检索结果-内蒙古大学图书馆

SR-AFU: super-resolution network using adaptive frequency component upsampling and multi-resolution features

Frontiers of Computer Science 2023年第1期17卷 123-132页

作者： Ke-Jia CHEN Mingyu WU Yibo ZHANG Zhiwei CHEN School of Computer Science Nanjing University of Posts and TelecommunicationsNanjing 210023China Jiangsu Key Laboratory of Big Data Security&Intelligent Processing Nanjing University of Posts and TelecommunicationsNanjing 210023China College of Telecommunications and Information Engineering Nanjing University of Posts and TelecommunicationsNanjing 210003China

Image super-resolution (SR) is one of the classic computer vision tasks. This paper proposes a super-resolution network based on adaptive frequency component upsampling, named SR-AFU. The network is composed of multiple cascaded dilated convolution residual blocks (CDCRB) to extract multi-resolution features representing image semantics, and multiple multi-size convolutional upsampling blocks (MCUB) to adaptively upsample different frequency components using CDCRB features. The paper also defines a new loss function based on the discrete wavelet transform, making the reconstructed SR images closer to human perception. Experiments on the benchmark datasets show that SR-AFU has higher peak signal to noise ratio (PSNR), significantly faster training speed and more realistic visual effects compared with the existing methods.

关键词： super-resolution multi-resolution features adaptive frequency upsampling wavelet transformation

来源：评论

学校读者我要写书评

暂无评论

Pedestrian wind flow prediction using spatial-frequency generative adversarial network

引用

Building Simulation 2024年第2期17卷 319-334页

作者： Pengyue Wang Maozu Guo Yingeng Cao Shimeng Hao Xiaoping Zhou Lingling Zhao School of Architecture and Urban Planning Beijing University of Civil Engineering and ArchitectureBeijing100044China Beijing Key Laboratory of Intelligent Processing for Building Big Data Beijing100044China School of Electrical and Information Engineering Beijing University of Civil Engineering and ArchitectureBeijing100044China School of Computer Science and Technology Harbin Institute of TechnologyHarbin150001China

Pedestrian wind flow is a critical factor in designing livable residential environments under growing complex urban *** pedestrian wind flow during the early design stages is essential but currently suffers from inefficiencies in numerical *** learning,particularly generative adversarial networks(GAN),has been increasingly adopted as an alternative method to provide efficient prediction of pedestrian wind ***,existing GAN-based wind flow prediction schemes have limitations due to the lack of considering the spatial and frequency characteristics of wind flow *** study proposes a novel approach termed SFGAN,which embeds spatial and frequency characteristics to enhance pedestrian wind flow *** the spatial domain,Gaussian blur is employed to decompose wind flow into components containing wind speed and distinguished flow edges,which are used as the embedded spatial *** information of wind flow is obtained through discrete wavelet transformation and used as the embedded frequency *** spatial and frequency characteristics of wind flow are jointly utilized to enforce consistency between the predicted wind flow and ground truth during the training phase,thereby leading to enhanced *** results demonstrate that SFGAN clearly improves wind flow prediction,reducing Wind_MAE,Wind_RMSE and the Fréchet Inception Distance(FID)score by 5.35%,6.52%and 12.30%,compared to the previous best method,*** also analyze the effectiveness of incorporating the spatial and frequency characteristics of wind flow in predicting pedestrian wind *** reduces errors in predicting wind flow at large error intervals and performs well in wake regions and regions surrounding *** enhanced predictions provide a better understanding of performance variability,bringing insights at the early design stage to improve pedestrian wind *** proposed spatial-frequen

关键词： pedestrian wind flow prediction generative adversarial network Gaussian kernel wavelet transform objective function

来源：评论

学校读者我要写书评

暂无评论

Identifiability Analysis of Noise Covariances for LTI Stochastic Systems With Unknown Inputs

