检索结果-内蒙古大学图书馆

32nd ACM International Conference on Multimedia, MM 2024

作者： Huang, Jingjia Tu, Jingyan Meng, Ge Wang, Yingying Dong, Yuhang Tu, Xiaotong Ding, Xinghao Huang, Yue School of Informatics Xiamen University Xiamen China Key Laboratory of Multimedia Trusted Perception and Efficient Computing Xiamen University Xiamen China

ISBN: (纸本)9798400706868

Multi-focus image fusion (MFIF) aims to combine multiple images with different focused regions into a single all-in-focus image. Existing unsupervised deep learning-based methods only fuse structural information of images in the spatial domain, neglecting potential solutions from the frequency domain exploration. In this paper, we make the first attempt to integrate spatial-frequency information to achieve high-quality MFIF. We propose a novel unsupervised spatial-frequency interaction MFIF network named SFIMFN, which consists of three key components: Adaptive Frequency Domain Information Interaction Module (AFIM), Ret-Attention-Based Spatial Information Extraction Module (RASEM), and Invertible Dual-domain Feature Fusion Module (IDFM). Specifically, in AFIM, we interactively explore global contextual information by combining the amplitude and phase information of multiple images separately. In RASEM, we design a customized transformer to encourage the network to capture important local high-frequency information by redesigning the self-attention mechanism with a bidirectional, two-dimensional form of explicit decay. Finally, we employ IDFM to fuse spatial-frequency information without information loss to generate the desired all-in-focus image. Extensive experiments on different datasets demonstrate that our method significantly outperforms state-of-the-art unsupervised methods in terms of qualitative and quantitative metrics as well as the generalization ability. © 2024 ACM.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

Prompt-Enhanced Software Vulnerability Detection Using ChatGPT 24

Prompt-Enhanced Software Vulnerability Detection Using ChatG...

引用

46th International Conference on Software Engineering: Companion, ICSE-Companion 2024

作者： Zhang, Chenyuan Liu, Hao Zeng, Jiutian Yang, Kejing Li, Yuhong Li, Hui Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China School of Informatics Xiamen University China Alibaba China

ISBN: (纸本)9798400705021

With the increase in software vulnerabilities that cause significant economic and social losses, automatic vulnerability detection has become essential in software development and maintenance. Recently, large language models (LLMs) have received considerable attention due to their stunning intelligence, and some studies consider using ChatGPT for vulnerability detection. However, they do not fully consider the characteristics of LLMs, since their designed questions to ChatGPT are simple without a prompt design tailored for vulnerability detection. This paper launches a study on the performance of software vulnerability detection using ChatGPT with different prompt designs. Firstly, we complement previous work by applying various improvements to the basic prompt. Moreover, we incorporate structural and sequential auxiliary information to improve the prompt design. Moreover, we leverage ChatGPT's ability of memorizing multi-round dialogue to design suitable prompts for vulnerability detection. We conduct extensive experiments on two vulnerability datasets to demonstrate the effectiveness of promptenhanced vulnerability detection using ChatGPT. © 2024 IEEE Computer Society. All rights reserved.

关键词： Software design

来源：评论

学校读者我要写书评

暂无评论

A Microwave Sensor for Detection of Water Adulteration and Spoilage in Milk Based on Split-Ring Resonator 7

A Microwave Sensor for Detection of Water Adulteration and S...

引用

7th IEEE International Conference on Electronic Information and Communication Technology, ICEICT 2024

作者： Ding, Shuying Li, Yingsong Huang, Zhixiang Sinkevich, Eugene Mordachev, Vladimir Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education China Belarusian State University of Informatics and Radioelectronics EMC R and D Laboratory Minsk Belarus

ISBN: (纸本)9798350384437

The paper introduces a microwave sensor based on split-ring resonators (SRR) for detecting the moisture content and spoilage of milk. This sensor is characterized by its simple structure and high sensitivity, utilizing SRR to enhance the local electric field intensity of the electromagnetic field. By measuring the transmission characteristics of microwave signals, it can accurately detect the moisture content and spoilage of milk samples. The sensor operates at a frequency of 6 GHz and has dimensions of 30×25×1.6 mm. The study establishes the relationship between resonance frequency and water content in milk through simulated data, which provides an effective method for monitoring milk quality and holds potential applications in the food industry, contributing significantly to ensuring food safety. © 2024 IEEE.

