检索结果-内蒙古大学图书馆

18th CCF Conference on Computer Supported Cooperative Work and Social Computing, ChineseCSCW 2023

作者： Liao, Yuanming Wu, Duanji Lin, Pengyu Guo, Kun College of Computer and Data Science Fuzhou University Fuzhou350108 China Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou350108 China Key Laboratory of Spatial Data Mining and Information Sharing Ministry of Education Fuzhou350108 China

ISBN: (纸本)9789819996360

Graph neural networks have shown excellent performance in many fields owing to their powerful processing ability of graph data. In recent years, federated graph neural network has become a reasonable solution due to the enactment of privacy-related regulations. However, frequent communication between the coordinator and participants in federated graph neural network results in longer model training time and consumes many communication resources. To address this challenge, in this paper, we propose a novel semi-asynchronous federated graph learning communication protocol that simultaneously alleviates the negative impact of stragglers(slow participants) and accelerate the training process in the unsupervised federated graph neural network scenario. First, the weighted enforced synchronization strategy is intended to preserve the information carried by stragglers while preventing their stale models from harming the global model update. Second, the adaptive local update strategy is developed to make the local model of the participant with poor computing performance as close as possible to the global model. Experiments combine federated learning with graph contrastive learning. The results demonstrate that our proposed protocol outperforms the existing protocols in real-world networks. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Internet protocols

来源：评论

学校读者我要写书评

暂无评论

Research on an automatic light field refocusing method for a camera array

引用

Optics Express 2025年第10期33卷 20964-20980页

作者： Pan, Yihua Zhao, Yushan Li, Yuyang Liu, Bin Chen, Ping Shanxi Key Laboratory of Intelligent Detection Technology & Equipment School of Information and Communication Engineering North University of China Shanxi Taiyuan030051 China Key Laboratory of Photoelectronic Imaging Technology System of Ministry of Education of China School of Optics and Photonics Beijing Institute of Technology Beijing100081 China State Key Laboratory of Extreme Environment Optoelectronic Dynamic Testing Technology and Instruments North University of China Shanxi Taiyuan030051 China

Light field information includes the position and angle information of light in space. A camera array is one of the methods for obtaining light field information, which combines and arranges multiple cameras in space to achieve multi-angle imaging of the same target. Based on the light field information, a computational imaging method can be used to achieve refocusing technology for a camera array (also known as optical synthetic aperture imaging technology). In this technology, by setting the focusing coefficient, the light field information can be focused on different depths. This mode is called taking photos first and focusing later. However, in order to focus on a specific object surface, traditional refocusing methods require users to manually adjust the focusing coefficient multiple times, which is time-consuming and user-unfriendly. Therefore, in this paper, we propose an automatic focusing method based on the optimal focusing coefficient map (OFCM) to address the manual refocusing problem. This method transforms the refocusing problem into obtaining the optimal focus coefficient map. In the process of solving OFCM, the threshold filtering method and the neighborhood filling method are used to optimize the results and improve the robustness of the proposed method. The experimental results show that our proposed method has higher imaging quality and faster running efficiency compared to automatic refocusing methods based on disparity maps and gradient functions. © 2025 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement.

关键词： Computational Imaging

来源：评论

学校读者我要写书评

暂无评论

Leveraging catastrophic forgetting to develop safe diffusion models against malicious finetuning 24

Leveraging catastrophic forgetting to develop safe diffusion...

引用

Proceedings of the 38th International Conference on Neural information processing Systems

作者： Jiadong Pan Hongcheng Gao Zongyu Wu Taihang Hu Li Su Qingming Huang Liang Li Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS and University of Chinese Academy of Sciences University of Chinese Academy of Sciences The Pennsylvania State University Nankai University Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS

ISBN: (纸本)9798331314385

Diffusion models (DMs) have demonstrated remarkable proficiency in producing images based on textual prompts. Numerous methods have been proposed to ensure these models generate safe images. Early methods attempt to incorporate safety filters into models to mitigate the risk of generating harmful images but such external filters do not inherently detoxify the model and can be easily bypassed. Hence, model unlearning and data cleaning are the most essential methods for maintaining the safety of models, given their impact on model parameters. However, malicious fine-tuning can still make models prone to generating harmful or undesirable images even with these methods. Inspired by the phenomenon of catastrophic forgetting, we propose a training policy using contrastive learning to increase the latent space distance between clean and harmful data distribution, thereby protecting models from being fine-tuned to generate harmful images due to forgetting. The experimental results demonstrate that our methods not only maintain clean image generation capabilities before malicious fine-tuning but also effectively prevent DMs from producing harmful images after malicious fine-tuning. Our method can also be combined with other safety methods to maintain their safety against malicious fine-tuning further.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Fusion Shallow and Deep Features Network for Facial StO2 Stress Classification 6

A Fusion Shallow and Deep Features Network for Facial StO2 S...