引用

IEEE TRANSACTIONS ON AUTOMATIC CONTROL 2023年第7期68卷 4459-4466页

作者： Kong, He Sukkarieh, Salah Arnold, Travis J. Chen, Tianshi Mu, Biqiang Zheng, Wei Xing Southern Univ Sci & Technol Dept Mech & Energy Engn Shenzhen Key Lab Biomimet Robot & Intelligent Syst Shenzhen Peoples R China Southern Univ Sci & Technol Guangdong Prov Key Lab Human Augmentat & Rehabil R Shenzhen 518055 Peoples R China Univ Sydney Sydney Inst Robot & Intelligent Syst Sydney NSW 2006 Australia Chinese Univ Hong Kong Sch Data Sci Shenzhen Res Inst Big Data Shenzhen Peoples R China Chinese Univ Hong Kong Shenzhen Res Inst Big Data Shenzhen 518172 Peoples R China Chinese Acad Sci Inst Syst Sci Acad Math & Syst Sci Key Lab Syst & Control Beijing 100190 Peoples R China Western Sydney Univ Sch Comp Data & Math Sci Sydney NSW 2751 Australia

existing works on optimal filtering of linear time invariant (LTI) stochastic systems with arbitrary unknown inputs assume perfect knowledge of the covariances of the noises in the filter design. This is impractical and raises the question of whether and under what conditions one can identify the process and measurement noise covariances (denoted as Q and R, respectively) of systems with unknown inputs. This article considers the identifiability of Q/R using the correlation-based measurement difference approach. More specifically, we establish 1) necessary conditions under which Q and R can be uniquely jointly identified;2) necessary and sufficient conditions under which Q can be uniquely identified, when R is known;3) necessary conditions under which R can be uniquely identified, when Q is known. It will also be shown that for achieving the results mentioned above, the measurement difference approach requires some decoupling conditions for constructing a stationary time series, which are proved to be sufficient for the well-known strong detectability requirements established by Hautus.

关键词： Arbitrary unknown input estimation Kalman filter noise covariance estimation

来源：评论

学校读者我要写书评

暂无评论

CTW: Confident Time-Warping for Time-Series Label-Noise Learning 32

CTW: Confident Time-Warping for Time-Series Label-Noise Lear...

引用

32nd International Joint Conference on Artificial Intelligence (IJCAI)

作者： Ma, Peitian Liu, Zhen Zheng, Junhao Wang, Linghao Ma, Qianli South China Univ Technol Sch Comp Sci & Engn Guangzhou Peoples R China South China Univ Technol Key Lab Big Data & Intelligent Robot Minist Educ Guangzhou Peoples R China

ISBN: (纸本)9781956792034

Noisy labels seriously degrade the generalization ability of Deep Neural Networks (DNNs) in various classification tasks. Existing studies on labelnoise learning mainly focus on computer vision, while time series also suffer from the same issue. Directly applying the methods from computer vision to time series may reduce the temporal dependency due to different data characteristics. How to make use of the properties of time series to enable DNNs to learn robust representations in the presence of noisy labels has not been fully explored. To this end, this paper proposes a method that expands the distribution of Confident instances by Time-Warping (CTW) to learn robust representations of time series. Specifically, since applying the augmentation method to all data may introduce extra mislabeled data, we select confident instances to implement Time-Warping. In addition, we normalize the distribution of the training loss of each class to eliminate the model's selection preference for instances of different classes, alleviating the class imbalance caused by sample selection. Extensive experimental results show that CTW achieves state-of-the-art performance on the UCR datasets when dealing with different types of noise. Besides, the t-SNE visualization of our method verifies that augmenting confident data improves the generalization ability. Our code is available at https://***/qianlima-lab/CTW.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Ancient Character Recognition: A Novel Image dataset of Shui Manuscript Characters and Classification Model

引用

Chinese Journal of Electronics 2023年第1期32卷 64-75页

作者： TANG Minli XIE Shaomin LIU Xiangrong Department of Computer Science and Technology School of Informatics Xiamen University School of Big Data Engineering KaiLi University Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan Ministry of Culture and Tourism Xiamen University

Shui manuscripts are part of the national intangible cultural heritage of China. Owing to the particularity of text reading, the level of informatization and intelligence in the protection of Shui manuscript culture is not adequate. To address this issue, this study created Shuishu＿C, the largest image dataset of Shui manuscript characters that has been reported. Furthermore, after extensive experimental validation, we proposed ShuiNet-A,a lightweight artificial neural network model based on the attention mechanism, which combines channel and spatial dimensions to extract key features and finally recognize Shui manuscript characters. The effectiveness and stability of ShuiNet-A were verified through multiple sets of experiments. Our results showed that, on the Shui manuscript dataset with 113 categories, the accuracy of ShuiN et-A was 99.8%, which is 1.5% higher than those of similar studies. The proposed model could contribute to the classification accuracy and protection of ancient Shui manuscript characters.