关键词： Microwave sensors

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving in Agricultural IoT: Intrusion Detection Using Federated Learning and CNN 6

Privacy-Preserving in Agricultural IoT: Intrusion Detection ...

引用

6th International Conference on Advanced Aspects of Software Engineering, ICAASE 2024

作者： Khacha, Amina Saadouni, Rafika Harbi, Yasmine Aliouat, Zibouda Gherbi, Chirihane Harous, Saad LRSD Laboratory Ferhat Abbas University of Setif 1 Setif Algeria College of Computing and Informatics University of Sharjah Sharjah United Arab Emirates

ISBN: (纸本)9798331522810

The Agricultural Internet of Things (AIoT) network integrates agriculture with IoT to enhance productivity and improve quality. This infrastructure connects many devices, facilitating extensive information exchange within the network. However, this increased data exchange also heightens the network's susceptibility to attacks and vulnerabilities, posing risks and potentially causing damage to the network infrastructure. Intrusion Detection Systems (IDS) are effective solutions for detecting attacks and preserving productivity. Many existing approaches in the literature combine deep learning with IDS to create robust anomaly-based IDS. However, these solutions often encounter challenges related to data collection, which compromises user privacy by centralizing data from various entities into a single entity. Our paper proposes a privacy-preserving IDS based on federated learning techniques and Convolutional neural networks (CNN) to develop a robust IDS with significant performance. We evaluate our experiments using a new dataset, Edge-IIoT, which consists of real IoT traffic across binary, 6-class, and 15-class scenarios with 10 and 15 clients. The results demonstrate the performance of our model across all scenarios, achieving 100% and 99.99% accuracy in binary classification and both 6-class and 15-class scenarios, respectively. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

PSO-based Feature Selection for DDoS Detection using Machine Learning in Smart Agriculture

PSO-based Feature Selection for DDoS Detection using Machine...

引用

2024 International Conference on Advances in Electrical and Communication Technologies, ICAECOT 2024

作者： Saadouni, Rafika Khacha, Amina Gherbi, Chirihane Harbi, Yasmine Aliouat, Zibouda Harous, Saad Ferhat Abbas University of Setif 1 Lrsd Laboratory Setif Algeria University of Sharjah College of Computing and Informatics Sharjah United Arab Emirates

ISBN: (纸本)9798350353754

Distributed denial-of-service (DDoS) attacks pose a significant threat to smart agriculture systems by disrupting services through the saturation of targeted networks with traffic from multiple sources. Real-time detection of these attacks has become a critical cybersecurity task in smart agriculture. However, the analysis of traffic in DDoS attack detection is often hindered by the large number of features present, leading to prolonged processing times. Furthermore, current DDoS detection methods usually have a limited scope regarding the types of attacks they can effectively detect, overlooking the full spectrum of potential DDoS attack scenarios. This work presents a DDoS attack detection using Particle Swarm Optimization (PSO) for feature selection (FS) combined with various machine learning classifiers. The PSO-FS-DDoS-ML method is evaluated on the CICIoT-2023 dataset, which includes twelve distinct types of DDoS attacks. We conducted a comprehensive analysis before and after feature selection in both binary and multiclass classification scenarios, demonstrating improvements in classification accuracy, precision, recall, F1-score, and reductions in false positive rates and computational time. Experimental results show that PSO-FS-DDoS-ML achieves an accuracy of 99.99% for Decision Trees (DT), 99.97% for Random Forest (RF), and 99.93% for k-Nearest Neighbors (KNN) in multiclass classification after feature selection, with 24, 18, and 22 selected features, respectively. In binary classification, PSO-FS-DDoS-ML achieves 100% accuracy with 0% false positive rate (FPR). © 2024 IEEE.

关键词： Denial-of-service attack

来源：评论

学校读者我要写书评

暂无评论

Robustness-Enhanced Data-Free Quantization for Vision Transformer 24

Robustness-Enhanced Data-Free Quantization for Vision Transf...

