features strengthens resilience against clothing change uncertainty. Extensive experiments on cloth-changing datasets demonstrate the efficacy of our approach, consistently outperforming state-of-the-art methods. © 2024 ACM.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Manifold Projection for Adversarial Defense on Face Recognition 1

引用

16th European Conference on computer Vision, ECCV 2020

作者： Zhou, Jianli Liang, Chao Chen, Jun National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan China Key Laboratory of Multimedia and Network Communication Engineering BeijingHubei Province China

ISBN: (数字)9783030585778

ISBN: (纸本)9783030585761

Although deep convolutional neural network based face recognition system has achieved remarkable success, it is susceptible to adversarial images: carefully constructed imperceptible perturbations can easily mislead deep neural networks. A recent study has shown that in addition to regular off-manifold adversarial images, there are also adversarial images on the manifold. In this paper, we propose Adversarial Variational AutoEncoder (A-VAE), a novel framework to tackle both types of attacks. We hypothesize that both off-manifold and on-manifold attacks move the image away from the high probability region of image manifold. We utilize variational autoencoder (VAE) to estimate the lower bound of the log-likelihood of image and explore to project the input images back into the high probability regions of image manifold again. At inference time, our model synthesizes multiple similar realizations of a given image by random sampling, then the nearest neighbor of the given image is selected as the final input of the face recognition model. As a preprocessing operation, our method is attack-agnostic and can adapt to a wide range of resolutions. The experimental results on LFW demonstrate that our method achieves state-of-the-art defense success rate against conventional off-manifold attacks such as FGSM, PGD, and C&W under both grey-box and white-box settings, and even on-manifold attack. © 2020, Springer Nature Switzerland AG.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

A Theoretical Analysis of Backdoor Poisoning Attacks in Convolutional Neural networks 41

A Theoretical Analysis of Backdoor Poisoning Attacks in Conv...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Li, Boqi Liu, Weiwei 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 Wuhan China

The rising threat of backdoor poisoning attacks (BPAs) on Deep Neural networks (DNNs) has become a significant concern in recent years. In such attacks, the adversaries strategically target a specific class and generate a poisoned training set. The neural network (NN), well-trained on the poisoned training set, is able to predict any input with the trigger pattern as the targeted label, while maintaining accurate outputs for clean inputs. However, why the BPAs work remains less explored. To fill this gap, we employ a dirty-label attack and conduct a detailed analysis of BPAs in a two-layer convolutional neural network. We provide theoretical insights and results on the effectiveness of BPAs. Our experimental results on two real-world datasets validate our theoretical findings. Copyright 2024 by the author(s)

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Theoretical mean-variance relationship of IP network traffic based on ON/OFF model

引用

Science in China(Series F) 2009年第4期52卷 645-655页

作者： JIN Yi ZHOU Gang JIANG DongChen YUAN Shuai WANG LiLi CAO JianTing State Key Laboratory of Software Development Environment Beihang University Beijing 100191 China School of Computer Science & Engineering Beihang University Beijing 100191 China National Digital Switching System Engineering & Technological Research Center Zhengzhou 450002 China

Mean-variance relationship （MVR）, nowadays agreed in power law form, is an important function. It is currently used by traffic matrix estimation as a basic statistical assumption. Because all the existing papers obtain MVR only through empirical ways, they cannot provide theoretical support to power law MVR or the definition of its power exponent. Furthermore, because of the lack of theoretical model, all traffic matrix estimation methods based on MVR have not been theoretically supported yet. By observing both our laboratory and campus network for more than one year, we find that such an empirical MVR is not sufficient to describe actual network traffic. In this paper, we derive a theoretical MVR from ON/OFF model. Then we prove that current empirical power law MVR is generally reasonable by the fact that it is an approximate form of theoretical MVR under specific precondition, which can theoretically support those traffic matrix estimation algorithms of using MVR. Through verifying our MVR by actual observation and public DECPKT traces, we verify that our theoretical MVR is valid and more capable of describing actual network traffic than power law MVR.

关键词： traffic matrix mean-variance relationship self-similar

来源：评论

学校读者我要写书评

暂无评论

An analysis-oriented ROI based coding approach on surveillance video data 17th

An analysis-oriented ROI based coding approach on surveillan...

引用

17th Pacific-Rim Conference on Multimedia, PCM 2016

作者： Liao, Liang Hu, Ruimin Xiao, Jing Zhan, Gen Chen, Yu Xiao, Jun State Key Laboratory of Software Engineering Wuhan University Wuhan China Computer School National Engineering Research Center for Multimedia Software Wuhan University Wuhan China Hubei Provincial Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan China Research Institute of Wuhan University in Shenzhen Shenzhen China

ISBN: (纸本)9783319488950

Driven by the growing amount of surveillance video data, intelligent video analysis has been applied to manipulate the stored videos automatically. As the most important method of video storage, the conventional coding method with high compression ratio severely degrades the video quality, which restrict the performance of intelligent analysis. In this paper, we propose an analysis-oriented region of interest (ROI) based coding approach to relieve this problem. We qualitatively analyze the effect of video compression on the performance of video analysis, such as feature similarity and object detection. Based on the analysis, we generate the ROI by the prior knowledge of interest objects rather than considering the characteristics of Human Visual System (HVS). Then, a weight-based rate control scheme is proposed to protect the quality of ROI by assigning more bits to encode it. Experimental results show that the proposed approach can reach 5.52% and 4.39% gains average over HEVC on the performance of feature similarity and object detection respectively under the same bitrate. © Springer International Publishing AG 2016.

关键词： Object detection

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：