关键词： Training Speech recognition Artificial neural networks Feature extraction Stability analysis Character recognition Machine translation

来源：评论

学校读者我要写书评

暂无评论

Point Cloud Compression Method Based on Curvature Grading and Inter-point Compression for Industrial Products 15

Point Cloud Compression Method Based on Curvature Grading an...

引用

15th International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC 2023

作者： Wang, Lei Huang, Wei Chen, Yiping Chen, Ran Nanjing University of Posts and Telecommunications School of Computer Nanjing210023 China Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing210023 China

ISBN: (纸本)9798350308693

The traditional point cloud compression methods fail to meet the compression requirements of complex surface point cloud files in the industrial field. This paper proposes a point cloud compression method suitable for industrial products with defective and complex surfaces, which compresses the defect and non-defect parts separately using different compression approaches. A curvature-based compression method is designed for the defect points, and an inter-point compression method is developed for the non-defect part, achieving compression of both components of the point cloud. The experimental results show the advantages of the proposed compression method through a comparative analysis of time efficiency, compression ratio, and reconstruction accuracy for industrial point cloud compression. © 2023 IEEE.

关键词： Grading

来源：评论

学校读者我要写书评

暂无评论

Multimodal Topic Modeling by Exploring Characteristics of Short Text Social Media

引用

IEEE TRANSACTIONS ON MULTIMEDIA 2023年 25卷 2430-2445页

作者： Zhang, Huakui Cai, Yi Ren, Haopeng Li, Qing South China Univ Technol Key Lab Big Data & Intelligent Robot Minist Educ Guangzhou 510640 Peoples R China South China Univ Technol Sch Software Engn Guangzhou 510640 Peoples R China Hong Kong Polytech Univ Dept Comp Kowloon Hong Kong Peoples R China

Millions of people post images and texts to express their feelings and point of views on social media everyday, especially on the short text social media such as Twitter or Weibo. As the images can provide important supplementary information for the text, many multimodal topic models have been developed to mine the topics from the multimodal social media content. We summarize three fundamental characteristics of the short text multimodal social media. The first is that the text of a short social media document generally belong to only one topic. The second is that the attached images can be relevant to multiple topics due to the rich information expressed in the images. The last is that although in most cases, text and images in social media posts are relevant, it should be noted that in a small number of cases, text and pictures are not relevant. However, most of the current multimodal topic models fail to model the these characteristics, and thus may produce low-quality topics. Based on these characteristics, we propose an unsupervised multimodal topic model SMMTM to model the short text multimodal social media documents. In the SMMTM model, only one topic is sampled for the the text while an image can belong to different topics. The correlation of the topics between the text and the images in a document are also formulated in an appropriate way. The experiments on three short text social media datasets with four evaluation metrics show the advantages of our model over the existing models.

关键词： Multimodal social media topic models

来源：评论

学校读者我要写书评

暂无评论

PriFU: Capturing Task-Relevant Information Without Adversarial Learning 24

PriFU: Capturing Task-Relevant Information Without Adversari...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Bi, Xiuli Hu, Yang Liu, Bo Li, Weisheng Cosman, Pamela Xiao, Bin Chongqing Key Laboratory of Image Cognition Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education Chongqing University of Posts and Telecommunications Chongqing China Department of Electrical and Computer Engineering University of California San Diego San Diego United States

ISBN: (纸本)9798400706868

As machine learning advances, machine learning as a service (MLaaS) in the cloud brings convenience to human lives but also privacy risks, as powerful neural networks used for generation, classification or other tasks can also become privacy snoopers. This motivates privacy preservation in the inference phase. Many approaches for preserving privacy in the inference phase introduce multi-objective functions, training models to remove specific private information from users' uploaded data. Although effective, these adversarial learning-based approaches suffer not only from convergence difficulties, but also from limited generalization beyond the specific privacy for which they are trained. To address these issues, we propose a method for privacy preservation in the inference phase by removing task-irrelevant information, which requires no knowledge of the privacy attacks nor introduction of adversarial learning. Specifically, we introduce a metric to distinguish task-irrelevant information from task-relevant information, and achieve more efficient metric estimation to remove task-irrelevant features. The experiments demonstrate the potential of our method in several tasks. Our code will be available at: https://***/iwhoyoung/PriFU. © 2024 ACM.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Temporal-Frequency Co-training for Time Series Semi-supervised Learning 37

Temporal-Frequency Co-training for Time Series Semi-supervis...

