检索结果-内蒙古大学图书馆

34th ACM Web Conference, WWW 2025

作者： Yang, Jiyu He, Qiang Zhou, Zheyu Dai, Xiaohai Chen, Feifei Tian, Cong Yang, Yun Swinburne University of Technology Melbourne Australia Huazhong University of Science and Technology Wuhan China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan 430074 China Deakin University Melbourne Australia Xidian University Xi’an China

ISBN: (纸本)9798400712746

Machine learning (ML) models are widely deployed on edge nodes, such as mobile phones and edge servers, to power a wide range of AI applications over the web. Ensuring the integrity of these edge models is paramount, as they are subject to corruption caused by software/hardware exceptions and malicious tampering, which may undermine model performance, incur economic losses, and pose health risks. Existing data integrity mechanisms designed for files stored on disks cannot properly verify the integrity of models running in GPUs or mitigate the new integrity threats against edge models. This paper proposes EdgeThemis, a novel mechanism for verifying the integrity of edge models through sentinel verification. To enable verifiability for a model M, EdgeThemis embeds a sentinel backdoor and a verification module into M. Then, a challenger can send verification requests to the edge node hosting M to verify its integrity. Next, the sentinel activates the verification module to generate a unique integrity proof tied to the identity of the edge node for verification. Finally, the challenger can verify the integrity proof to detect model corruption. Theoretical analysis proves that EdgeThemis can properly mitigate potential integrity threats against edge models. Experiments demonstrate that EdgeThemis achieves a verification accuracy of 100.00% across various models and different types of model corruption with robustness against replay attacks, theft attacks, and replacement attacks. © 2025 Copyright held by the owner/author(s).

关键词： edge computing edge intelligence Model integrity

来源：评论

学校读者我要写书评

暂无评论

Knowledge-aware contrastive heterogeneous molecular graph learning

arXiv

引用

arXiv 2025年

作者： Chen, Mukun Wu, Jia Pan, Shirui Lin, Fu Du, Bo Gong, Xiuwen Hu, Wenbin School of Computer Science Wuhan University Hubei Province Wuhan China School of Computing Macquarie University Sydney Australia School of Information and Communication Technology Griffith University Queensland Australia Faculty of Engineering and Information Technology University of Technology Sydney Sydney Australia

Molecular representation learning is pivotal in predicting molecular properties and advancing drug design. Traditional methodologies, which predominantly rely on homogeneous graph encoding, are limited by their inability to integrate external knowledge and represent molecular structures across different levels of granularity. To address these limitations, we propose a paradigm shift by encoding molecular graphs into heterogeneous structures, introducing a novel framework: Knowledge-aware Contrastive Heterogeneous Molecular Graph Learning. This approach leverages contrastive learning to enrich molecular representations with embedded external knowledge. KCHML conceptualizes molecules through three distinct graph views—molecular, elemental, and pharmacological—enhanced by heterogeneous molecular graphs and a dual message-passing mechanism. This design offers a comprehensive representation for property prediction, as well as for downstream tasks such as drug-drug interaction prediction. Extensive benchmarking demonstrates KCHML’s superiority over state-of-the-art molecular property prediction models, underscoring its ability to capture intricate molecular features. © 2025, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Revealing twin-induced deformation mechanisms of AZ31 Mg alloy sheet during warm deep drawing

引用

Journal of Magnesium and Alloys 2025年

作者： Tian, Lei Wang, Lifei Fu, Xinwei Deng, Kunkun Wang, Xiao Zheng, Liuwei Wang, Hongxia Zhang, Qiang Shin, Kwang Seon Shanxi Key Laboratory of Advanced Magnesium-based Materials College of Materials Science and Engineering Taiyuan University of Technology Taiyuan030024 China Qian Xuesen Space Technology Laboratory China Academy of space technology Beijing100081 China National Key Laboratory of Helicopter Aeromechanics Nanjing University of Aeronautics and Astronautics Nanjing210016 China Magnesium Technology Innovation Center School of Materials Science and Engineering Seoul National University Seoul08826 Korea Republic of

