检索结果-内蒙古大学图书馆

IEEE International Conference on Automated Software Engineering (ASE)

作者： Zhen Li Ruqian Zhang Deqing Zou Ning Wang Yating Li Shouhuai Xu Chen Chen Hai Jin School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Cluster and Grid Computing Lab National Engineering Research Center for Big Data Technology and System Hubei Engineering Research Center on Big Data Security Department of Computer Science University of Colorado Colorado Springs USA Center for Research in Computer Vision University of Central Florida USA School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

Deep learning has been widely used in source code classification tasks, such as code classification according to their functionalities, code authorship attribution, and vulnerability detection. Unfortunately, the black-box nature of deep learning makes it hard to interpret and understand why a classifier (i.e., classification model) makes a particular prediction on a given example. This lack of interpretability (or explainability) might have hindered their adoption by practitioners because it is not clear when they should or should not trust a classifier's prediction. The lack of interpretability has motivated a number of studies in recent years. However, existing methods are neither robust nor able to cope with out-of-distribution examples. In this paper, we propose a novel method to produce Robust interpreters for a given deep learning-based code classifier; the method is dubbed Robin. The key idea behind Robin is a novel hybrid structure combining an interpreter and two approximators, while leveraging the ideas of adversarial training and data augmentation. Experimental results show that on average the interpreter produced by Robin achieves a 6.11% higher fidelity (evaluated on the classifier), 67.22% higher fidelity (evaluated on the approximator), and 15.87x higher robustness than that of the three existing interpreters we evaluated. Moreover, the interpreter is 47.31% less affected by out-of-distribution examples than that of LEMNA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Method of Constructing and Automatically Labeling Radio Frequency Signal Training Dataset for UAV 48

A Method of Constructing and Automatically Labeling Radio Fr...

引用

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

作者： Liu, Chao Ma, Ruipeng Si, Zheng Chi, Mingmin Fudan University School of Computer Science Shanghai Key Laboratory of Data Science China Zhengzhou Zhongke Institute of Integrated Circuit and System Application China Zhengzhou University School of Cyber Science and Engineering China Zhengzhou University Henan Institute of Advanced Technology China

ISBN: (纸本)9781728163277

The problem of signal detection and classification of multiple UAVs can be solved using object detection techniques in computer vision. However, this requires collecting and labeling a large amount of reliable raw data. Since the UAV signal dataset cannot be directly applied to object detection, we propose a method using time-frequency domain filtering and automatic labeling to construct a large-scale time-frequency spectrogram dataset. Experimental results show that the average recognition accuracies of image transmission signals and remote control signals under interference conditions are 97% and 82%, respectively, while the average errors of signal parameters are 0.93% and 5.57%. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Toward Comprehensive Semantic Prompt for Region Contrastive Learning Underwater Image Enhancement

Toward Comprehensive Semantic Prompt for Region Contrastive ...

引用

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

作者： Xiao Wang Yongsheng Fu Wei Wang Wei Liu School of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Underwater image enhancement (UIE) focuses on mitigating image quality degradation due to light absorption and scattering. However, most existing methods enhance images via a global and uniform manner, neglecting the inherent semantic information in different regions, which may cause the network to easily deviate from the region’s original color. Moreover, these methods typically rely on clear images to guide network convergence, a process constrained by the limited availability of real-world datasets, making it extremely challenging to train enhancement models for various degradations. To address these challenges, this paper introduces a semantic guidance and region contrastive constraints network (SRCNet). Initially, we propose a semantic-aware RWKV (Receptance Weighted Key Value) block and a semantic prompt regularization module. These components leverage intra-target semantic correlations to preserve image details and colors within a global perceptual framework, while employing focal loss to emphasize the restoration of severely degraded regions. Subsequently, we introduce a region contrastive learning method that effectively utilizes negative samples to precisely capture features sensitive to degradation factors, thereby fostering robust feature distributions. Finally, experimental results demonstrate that our method outperforms existing state-of-the-art (SOTA) approaches.