引用

6th IEEE information technology, Networking, Electronic and Automation Control Conference, ITNEC 2023

作者： Xia, Haolin Sun, Sirui Liu, Xinyu Zhou, Ju Wang, Hanpu Chen, Tong School of Electronic and Information Engineering Southwest University Chongqing China Key Laboratory of Non-Linear Circuit and Intelligent Information Processing of Chongqing Chongqing China Institute of Legal Psychology and Intelligent Computing Chongqing China

ISBN: (纸本)9781665460033

Stress is an emotional state that affects our lives, so it is vital to detect it accurately. Numerous studies have shown that tissue oxygen saturation (StO2) is an effective physiological signal for identifying different stress states. However, previous StO2 feature extraction methods relied too heavily on baselines to be realized in practice. In this paper, a two-stream network combining shallow and deep features, called CRNet, is proposed for baseline-independent StO2 stress classification. In CRNet, shallow features are extracted using a CNN network and deep features are extracted using a ResNet network. For the extracted high-dimensional deep features, MLP module is employed for dimensionality reduction, which can effectively combine the two levels of features and improve the feature extraction capability of the network. Experimental results show that CRNet can significantly improve the performance of StO2 stress classification to the state-of-the-art (SOTA) even when using only raw imbalanced data. © 2023 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Numerical and experimental studies on the effectiveness of time-varying electromagnetic fields in reducing electron density

引用

Plasma Science and technology 2023年第6期25卷 30-40页

作者：郭韶帅谢楷徐晗付麦霞牛营营 Key Laboratory of Grain Information Processing and Control(Henan University of Technology) Ministry of EducationZhengzhou 450001People's Republic of China College of Information Science and Engineering Henan University of TechnologyZhengzhou 450001People's Republic of China School of Aerospace Science and Technology Xidian UniversityXi'an 710071People's Republic of China

When an aircraft or a hypersonic vehicle re-enters the atmosphere,the plasma sheath generated can severely attenuate electromagnetic wave signals,causing the problem of communication blackout.A new method based on time-varying E×B fields is proposed to improve on the existing static E×B fields and mitigate the radio blackout *** use of the existing method is limited by the invalid electron density reduction resulting from current density j=0 A m^(-2)in plasma beyond the Debye *** most remarkable feature is the introduction of a time-varying electric field to increase the current density in the plasma to overcome the Debye shielding effect on static electric ***,a magnetic field with the same frequency and phase as the electric field is applied to ensure that the electromagnetic force is always acting on the plasma in one *** order to investigate the effect of time-varying E×B fields on the plasma electron density distribution,two directions of voltage application are considered in numerical *** simulation results indicate that different voltage application methods generate electromagnetic forces in different directions in the plasma,resulting in repulsion and vortex effects in the plasma.A comparison of the vortex effect and repulsion effect reveals that the vortex effect is better at reducing the electron *** local plasma electron density can be reduced by more than 80%through the vortex effect,and the dimensions of the area of reduced electron density reach approximately 6 cm×4 cm,meeting the requirements of electromagnetic wave ***,the vortex effect of reducing the electron density in RAM-C(radio attenuation measurements for the study of communication blackout)reentry at an altitude of 40 km is *** the basis of the simulation results,an experiment based on a rectangular-window discharge device is proposed to demonstrate the effectiveness of the vortex *** results show t

关键词： blackout magnetic window method time-varying E×B fields

来源：评论

学校读者我要写书评

暂无评论

EXPLORING THE COMMON APPEARANCE-BOUNDARY ADAPTATION FOR NIGHTTIME OPTICAL FLOW 12

EXPLORING THE COMMON APPEARANCE-BOUNDARY ADAPTATION FOR NIGH...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Zhou, Hanyu Chang, Yi Liu, Haoyue Yan, Wending Duan, Yuxing Shi, Zhiwei Yan, Luxin National Key Lab of Multispectral Information Intelligent Processing Technology School of Artificial Intelligence and Automation Huazhong University of Science and Technology China Huawei International Co. Ltd. China