In this work, the {10–12} tensile twins are introduced to improve the drawability of the AZ31 Mg alloy sheet. Concretely, the drawing depth is increased by 32 % compared with the as-received sheet at 200 °C. This is because {10–12} tensile twins promote the occurrences of many deformation mechanisms during warm deep drawing, such as slips, detwinning, dynamic recrystallization (DRX) behaviors, etc. Further, based on the different stress states during deep drawing, these mechanisms and their competition relationships, as well as texture evolutions, are systematically studied. Combined with critical resolved shear stress (CRSS) and microstructure evolution, the global Schmid factor (GSF) obtained by quantizing stress states by stress tensor (σ) can accurately predict the activation trend of deformation mechanisms. It is found that the stress states have a reverse influence on the activation trend of the {10–12} twinning and detwinning. The change of stress states affects the competitive relationships between detwinning and DRX, and then affects the process and degree of DRX. The {10–12} tensile twins and large plane strain promote the activation of prismatic slips, and the larger plane strain also deflected the {10–12} twinning lattice. The {10–12} tensile twins and their induced deformation mechanisms can prominently weaken the basal texture and improve the drawability. © 2025

关键词： Magnesium alloys

来源：评论

学校读者我要写书评

暂无评论

Optimizing Cloud Security with CNN and XGBoost Models for Intrusion Detection Systems 3

Optimizing Cloud Security with CNN and XGBoost Models for In...

引用

3rd International Conference on Integrated Circuits and Communication Systems, ICICACS 2025

作者： Mogal, Amit Karbhari Anitha, V. Bhatt, Preeti Nitin Srivasatava, Kriti Devi, S. Rukmani Perada, Anvesh Mvp Samaj's Cmcs College Department of Computer Science and Application Nashik India School of Engineering and Technology Dhanalakshmi Srinivasan University Department of Computer Science and Engineering Trichy India Iimt College of Engineering Department of Electronics & Communication Engineering Greater Noida India Vile Parle India Saveetha College of Liberal Arts and Sciences Simats Deemed to be University Department of Computer Science Chennai India Drexel University Department of Electrical and Computer Engineering Philadelphia United States

ISBN: (纸本)9798331508456

Cloud computing and Internet growth have simplified certain formerly difficult activities. This advancement has also revealed many security weaknesses. Due to cyberattacks, organizations need Intrusion Detection Systems (IDS) to protect their data and networks. Preprocessing, feature selection, and model training comprise the suggested strategy. Preprocessing includes data cleansing, standardization, and labeling. Information gain, chi-square, and PSO are used to choose features. CNN-XGBoost trains the model. The CNN-XGBoost model outperforms solo CNN and XGBoost with an average accuracy of 92.08%. This accuracy proves the hybrid method's cloud computing breach detection usefulness. The study underlines the importance of enhanced IDS models in cyber risk reduction. CNN's feature extraction and XGBoost's classification power provide a powerful, efficient, and reliable cloud intrusion detection model. Modern organizations benefit from this network security method. © 2025 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Harnessing Light Field Angular Cues and Spatial Geometries for Semantic Segmentation

Harnessing Light Field Angular Cues and Spatial Geometries f...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Chen Jia Fan Shi Xu Cheng School of Computer Science and Engineering The Engineering Research Center of Learning-Based Intelligent System (Ministry of Education) The Key Laboratory of Computer Vision and System (Ministry of Education) Tianjin University of Technology Tianjin China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

4D light field imaging captures rich spatial-angular information, providing essential geometric cues for semantic segmentation tasks. In this paper, we introduce a novel backbone network called the Light Field Extraction Interaction Network (LFEI-Net). LFEI-Net excels in extracting global structures and multi-scale spatial-angular features, capturing feature dependencies through channel modeling and diverse feature interactions. Unlike traditional methods that depend on pyramid and dilated feature extraction, LFEI-Net pioneers an efficient method by integrating large-scale horizontal depth-wise convolution (HDWC) and vertical depth-wise convolution (VDWC) with interactive operations for comprehensive spatial multi-scale feature extraction. Furthermore, we present the Multi-Angular Modeling (MAM) module, which effectively captures scene angle variations from multiple perspectives and precisely delineates object boundaries, thereby improving model adaptability. Our experimental evaluations on two datasets demonstrate that LFEI-Net significantly outperforms state-ofthe-art (SOTA) 2D and 4D light field semantic segmentation methods, achieving mean Intersection over Union (mIoU) of 83.72% and 86.88%, respectively.

