检索结果-内蒙古大学图书馆

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Wu, Zhiliang Zhang, Kang Sun, Changchang Xuan, Hanyu Yan, Yan Nanjing University of Science and Technology School of Computer Science and Engineering China Illinois Institute of Technology Department of Computer Science United States Anhui University School of Big Data and Statistics China

ISBN: (纸本)9781728163277

Video inpainting aims to utilize plausible contents to fill missing regions in the video. State-of-the-art video inpainting methods typically generate the missing contents of the target frame (current frame) by aggregating the temporal information of reference frames (neighboring frames) aligned using deformable convolution. However, these deformable convolution alignment networks often suffer from offset overflow during training, resulting in unsatisfactory alignment, thereby obtaining compromised inpainting performance. In this paper, we propose a self-supervised Flow-Guided Deformable Alignment (FGDA) network for aligning reference frames at the feature level. FGDA computes the residual of the optical flow as the offsets. This design can effectively reduce the burden of offsets learning, thereby avoiding offset overflow. Furthermore, a gradient-weighted reconstruction loss for supervised completed frame reconstruction is designed, which can use the gradients in all directions of the video frame to emphasize the difficultly reconstructed texture regions, so that detail textures get more attention during training. Experiments show that FGDA-based video inpainting model trained with gradient-weighted reconstruction loss outperforms the state-of-the-art by a significant margin in terms of PSNR and SSIM with relative improvements of 6.2% and 2.1%, respectively. © 2023 IEEE.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

A Dental Caries Segmentation Method Based on Dental Bitewings 2

A Dental Caries Segmentation Method Based on Dental Bitewing...

引用

2022 2nd International Conference on Health big data and Smart Sports, HBDSS 2022

作者： Han, Zhiyuan Yang, Jingyu Wang, Chen Du, Chenxi School of Computer Science and Engineering Beijing Technology and Business University Beijing China Beijing Key Laboratory of Big Data Technology for Food Safety Beijing China

ISBN: (纸本)9783800760428

Computer Aided Diagnosis (CAD) has become a hot research field in oral clinic. Due to the similar contrast between caries and periodontal tissues, especially the proximal caries, it is difficult for general CAD methods to accurately detect the location of caries. Aiming at this problem, an image semantic segmentation algorithm based on U-Net and attention mechanism is proposed. First, the dental bitewings dataset was constructed. Second, the CBAM module is integrated into the U-Net network for focusing on caries-affected areas. Finally, the semantic segmentation accuracy is further improved by multi-scale feature fusion. The experimental results show that the model proposed in this paper has significant improvements in multiple performances compared with algorithms such as PSP-Net. © VDE VERLAG GMBH ∙ Berlin ∙ Offenbach.

关键词： Computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

Visual-semantic network: a visual and semantic enhanced model for gesture recognition

引用

Visual Intelligence 2023年第1期1卷 71-83页

作者： Yizhe Wang Congqi Cao Yanning Zhang National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer ScienceNorthwestern Polytechnical UniversityXi’an710129China

Gesture recognition has attracted considerable attention and made encouraging progress in recent years due to its great potential in ***,the spatial and temporal modeling in gesture recognition is still a problem to be ***,existing works lack efficient temporal modeling and effective spatial attention *** efficiently model temporal information,wefirst propose a long-and short-term temporal shift module(LS-TSM)that models the long-term and short-term temporal information ***,we propose a spatial attention module(SAM)that focuses on where the change primarily occurs to obtain effective spatial attention *** addition,the semantic relationship among gestures is helpful in gesture ***,this is usually neglected by previous ***,we propose a label relation module(LRM)that takes full advantage of the relationship among classes based on their labels’semantic *** explore the best form of LRM,we design four different semantic reconstruction methods to incorporate the semantic relationship information into the class label’s semantic *** perform extensive ablation studies to analyze the best settings of each *** best form of LRM is utilized to build our visual-semantic network(VS Network),which achieves the state-of-the-art performance on two gesture datasets,i.e.,EgoGesture and NVGesture.

关键词： Gesture recognition Temporal modeling Spatial attention Semantic relationship

来源：评论

学校读者我要写书评

暂无评论

A Time Series Sales data Forecasting Model Based on TCN and Its Three Variants

A Time Series Sales Data Forecasting Model Based on TCN and ...