We investigate a challenging task of nighttime optical flow, which suffers from weakened texture and amplified noise. These degradations weaken discriminative visual features, thus causing invalid motion feature matching. Typically, existing methods employ domain adaptation to transfer knowledge from auxiliary domain to nighttime domain in either input visual space or output motion space. However, this direct adaptation is ineffective, since there exists a large domain gap due to the intrinsic heterogeneous nature of the feature representations between auxiliary and nighttime domains. To overcome this issue, we explore a common-latent space as the intermediate bridge to reinforce the feature alignment between auxiliary and nighttime domains. In this work, we exploit two auxiliary daytime and event domains, and propose a novel common appearance-boundary adaptation framework for nighttime optical flow. In appearance adaptation, we employ the intrinsic image decomposition to embed the auxiliary daytime image and the nighttime image into a reflectance-aligned common space. We discover that motion distributions of the two reflectance maps are very similar, benefiting us to consistently transfer motion appearance knowledge from daytime to nighttime domain. In boundary adaptation, we theoretically derive the motion correlation formula between nighttime image and accumulated events within a spatiotemporal gradient-aligned common space. We figure out that the correlation of the two spatiotemporal gradient maps shares significant discrepancy, benefitting us to contrastively transfer boundary knowledge from event to nighttime domain. Moreover, appearance adaptation and boundary adaptation are complementary to each other, since they could jointly transfer global motion and local boundary knowledge to the nighttime domain. Extensive experiments have been performed to verify the superiority of the proposed method. © 2024 12th International Conference on Learning Representations,

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

Overcoming the Limits of Cross-Sensitivity:Pattern Recognition Methods for Chemiresistive Gas Sensor Array

引用

Nano-Micro Letters 2024年第12期16卷 285-341页

作者： Haixia Mei Jingyi Peng Tao Wang Tingting Zhou Hongran Zhao Tong Zhang Zhi Yang Key Lab Intelligent Rehabil&Barrier Free Disable(Ministry of Education) Changchun UniversityChangchun 130022People’s Republic of China Shanghai Key Laboratory of Intelligent Sensing and Detection Technology School of Mechanical and Power EngineeringEast China University of Science and TechnologyShanghai 200237People’s Republic of China National Key Laboratory of Advanced Micro and Nano Manufacture Technology Department of Micro/Nano ElectronicsSchool of Electronic Information and Electrical EngineeringShanghai Jiao Tong UniversityShanghai 200240People’s Republic of China State Key Laboratory of Integrated Optoelectronics College of Electronic Science and EngineeringJilin UniversityChangchun 130012People’s Republic of China

As information acquisition terminals for artificial olfaction,chemiresistive gas sensors are often troubled by their cross-sensitivity,and reducing their cross-response to ambient gases has always been a difficult and important point in the gas sensing *** recognition based on sensor array is the most conspicuous way to overcome the cross-sensitivity of gas *** is crucial to choose an appropriate pattern recognition method for enhancing data analysis,reducing errors and improving system reliability,obtaining better classification or gas concentration prediction *** this review,we analyze the sensing mechanism of crosssensitivity for chemiresistive gas *** further examine the types,working principles,characteristics,and applicable gas detection range of pattern recognition algorithms utilized in gas-sensing ***,we report,summarize,and evaluate the outstanding and novel advancements in pattern recognition methods for gas *** the same time,this work showcases the recent advancements in utilizing these methods for gas identification,particularly within three crucial domains:ensuring food safety,monitoring the environment,and aiding in medical *** conclusion,this study anticipates future research prospects by considering the existing landscape and *** is hoped that this work will make a positive contribution towards mitigating cross-sensitivity in gas-sensitive devices and offer valuable insights for algorithm selection in gas recognition applications.

关键词： Pattern recognition Sensor array Chemiresistive gas sensor Cross-sensitivity Artificial olfactory

来源：评论

学校读者我要写书评

暂无评论

A Novel Classification Model Based on DWT and CNN-LSTM Motor EEG Imagination Signals 7

A Novel Classification Model Based on DWT and CNN-LSTM Motor...