关键词： Geometry Adaptation models Convolution Semantic segmentation Imaging Feature extraction Light fields Acoustics Speech processing

来源：评论

学校读者我要写书评

暂无评论

Task-Oriented Feature Compression for Multimodal Understanding via Device-Edge Co-Inference

arXiv

引用

arXiv 2025年

作者： Yuan, Cheng Liu, Zhening Lv, Jiashu Shao, Jiawei Jiang, Yufei Zhang, Jun Li, Xuelong of China Telecom China Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong School of Software and Microelectronics Peking University China School of Electronic and Information Engineering Harbin Institute of Technology Shenzhen China

With the rapid development of large multimodal models (LMMs), multimodal understanding applications are emerging. As most LMM inference requests originate from edge devices with limited computational capabilities, the predominant inference pipeline involves directly forwarding the input data to an edge server which handles all computations. However, this approach introduces high transmission latency due to limited uplink bandwidth of edge devices and significant computation latency caused by the prohibitive number of visual tokens, thus hindering delay-sensitive tasks and degrading user experience. To address this challenge, we propose a task-oriented feature compression (TOFC) method for multimodal understanding in a device-edge co-inference framework, where visual features are merged by clustering and encoded by a learnable and selective entropy model before feature projection. Specifically, we employ density peaks clustering based on K nearest neighbors to reduce the number of visual features, thereby minimizing both data transmission and computational complexity. Subsequently, a learnable entropy model with hyperprior is utilized to encode and decode merged features, further reducing transmission overhead. To enhance compression efficiency, multiple entropy models are adaptively selected based on the characteristics of the visual features, enabling a more accurate estimation of the probability distribution. Comprehensive experiments on seven visual question answering benchmarks validate the effectiveness of the proposed TOFC method. Results show that TOFC achieves up to 60% reduction in data transmission overhead and 50% reduction in system latency while maintaining identical task performance, compared with traditional image compression methods. Copyright © 2025, The Authors. All rights reserved.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

Improved Speaker-Emotion Voice Conversion with Limited Corpus based on Large Language Model and Pre-trained Model

Improved Speaker-Emotion Voice Conversion with Limited Corpu...

引用

Mobile Computing and Sustainable Informatics (ICMCSI), International Conference on

作者： Fanchang Tang YaLing Amit Yadav Abhishek Pratap Sah Asif Khan Department of Software Engineering Chengdu Neusoft University Chengdu China College of Engineering IT and Environment Charles Darwin University NT Australia School of Management Science and Engineering University of Electronic Science and Technology of China Chengdu China Department of Computer Application Integral University Lucknow India

ISBN: (数字)9798331522667

ISBN: (纸本)9798331522674

Existing research on speaker and emotional voice conversion often focuses on separate tasks, neglecting their joint exploration. Furthermore, the limited availability of emotional corpora for target speakers poses a significant challenge for training robustness and generalized models. This paper proposes an improved scheme for speaker-emotion voice conversion with limited target speaker's emotional corpus, integrating a large language model and a pre-trained emotional speech synthesis model. It introduces several enhancements to enhance the quality of converted speech in terms of speaker similarity and emotional expressiveness. First, emotionally tagged text is generated using a large language model and emotional speech is synthesized from this text using a fine-tuned pre-trained emotional speech synthesis model. Then, a speaker-emotion voice conversion model is co-trained with both synthesized and real target emotional speech. Finally, the model is fine-tuned with the real target emotional speech to further boost the speaker and emotional similarity.

关键词： Training Large language models Computational modeling Speech enhancement Robustness Libraries Speech synthesis Informatics Optimization Mobile computing

来源：评论

学校读者我要写书评

暂无评论

Sparse and Dense: Learning Confusion Representation Network for 3D Action Recognition

引用

IEEE Internet of Things Journal 2025年

作者： Hou, Xinran Geng, Pei Li, Tianchen Li, Yalin Li, Yan Lyu, Lei School of Information Science and Engineering Shandong Normal University Jinan250358 China School of Information Engineering Shandong Management University Jinan250100 China Shandong Provincial Key Laboratory for Novel Distributed Computer Software Technology Jinan250358 China