关键词： Degradation Visualization Image color analysis Semantics Signal processing algorithms Contrastive learning Speech enhancement Signal processing Image restoration Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Event-based Video Person Re-identification via Cross-Modality and Temporal Collaboration

arXiv

引用

arXiv 2025年

作者： Li, Renkai Yuan, Xin Liu, Wei Xu, Xin School of Computer Science and Technology Wuhan University of Science and Technology China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System China

Video-based person re-identification (ReID) has become increasingly important due to its applications in video surveillance applications. By employing events in video-based person ReID, more motion information can be provided between continuous frames to improve recognition accuracy. Previous approaches have assisted by introducing event data into the video person ReID task, but they still cannot avoid the privacy leakage problem caused by RGB images. In order to avoid privacy attacks and to take advantage of the benefits of event data, we consider using only event data. To make full use of the information in the event stream, we propose a Cross-Modality and Temporal Collaboration (CMTC) network for event-based video person ReID. First, we design an event transform network to obtain corresponding auxiliary information from the input of raw events. Additionally, we propose a differential modality collaboration module to balance the roles of events and auxiliaries to achieve complementary effects. Furthermore, we introduce a temporal collaboration module to exploit motion information and appearance cues. Experimental results demonstrate that our method outperforms others in the task of event-based video person ReID. Copyright © 2025, The Authors. All rights reserved.

关键词： Information leakage

来源：评论

学校读者我要写书评

暂无评论

VAGeo: View-specific Attention for Cross-View Object Geo-Localization

arXiv

引用

arXiv 2025年

作者： Li, Zhongyang Yuan, Xin Liu, Wei Xu, Xin School of Computer Science and Technology Wuhan University of Science and Technology China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System China

Cross-view object geo-localization (CVOGL) aims to locate an object of interest in a captured ground- or drone-view image within the satellite image. However, existing works treat ground-view and drone-view query images equivalently, overlooking their inherent viewpoint discrepancies and the spatial correlation between the query image and the satellite-view reference image. To this end, this paper proposes a novel View-specific Attention Geo-localization method (VAGeo) for accurate CVOGL. Specifically, VAGeo contains two key modules: view-specific positional encoding (VSPE) module and channel-spatial hybrid attention (CSHA) module. In object-level, according to the characteristics of different viewpoints of ground and drone query images, viewpoint-specific positional codings are designed to more accurately identify the click-point object of the query image in the VSPE module. In feature-level, a hybrid attention in the CSHA module is introduced by combining channel attention and spatial attention mechanisms simultaneously for learning discriminative features. Extensive experimental results demonstrate that the proposed VAGeo gains a significant performance improvement, i.e., improving acc@0.25/acc@0.5 on the CVOGL dataset from 45.43%/42.24% to 48.21%/45.22% for ground-view, and from 61.97%/57.66% to 66.19%/61.87% for drone-view. Copyright © 2025, The Authors. All rights reserved.

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

Arrayed Waveguide Grating for Visible Light Application 14

Arrayed Waveguide Grating for Visible Light Application

引用

Holography, Diffractive Optics, and Applications XIV 2024

作者： Sun, Quancheng Feng, Zhihua Li, Yuhong Wang, Dongcheng Wang, Yan Liu, Haipeng Li, Junhao Yang, Cunliang Feng, Jijun Shanghai Key Laboratory of Modern Optical System Engineering Research Center of Optical Instrument and System Ministry of Education School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai200093 China School of Physics Xidian University Shaanxi Xi'an710071 China Nanjing Electronic Devices Institute Jiangsu210016 China