引用

37th AAAI Conference on Artificial Intelligence (AAAI) / 35th Conference on Innovative Applications of Artificial Intelligence / 13th Symposium on Educational Advances in Artificial Intelligence

作者： Liu, Zhen Ma, Qianli Ma, Peitian Wang, Linghao South China Univ Technol Sch Comp Sci & Engn Guangzhou Peoples R China South China Univ Technol Key Lab Big Data & Intelligent Robot Minist Educ Guangzhou Peoples R China

ISBN: (纸本)9781577358800

Semi-supervised learning (SSL) has been actively studied due to its ability to alleviate the reliance of deep learning models on labeled data. Although existing SSL methods based on pseudo-labeling strategies have made great progress, they rarely consider time-series data's intrinsic properties (e.g., temporal dependence). Learning representations by mining the inherent properties of time series has recently gained much attention. Nonetheless, how to utilize feature representations to design SSL paradigms for time series has not been explored. To this end, we propose a Time Series SSL framework via Temporal-Frequency Co-training (TS-TFC), leveraging the complementary information from two distinct views for unlabeled data learning. In particular, TS-TFC employs time-domain and frequency-domain views to train two deep neural networks simultaneously, and each view's pseudo-labels generated by label propagation in the representation space are adopted to guide the training of the other view's classifier. To enhance the discriminative of representations between categories, we propose a temporal-frequency supervised contrastive learning module, which integrates the learning difficulty of categories to improve the quality of pseudo-labels. Through co-training the pseudo-labels obtained from temporal-frequency representations, the complementary information in the two distinct views is exploited to enable the model to better learn the distribution of categories. Extensive experiments on 106 UCR datasets show that TS-TFC outperforms state-of-the-art methods, demonstrating the effectiveness and robustness of our proposed model.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

A Path Planning Method Based on Optimal Arm Angle of 7-Degrees-of-Freedom Manipulator

引用

JOURNAL OF intelligent & robotIC SYSTEMS 2025年第2期111卷 1-20页

作者： Zhang, Li Han, Bing Niu, Jianwei Tong, Kun Tian, Xinyang Yu, Xiaolong Hou, Renluan Guo, Yuliang Beihang Univ Hangzhou Innovat Inst Zhejiang Ind Big Data & Robot Intelligent Syst Key Hangzhou 310052 Peoples R China Zhejiang Univ Sch Mech Engn Hangzhou 310030 Peoples R China Beihang Univ Sch Comp Sci & Engn State Key Lab Virtual Real Technol & Syst Beijing 100191 Peoples R China Beihang Univ Sch Automat Sci & Elect Engn Beijing 100191 Peoples R China

This paper aims to address the issue of explicitly utilizing the joint limit avoidance, singularity avoidance, and self-motion obstacle avoidance properties of a 7-degrees-of-freedom manipulator during path planning, given a cartesian space task path. First, the redundant degree of freedom of the manipulator is represented using arm angle parameterization, and the mapping of joint limits and singular configurations to arm angle space is derived in detail, in conjunction with analytical inverse kinematics solution. Next, based on the cartesian space task path, the arm angle space is discretized to obtain the feasible arm angle range under the self-motion obstacle avoidance condition. The arm angle values determine the joint angles of the manipulator. To minimize task execution time and improve efficiency, the total joint angle displacement of the manipulator is set as the optimization objective, and an improved particle swarm optimization algorithm is employed to iteratively search for the optimal arm angles at each path point. Finally, the effectiveness of the proposed method is validated through both simulation and real machine experiments.

关键词： Redundant manipulator Inverse kinematics Path planning Joint limit avoidance Self-motion obstacle avoidance

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：