引用

9th International Conference on Cyber Security and Information Engineering, ICCSIE 2024

作者： Zhou, Yuyao Chao, Fei Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University China School of Informatics Xiamen University China

ISBN: (纸本)9798400718137

Transformer has been a huge success in computer vision tasks, but its complex architecture and huge computational overhead limit the application of Vision Transformer (ViT) on edge devices. Recently, some works have focused on the field of data-free quantization of ViTs with good results. However, as they ignore the properties of ViT’s non-smooth loss landscape, it leads to a quantization model that is susceptible to small perturbations. This paper proposes RE-ViT, a robustness-enhanced data-free quantization method for ViTs. RE-ViT utilizes Image Robustness Enhancement, which does interference with the input during data generation, to obtain synthetic samples with high semanticity and robustness. In the model quantization stage, contrast learning is introduced to alleviate the non-smooth loss landscape phenomenon of ViTs. A large number of experiments demonstrate the effectiveness of RE-ViT and it is shown to be superior to State-of-the-Art. RE-ViT establishes a new baseline for data-free quantization of ViTs. © 2024 Copyright held by the owner/author(s).

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Multi-Level Cross-Modal Alignment for Speech Relation Extraction

Multi-Level Cross-Modal Alignment for Speech Relation Extrac...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Zhang, Liang Yang, Zhen Fu, Biao Lu, Ziyao Shao, Liangying Liu, Shiyu Meng, Fandong Zhou, Jie Wang, Xiaoli Su, Jinsong School of Informatics Xiamen University China Xiamen Key Laboratory of Intelligent Storage and Computing School of Informatics Xiamen University China Pattern Recognition Center WeChat AI Tencent Inc. China

ISBN: (纸本)9798891761643

Speech Relation Extraction (SpeechRE) aims to extract relation triplets from speech data. However, existing studies usually use synthetic speech to train and evaluate SpeechRE models, hindering the further development of SpeechRE due to the disparity between synthetic and real speech. Meanwhile, the modality gap issue, unexplored in SpeechRE, limits the performance of existing models. In this paper, we construct two real SpeechRE datasets to facilitate subsequent researches and propose a Multi-level Cross-modal Alignment Model (MCAM) for SpeechRE. Our model consists of three components: 1) a speech encoder, extracting speech features from the input speech;2) an alignment adapter, mapping these speech features into a suitable semantic space for the text decoder;and 3) a text decoder, autoregressively generating relation triplets based on the speech features. During training, we first additionally introduce a text encoder to serve as a semantic bridge between the speech encoder and the text decoder, and then train the alignment adapter to align the output features of speech and text encoders at multiple levels. In this way, we can effectively train the alignment adapter to bridge the modality gap between the speech encoder and the text decoder. Experimental results and in-depth analysis on our datasets strongly demonstrate the efficacy of our method. Our source code is available at https://***/DeepLearnXMU/SpeechRE-MCAM. © 2024 Association for Computational Linguistics.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Designing Quantizers for Low-Precision Post-Training Quantization: A Standard Pipeline Approach for CNNs 24

Designing Quantizers for Low-Precision Post-Training Quantiz...

引用

9th International Conference on Cyber Security and Information Engineering, ICCSIE 2024

作者： Yang, Xiao Chao, Fei Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University China School of Informatics Xiamen University China

ISBN: (纸本)9798400718137

Quantization is a widely adopted technique for enhancing the inference performance of neural networks by exploiting hardware support for low-precision algorithms. It offers significant advantages such as higher throughput, reduced memory traffic, and decreased storage requirements. Neural networks have demonstrated robustness to quantization, allowing them to be quantized to lower bit widths with minimal impact on accuracy. However, the quantization process often leads to a loss in precision, especially when performed without retraining. Addressing this issue, this paper focuses on the design of quantizers for low-precision post-training quantization tasks, aiming to minimize accuracy loss without the need for access to the full training dataset or extensive computational resources. We propose a novel approach that introduces outlier clipping for weights and designs bias correction schemes for both weights and activations. Our methodology emphasizes the development of a standard pipeline for low-precision post-training quantization, which balances simplicity and performance. Through comprehensive experiments, we demonstrate that our proposed pipeline achieves superior accuracy compared to many existing post-training quantization methods. This work contributes to the ongoing efforts in the field by providing a practical and efficient solution for quantizing convolutional neural networks (CNNs) in low-precision scenarios. © 2024 Copyright held by the owner/author(s).