ISBN: (纸本)9781510682085

Miniaturized spectrometers, owing to their compact dimensions, high sensitivity, and low cost, have been extensively applied in environmental monitoring, biomedical diagnostics, industrial inspection, and other fields. However, conventional miniature spectrometers often face challenges in simultaneously achieving high spectral resolution, miniaturization, and a high degree of integration. As a pivotal component in integrated optics, the Arrayed Waveguide Grating (AWG) possesses advantages such as exceptional resolution, broad spectral bandwidth, and superior integrability, thus serving as a highly effective means for the design and realization of miniature spectrometers. Here, a highly uniform visible light arrayed waveguide grating with a central wavelength of 633nm was designed and fabricated. The device was based on a 300 nm silicon nitride platform, with the waveguide width of 300nm. The beam diverges at the input star coupler, then propagates through the arrayed waveguide, and finally converges on the image plane of the output star coupler. There are 4 output channels with a channel spacing of 10nm, and the spectral resolution is 5nm. This configuration can provide a uniform spectral output with a high stability, making it suitable for applications in the field of spectral analysis. © 2024 SPIE. All rights reserved.

关键词： Spectral resolution

来源：评论

学校读者我要写书评

暂无评论

Vulnerability Detection Based on Adapter Tuning and Enhanced Feature Learning 36

Vulnerability Detection Based on Adapter Tuning and Enhanced...

引用

36th International Conference on Software Engineering and Knowledge Engineering, SEKE 2024

作者： Luo, Hui Lu, Lu Liang, Zhihong Suo, Siliang School of Computer Science and Engineering South China University of Technology Guangzhou China Pazhou Laboratory Guangzhou China PengCheng Laboratory Shenzhen China Electric Power Research Institute CSG Guangdong Guangzhou China Guangdong Provincial Key Laboratory of Power System Network Security Guangdong Guangzhou China

ISBN: (纸本)1891706594

Pre-trained code models have achieved promising results in the vulnerability detection field. The prevailing approach is to adapt these models with vulnerability datasets using inefficient full-model fine-tuning. These pre-trained models primarily capture the semantic features of code, while neglecting its structural characteristics. To address these issues, this paper proposes a vulnerability detection method with adapter tuning and enhanced feature learning. First, adapter modules are introduced to UniXcoder and tune only the parameters in the adapters to extract semantic features. This significantly reduces the number of training parameters and better adapts the model to downstream tasks. Then, structural features, including control and data flow information, are extracted from the Program Dependence Graph (PDG) to compensate for the limitations of pre-trained models that rely solely on semantic features. Finally, the semantic and structural features are integrated to train the detection model. The experimental results demonstrate that our proposed method outperforms state-of-the-art approaches and is highly efficient in terms of both training parameters and training data. © 2024 Knowledge systems Institute Graduate school. All rights reserved.

关键词： Data flow graphs

来源：评论

学校读者我要写书评

暂无评论

MG6D: A Deep Fusion Approach for 6D Pose Estimation with Mamba and Graph Convolution Network

引用

IEEE Access 2025年 13卷 100433-100445页

作者： Zhu, Jiaqi Li, Bin Zhao, Xinhua Tianjin University of Technology School of Computer Science and Engineering Tianjin 300384 China Tianjin University of Technology Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin 300384 China

Accurate and efficient 6D pose estimation is a fundamental technology in many industrial applications. While existing dense correspondence methods have shown progress, they face challenges in multimodal feature fusion under complex scenarios involving occlusions, illumination variations, and sensor noise. This paper proposes a novel 6D pose estimation framework that addresses these limitations through a hybrid Mamba-Graph architecture. The algorithm first introduces a panoramic attention fusion Mamba module, leveraging state-space modeling to capture long-range dependencies in multi-modal data while establishing cross-dimensional interactions between channel and spatial features to emphasize critical information. A dynamic graph convolutional adaptive fusion module is then designed to enable cross-modal geometric consistency modeling via multi-modal feature integration. Finally, a texture-geometry co-driven keypoint selection mechanism is proposed to ensure keypoint distributions satisfy both spatial uniformity and discriminability requirements. Experimental results on three common datasets demonstrate that the proposed algorithm achieves ADD(-S) metrics of 99.82%, 80.26%, and 97.2%, respectively. Notably, it exhibits significant advantages in pose estimation for objects with repetitive textures and high symmetry. © 2013 IEEE.