引用

Industrial IoT, big data and Supply Chain (IIoTBDSC), International Conference on

作者： Sian Chen Department of Data Science and Big Data Technology Brunel London School North China University of Technology Beijing China

ISBN: (数字)9798331539818

ISBN: (纸本)9798331539825

The forecasting of sales data is a widely studied issue in the fields of artificial intelligence and time series forecasting. TCN (Temporal Convolutional Network) is the most adept at managing time series data among all classical models due to its distinctive architecture. In this paper, we design a TCN-based model for time series forecasting of sales data and propose three variants: a combined model of TCN with RNN, LSTM and GRU to enhance the performance of time series forecasting. Experimental results show that these models perform well in handling the sales data forecasting task, especially the combination of TCN with LSTM performs best in several metrics.

关键词： Measurement Time series analysis Supply chains Predictive models big data data models Convolutional neural networks Forecasting Long short term memory Industrial Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Differentially Private Federated Stochastic Primal-Dual Learning for Internet of Vehicles

引用

IEEE Internet of Things Journal 2025年第11期12卷 17034-17050页

作者： Li, Yiwei Wang, Shuai Chang, Tsung-Hui Xiamen University of Technology Fujian Key Laboratory of Communication Network and Information Processing Xiamen361024 China University of Electronic Science and Technology of China National Key Laboratory of Wireless Communications Chengdu611731 China Chinese University of Hon g Kong School of Science and Engineering Shenzhen518172 China Shenzhen Research Institute of Big Data Shenzhen518172 China

Federated learning (FL) has the potential to empower Internet of Vehicles (IoV) networks by enabling smart vehicles (SVs) to participate in the learning process under the orchestration of a vehicular service provider while keeping data locally. In this article, we propose a novel federated stochastic primal-dual algorithm with differential privacy (FedSPD-DP) to ensure robust privacy protection for FL based IoV (FL-IoV) systems. The FedSPD-DP algorithm leverages multiple steps of local stochastic gradient descent (SGD) and partial client participation (PCP) to improve communication efficiency while incorporating differential privacy (DP) to ensure privacy protection. Our theoretical analysis explores the impact of these strategies on learning performance. Specifically, we demonstrate that the data sampling strategy and PCP enhance data privacy, while a larger number of local SGD steps may increase privacy leakage, revealing a nontrivial tradeoff between communication efficiency and privacy protection. Extensive experiments on real-world data validate the effectiveness of the proposed algorithm, showing superior performance compared to state-of-the-art FL algorithms, and confirming the analytical results and properties. © 2014 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

UARC:Unsupervised Anomalous Traffic Detection with Improved U-Shaped Autoencoder and RetNet Based Multi-clustering 26th

UARC:Unsupervised Anomalous Traffic Detection with Improved ...

引用

26th International Conference on Information and Communications Security, ICICS 2024

作者： Xie, Yunyang Chen, Kai Li, Shenghui Li, Bingqian Zhang, Ning Hubei Key Laboratory of Distributed System Security Hubei Engin eering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University Technology Wuhan430074 China

ISBN: (纸本)9789819787975

With the ongoing advancement of deep learning, modern network intrusion detection systems increasingly favor utilizing deep learning networks to improve their ability to learn traffic characteristics. To address the challenge of obtaining a substantial amount of labeled training data, many intrusion detection systems now focus on unsupervised anomaly detection methods. Despite this shift, researchers still face the daunting task of distinguishing a significant volume of anomalous traffic and dealing with data imbalance. To address these real-world challenges, we introduce UARC, a system capable of achieving unsupervised anomaly traffic detection through multi-clustering. UARC utilizes an enhanced U-shaped autoencoder and a feature fusion method incorporating Masked Retnet to effectively extract spatiotemporal features from network traffic. It combines these techniques with the HDBSCAN algorithm for multi-clustering of traffic, providing a form of reverse guidance for network learning. Experimental results on multiple datasets demonstrate that UARC can cluster various types of traffic with an impressive accuracy rate of up to 97.96%, while achieving a 99.70% AUC value for anomaly detection. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Adaptive weighted broad learning system for imbalanced classification 6

Adaptive weighted broad learning system for imbalanced class...