引用

7th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2024

作者： Yang, Yuyao Chen, Zuowen Li, Weisu Ma, Yahong Xijing University School of Electronic Information Xi'an Key Laboratory of High Pricision Industrial Intelligent Vision Measurement Technology Xi'an China

ISBN: (纸本)9798350350890

Feature extraction and pattern classification play important roles in brain-computer interface (BCI) systems, which are widely used in rehabilitation medicine, artificial intelligence and other fields. Although advanced EEG acquisition technology can generate a large amount of EEG data for different brain regions, it inevitably has disadvantages such as high cost, long time consuming and inherent high false positives. Considering the contradiction between data volume and accuracy, this paper proposes a MI EEG feature extraction and classification method based on discrete wavelet transform (DWT) and Convolutional Neural Network-Long Short Term Memory (CNN-LSTM). Based on the project BCI motor imagination EEG(MI-EGG) data set, all evaluation indexes of the proposed CNN-LSTM model are superior to other models. The prediction accuracy, precision, recall rate, F1-score and MCC of C3 and C4 channels reaches 96.43%, 96.57%, 96.57%, 96.57% and 93.02%, respectively. The reliability of the proposed model is also proved by tenfold cross-validation. The average accuracy is 99.64%, which is far higher than the other models. It can be concluded that it is a reliable method to predict MI-EEG signals by using CNN-LSTM to train the modeling ability of images. © 2024 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

keypoints and Action Units Jointly Drive Talking Head Generation for Video Conferencing

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年

作者： Shi, Wuzhen Xue, Zibang Wen, Yang Shenzhen University Shenzhen Key Laboratory of Digital Creative Technology Guangdong Province Engineering Laboratory for Digital Creative Technology Guangdong Provincial Key Laboratory of Intelligent Information Processing College of Electronics and Information Engineering Shenzhen518060 China

This paper introduces a high-quality talking head generation method that is jointly driven by keypoints and action units, aiming to strike a balance between low-bandwidth transmission and high-quality generation in video conference scenarios. Existing methods for talking head generation often face limitations: they either require an excessive amount of driving information or struggle with accuracy and quality when adapted to low-bandwidth conditions. To address this, we decompose the talking head generation task into two components: a driving task, focused on information-limited control, and an enhancement task, aimed at achieving high-quality, high-definition output. Our proposed method innovatively incorporates the joint driving of keypoints and action units, improving the accuracy of pose and expression generation while remaining suitable for low-bandwidth environments. Furthermore, we implement a multistep video quality enhancement process, targeting both the entire frame and key regions, while incorporating temporal consistency constraints. By leveraging attention mechanisms, we enhance the realism of the challenging-to-generate mouth regions and mitigate background jitter through background fusion. Finally, a prior-driven super-resolution network is employed to achieve high-quality display. Extensive experiments demonstrate that our method effectively supports low-resolution recording, low-bandwidth transmission, and high-definition display. © 1991-2012 IEEE.

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

A Voxel Classification and Deletion Strategy for LiDAR-based 3D Object Detection 43

A Voxel Classification and Deletion Strategy for LiDAR-based...

引用

43rd Chinese Control Conference, CCC 2024

作者： Chen, Fang Li, Zheng Zuo, Zhiqiang Wang, Yijing Tianjin University Tianjin Key Laboratory of Intelligent Unmanned Swarm Technology and System School of Electrical and Information Engineering Tianjin300072 China

ISBN: (纸本)9789887581581

LiDAR-based 3D object detection plays an important role in autonomous driving. Among them, voxel-based methods have found wide applications in industrial deployments. This paper proposes a strategy to alleviate the imbalance in the numbers of foreground points and background points with the help of voxel classification (VoxCls) and voxel deletion (VoxDel). It can significantly improve the performance of voxel-based models without changing the network inference structure. First, a binary classification is developed to guide the network in distinguishing foreground voxels from background voxels. By doing so, the features of voxels implicitly incorporate information about both foreground and background. Second, background voxels are filtered based on VoxCls to solve the imbalance issue between foreground and background. Finally, experimental results demonstrate the effectiveness of enhancing voxel-based 3D object detection performance. © 2024 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Object recognition

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：