关键词： 6D pose estimation Fusion Mamba Graph feature fusion Panoramic Attention

来源：评论

学校读者我要写书评

暂无评论

A practical conflicting role-based cloud security risk evaluation method

Recent Advances in Computer Science and Communications

引用

Recent Advances in computer science and Communications 2021年第3期14卷 874-886页

作者： Han, Jin Zhan, Jing Xia, Xiaoqing Fan, Xue School of Computer Science Faculty of Information Technology Beijing University of Technology Beijing100124 China Beijing Key Laboratory of Trusted Computing Faculty of Information Technology Beijing University of Technology Beijing100124 China

Background: Currently, Cloud Service Provider (CSP) or third party usually proposes principles and methods for cloud security risk evaluation, while cloud users have no choice but to accept them. However, since cloud users and cloud service providers have conflicts of interests, cloud users may not trust the results of security evaluation performed by the CSP. Different cloud users may have different security risk preferences, which makes it difficult for the third party to con-sider all users' needs during evaluation. In addition, current security evaluation indexes for the cloud are too impractical to test (e.g., indexes like interoperability, transparency, portability are not easy to be evaluated). Methods: To solve the above problems, this paper proposes a practical cloud security risk evaluation method of decision-making based on conflicting roles by using the Analytic Hierarchy Process (AHP) with Aggregation of Individual Priorities (AIP). Results: Not only can our method bring forward a new index system based on risk source for cloud security and corresponding practical testing methods, but also can obtain the evaluation result with the risk preferences of conflicting roles, namely CSP and cloud users, which can lay a foundation for improving mutual trusts between the CSP and cloud users. The experiments show that the method can effectively assess the security risk of cloud platforms and in the case where the number of clouds increased by 100% and 200%, the evaluation time using our methodology increased by only 12% and 30%. Conclusion: Our method can achieve consistent decisions based on conflicting roles, high scalability and practicability for cloud security risk evaluation. © 2021 Bentham science Publishers.

关键词： Analytic hierarchy process

来源：评论

学校读者我要写书评

暂无评论

Coverage Probability of Distributed CoMP UAV-Assisted Cellular Networks

Coverage Probability of Distributed CoMP UAV-Assisted Cellul...

引用

International Symposium on Parallel and Distributed Processing with Applications, ISPA

作者： Yan Li Qingmin Long Qiang Tang Shiming He Bing Xiong School of Computer and Communication Engineering Changsha University of Science and Technology Changsha China Science and Technology on Information System Engineering Laboratory National University of Defense Technology Changsha China

ISBN: (数字)9798331509712

ISBN: (纸本)9798331509729

It is well-established that terrestrial communication systems may fail during emergencies such as earthquakes, tsunamis, and floods. Fortunately, with the rapid advancement of unmanned aerial vehicle (UAV) network technology, deploying UAV nodes as aerial base stations (BSs) is assuming an increasingly crucial role in facilitating downlink transmissions and restoring ground communication capabilities. However, a single UAV node is not sufficient to meet the requirements. Inspired by distributed communication, we introduce a performance analysis framework based on stochastic geometry to analyze the distributed coordinated multi-point (CoMP) UAV-assisted communication network. Specifically, we assume that all UAV nodes follow a homogeneous Poisson point process (PPP) and maintain a constant altitude. The entire space is tessellated by multiple hexagons, with multiple UAV nodes within each hexagonal region working together to serve terrestrial user equipments (UEs). For this region-centric cooperative model, we derive an exact expression for the coverage probability to quantify the performance improvement enabled by UAVs, analyze the upper bound of the coverage probability, and provide a simplified approximation. We then compare this model to a user-centric model. Our numerical findings demonstrate that the cooperation of UAV nodes can significantly enhance the coverage probability and save spectrum resources.

关键词： Analytical models Upper bound Spectral efficiency Earthquakes Stochastic processes Probability Autonomous aerial vehicles Tsunami Terrestrial communications Numerical models

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：