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Time-Domain Speech Enhancement Assisted by Multi-Resolution Frequency Encoder and Decoder 48

Time-Domain Speech Enhancement Assisted by Multi-Resolution ...

引用

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

作者： Shi, Hao Mimura, Masato Wang, Longbiao Dang, Jianwu Kawahara, Tatsuya Kyoto University Graduate School of Informatics Kyoto Japan Tianjin University College of Intelligence and Computing Tianjin Key Laboratory of Cognitive Computing and Application Tianjin China

ISBN: (纸本)9781728163277

Time-domain speech enhancement (SE) has recently been intensively investigated. Among recent works, DEMUCS [1] introduces multi-resolution STFT loss to enhance performance. However, some resolutions used for STFT contain non-stationary signals, and it is challenging to learn multi-resolution frequency losses simultaneously with only one output. For better use of multi-resolution frequency information, we supplement multiple spectrograms in different frame lengths into the time-domain encoders. They extract stationary frequency information in both narrowband and wideband. We also adopt multiple decoder outputs, each of which computes its corresponding resolution frequency loss. Experimental results show that (1) it is more effective to fuse stationary frequency features than non-stationary features in the encoder, and (2) the multiple outputs consistent with the frequency loss improve performance. Experiments on the Voice-Bank dataset show that the proposed method obtained a 0.14 PESQ improvement. © 2023 IEEE.

关键词： multiresolution spectrograms Speech enhancement time domain

来源：评论

学校读者我要写书评

暂无评论

A Real-Time Global Inference Network for One-Stage Referring Expression Comprehension

引用

IEEE Transactions on Neural Networks and Learning Systems 2023年第1期34卷 134-143页

作者： Zhou, Yiyi Ji, Rongrong Luo, Gen Sun, Xiaoshuai Su, Jinsong Ding, Xinghao Lin, Chia-Wen Tian, Qi Xiamen University Media Analytics and Computing Laboratory Xiamen361005 China Xiamen University School of Informatics Informatics and Communication Engineering Department Xiamen361005 China School of Informatics Xiamen University Media Analytics and Computing Laboratory Department of Artificial Intelligence Xiamen361005 China Xiamen University School of Informatics Xiamen361005 China National Tsing Hua University Department of Electrical Engineering Hsinchu30013 Taiwan Institute of Communications Engineering National Tsing Hua University Hsinchu30013 Taiwan Huawei Technologies Company Ltd. Cloud BU Shenzhen518129 China

Referring expression comprehension (REC) is an emerging research topic in computer vision, which refers to the detection of a target region in an image given a test description. Most existing REC methods follow a multistage pipeline, which is computationally expensive and greatly limits the applications of REC. In this article, we propose a one-stage model toward real-time REC, termed real-time global inference network (RealGIN). RealGIN addresses the issues of expression diversity and complexity of REC with two innovative designs: adaptive feature selection (AFS) and Global Attentive ReAsoNing (GARAN). Expression diversity concerns varying expression content, which includes information such as colors, attributes, locations, and fine-grained categories. To address this issue, AFS adaptively fuses features of different semantic levels to tackle the changes in expression content. In contrast, expression complexity concerns the complex relational conditions in expressions that are used to identify the referent. To this end, GARAN uses the textual feature as a pivot to collect expression-aware visual information from all regions and then diffuses this information back to each region, which provides sufficient context for modeling the relational conditions in expressions. On five benchmark datasets, i.e., RefCOCO, RefCOCO+, RefCOCOg, ReferIT, and Flickr30k, the proposed RealGIN outperforms most existing methods and achieves very competitive performances against the most advanced one, i.e., MAttNet. More importantly, under the same hardware, RealGIN can boost the processing speed by 10-20 times over the existing methods. © 2012 IEEE.

关键词： Semantics

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：