In the field of the Internet of Medical Things (IoMT), the demand for Human Action Recognition (HAR) is growing. Due to the limitations of portability and privacy of traditional sensors, many endeavors have made significant progress in 3D skeleton-based action recognition. However, existing methods ignore potential higher-order semantic information between joints and fail to perceive rapidly changing dynamic details, resulting in frequent confusion of actions with similar motion trajectories. To alleviate this issue, we propose a novel learning confusion representation network (LCR-Net). Specifically, a progressive feature enhancement module is first designed to utilize self-attention to gradually aggregate lower-order features to higher-order features, emphasizing the relative movement between body parts. Second, we design the enhanced spatiotemporal convolution to explore the potential spatio-temporal dependencies between joints by adding a mask matrix and an attention fusion mechanism. To further perceive the spatiotemporal relationships in subtle changes, we divide the interactive sparse-dense pathways at different spatio-temporal resolutions and enhance the complementary information between the two pathways through feature interaction. Finally, the frequency excitation learning module is proposed to efficiently learn the importance of different frequencies by cross-channel modeling, promoting the compactness of actions within classes and the separability of confusion actions. In addition, the lightweight LCR-Net+ is achieved through model compression optimization to meet the deployment requirements of IoT systems. Comprehensive experiments conducted on three public datasets (NTU-RGB+ D60&120, NW-UCLA) demonstrate the superior performance of our model. © 2025 IEEE. All rights reserved.

关键词： Joints (anatomy)

来源：评论

学校读者我要写书评

暂无评论

GridNet-3D: A Novel Real-Time 3D Object Detection Algorithm Based on Point Cloud

引用

Chinese Journal of Electronics 2021年第5期30卷 931-939页

作者： YUE Yuanchen CAI Yunfei WANG Dongsheng School of Computer Science and Engineering Nanjing University of Science and Technology

3D object detection based on point cloud has an important application prospect in automatic driving technology. Aiming at the low precision of 3D object detection based on point cloud and the poor real-time performance caused by large numbers of 3D convolutions, a novel end-to-end real-time object detection algorithm named GridNet-3D is proposed. In the work, 2D gridmapping is used to preprocess the original point *** a novel structure grid encoding layer is adopted to encode point cloud features and is gotten grid feature maps in bird's eye view which is connected to region proposal network module to generate detections. Despite only using point clouds, the results on the KITTI 3D detection benchmark show that our algorithm has higher detection precision and better real-time performance on the detection of cars, pedestrians and cyclists, which has high practical value.

关键词： GridNet-3D point cloud features region proposal network module structure grid encoding layer grid feature maps 2D gridmapping intelligent transportation systems end-to-end real-time object detection algorithm KITTI 3D detection benchmark feature extraction automatic driving technology object detection 3D convolution

来源：评论

学校读者我要写书评

暂无评论

Decoupling While Coupling: Towards More Accurate Stereo Image Sand Removal Beyond Certainty

Decoupling While Coupling: Towards More Accurate Stereo Imag...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Bingcai Wei Hui Liu Chuang Qian Yi Jia Wangyu Wu Zhishan Li School of Computer Science Wuhan University Wuhan China GNSS Research Center Wuhan Unicersity Wuhan China Intelligent Transport Systems Research Center Wuhan University of Technology Wuhan China College of Information and Control Engineering Jilin Institute of Chemical Technology Jilin China University of Liverpool Liverpool UK School of Computer Science and Engineering South China University of Technology Guangzhou China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Stereo image sand removal is crucial to improve the perceptual quality for autonomous driving perception. Existing methods often fall short in accurately estimating the uncertainty inherent in degraded images, leading to suboptimal outcomes. To address this, we introduce a novel framework named Decoupling While Coupling(DWC). DWC pioneers the integration of inter-view uncertainty estimation, cross-view uncertainty-aware interaction and block-wise uncertainty representation for superior stereo image sand removal. For cross-view information interaction, we propose an Uncertainty-aware Cross-view Attentive Interaction module(UCAI) to cope with the lack of uncertainty estimation ability in the existing cross-view information interaction mechanism. For the uncertainty perception and information interaction within the inter-view, we propose a Distribution Modeling Coupling Block(DMCB), which transmits the representation of uncertainty between each backbone module. For block-wise uncertainty estimation, we use our proposed Uncertainty-aware Distribution Feature Modulator(UDFM) as the backbone of DWC to modulate the uncertainty inside the neural network itself. Extensive experimental validations on our proposed stereo image sand removal dataset SandST confirm the efficacy of DWC. Our method not only achieves higher PSNR and SSIM, but also exhibits enhanced robustness against various sand degrees and patterns.

关键词： Couplings Uncertainty Neural networks Estimation Signal processing Robustness Stereo vision Image restoration Speech processing Autonomous vehicles

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：