引用

6th IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference, IMCEC 2024

作者： Li, Yanting Gao, Yiping Jin, Junwei Chen, C. L. Philip Zhengzhou University of Light Industry College of Computer Science and Technology Zhengzhou China Henan University of Technology College of Artificial Intelligence and Big Data Zhengzhou China South China University of Technology School of Computer Science and Engineering Guangzhou China

ISBN: (纸本)9798350316520

Broad Learning System (BLS) perform well in classification tasks with good computational efficiency. However, its effectiveness decreases when faced with imbalanced data distribution. The traditional BLS cannot solve this problem effectively. In this paper, we introduce an adaptive weighted method for BLS, aiming to improve its classification performance on imbalanced data. This method can assign different weights according to the distribution characteristics of samples. There exists a closed-form solution to the problem and the transformation matrix can be solved efficiently by pseudo-inverse. Experimental results on several imbalanced datasets demonstrate that the proposed method surpasses standard BLS and many advanced imbalanced classification methods. © 2024 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Preserving model privacy for Federated Reinforcement Learning in Complementary Environments 23

Preserving model privacy for Federated Reinforcement Learnin...

引用

15th International Conference on Machine Learning and Computing, ICMLC 2023

作者： Xuan, Pengyu Chen, Aiguo Sha, Zexin University of Electronic Science and Technology of China Chengdu China Trusted Cloud Computing and Big Data Key Laboratory of Sichuan Province Chengdu China

ISBN: (纸本)9781450398411

Federated reinforcement learning (FRL) uses data from multiple partners interacting with the environment to train a global decision model while maintaining data privacy. In specific situations, it is necessary to protect not only data privacy but also model privacy. That is, our objective is to collaboratively train a global model that can be used privately and independently by the initiator. We refer to this need for model privacy preservation as model monopolization. It allows the task initiator to ensure the privacy of the model during the training process and to own the trained model alone. To the best of our knowledge, model monopolization protection in Federated Reinforcement Learning has not been studied. We propose monopolized federated reinforcement learning in complementary environments via function transformation. We also provide contribution metrics to ensure the sustainability of monopolized federated reinforcement learning and to provide a quantitative basis for task initiators to give back to task participants. The experimental results show that our method achieved model monopolization by training agents in the Grid-world. © 2023 ACM.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Brief Overview of Recent Energy-Saving Researches in Smart Homes 1

引用

18th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2022

作者： Sung, Tien-Wen Liang, Qiaoxin Huang, Zeming Hong, Chuanbo Fujian Provincial Key Laboratory of Big Data Mining and Applications College of Computer Science and Mathematics Fujian University of Technology Fuzhou350118 China

ISBN: (数字)9789819906055

ISBN: (纸本)9789819906048

This paper gives a brief overview on the topic of energy saving in smart homes. It provides introduction of some recent researches and developments of energy-saving schemes for smart homes, so that helps readers to know information about the potential issues and to make improvements in the future. A brief summary given in the discussion indicates that not only considering the problem of energy consumption but also paying attention to the comfort and safety for users in the energy-saving solutions is also important. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Energy conservation

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Partial Multi-View Learning

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2023年第10期45卷 11824-11841页

作者： Zhou, Yuan Guo, Yanrong Hao, Shijie Hong, Richang Luo, Jiebo Ministry of Education Hefei University of Technology The Key Laboratory of Knowledge Engineering with Big Data Hefei230009 China Hefei University of Technology The School of Computer Science and Information Engineering Hefei230009 China University of Rochester The Department of Computer Science RochesterNY14627 United States

It is often the case that data are with multiple views in real-world applications. Fully exploring the information of each view is significant for making data more representative. However, due to various limitations and failures in data collection and pre-processing, it is inevitable for real data to suffer from view missing and data scarcity. The coexistence of these two issues makes it more challenging to achieve the pattern classification task. Currently, to our best knowledge, few appropriate methods can well-handle these two issues simultaneously. Aiming to draw more attention from the community to this challenge, we propose a new task in this paper, called few-shot partial multi-view learning, which focuses on overcoming the negative impact of the view-missing issue in the low-data regime. The challenges of this task are twofold: (i) it is difficult to overcome the impact of data scarcity under the interference of missing views;(ii) the limited number of data exacerbates information scarcity, thus making it harder to address the view-missing issue in turn. To address these challenges, we propose a new unified Gaussian dense-anchoring method. The unified dense anchors are learned for the limited partial multi-view data, thereby anchoring them into a unified dense representation space where the influence of data scarcity and view missing can be alleviated. We conduct extensive experiments to evaluate our method. The results on Cub-googlenet-doc2vec, Handwritten, Caltech102, Scene15, Animal, ORL, tieredImagenet, and Birds-200-2011 datasets validate its effectiveness. The codes will be released at https://***/zhouyuan888888/UGDA. © 1979-2012 IEEE.

关键词： Neural networks

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：