检索结果-内蒙古大学图书馆

2024 IEEE URUCON, URUCON 2024

作者： Dahri, Fida Hussain Laghari, Asif Ali Dahri, Nisar Ahmed Abro, Ghulam E Mustafa Estrela, Vania V. De Oliveira, G.G. Iano, Y. Chuma, Euclides L. Southeast University School of Computer Science and Engineering Nanjing China Shenyang Normal University Software College Shenyang China University Teknologi Malaysia Faculty of Educational Sciences and Technology Johor Bahru Malaysia King Fahd University of Petroleum and Minerals Interdisciplinary Research Centre for Aviation and Space Exploration Dhahran Saudi Arabia Department of Telecommunications Niteroi Brazil School of Electrical and Computer Engineering Campinas Brazil School of Technology Limeira Brazil

ISBN: (纸本)9798350355383

Unmanned aerial vehicles (UAVs) have boosted modern living. Tiny, frail high-density targets, low resolution, complicated backgrounds, noise, and poor real-time exposure performance have augmented due to UAV firms. Realtime recognition in high-altitude (HA) infrared thermal images is intricate. Our fresh OSTD-YOLOv8 is a multi-class target recognition tactic to tackle these issues and spot and classify objects on the HIT-UAV dataset. YOLOv8 is an effective advanced object detection model. Our OSTD-YOLOv8 model detects small objects in HA thermal images with 90% precision, 91.5% recall, 90.5% F1-score, 89.1% AP, and 98% mAP. Our unique approach delivers effective object recognition in difficult thermal imaging conditions. Consequently, this distinctive UAV-focused HA, thermal, target detection scheme can be used. © 2024 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Detecting Fake Deposit Attacks on Cross-chain Bridges from a Network Perspective

Detecting Fake Deposit Attacks on Cross-chain Bridges from a...

引用

IEEE International Symposium on Circuits and Systems (ISCAS)

作者： Kaixin Lin Dan Lin Ziye Zheng Yixiang Tan Jiajing Wu School of Computer Science and Engineering Sun Yat-Sen University Guangzhou China School of Software Engineering Sun Yat-Sen University Zhuhai China

ISBN: (数字)9798350330991

ISBN: (纸本)9798350331004

Cross-chain bridges are currently the most popular solution to support asset interoperability between heterogeneous blockchains. Over the past year, there have been more than ten serious attacks against cross-chain bridges, resulting in billions of dollars in losses. Among these attacks, fake deposits stand out as particularly destructive. Hackers can perpetrate such attacks by verifying the authenticity of proof associated with fake deposits on the target blockchain, subsequently pilfering the assets. However, existing tools have limitations in detecting this type of attack. To address this problem, this work proposes a tool to protect cross-chain bridges from fake deposit attacks by analyzing the network of transaction traces. Specifically, the framework first records the execution traces for each transaction, and then extracts the relevant contract interactions therein to extract statistical and structural features. Finally, real case labels are utilized to identify attacking and non-attacking transactions. We conducted experiments to validate the tool’s effectiveness and efficiency. In particular, for the detection of fake deposit transactions, our method achieved an average precision of 0.89, a recall value of 0.83, and the ability to identify 38.65 transactions per second.

关键词： Bridges Knowledge engineering computer hacking Bridge circuits Feature extraction Real-time systems Blockchains

来源：评论

学校读者我要写书评

暂无评论

ViRED: Prediction of Visual Relations in engineering Drawings

arXiv

引用

arXiv 2024年

作者： Gu, Chao Lin, Ke Luo, Yiyang Hou, Jiahui Li, Xiang-Yang School of Computer Science and Technology LINKE Lab University of Science and Technology of China Hefei China School of Software Tsinghua University Beijing China School of Computer Science and Engineering Nanyang Technological University Singapore Singapore

To accurately understand engineering drawings, it is essential to establish the correspondence between images and their description tables within the drawings. Existing document understanding methods predominantly focus on text as the main modality, which is not suitable for documents containing substantial image information. In the field of visual relation detection, the structure of the task inherently limits its capacity to assess relationships among all entity pairs in the drawings. To address this issue, we propose a vision-based relation detection model, named ViRED, to identify the associations between tables and circuits in electrical engineering drawings. Our model mainly consists of three parts: a vision encoder, an object encoder, and a relation decoder. We implement ViRED using PyTorch to evaluate its performance. To validate the efficacy of ViRED, we conduct a series of experiments. The experimental results indicate that, within the engineering drawing dataset, our approach attained an accuracy of 96% in the task of relation prediction, marking a substantial improvement over existing methodologies. The results also show that ViRED can inference at a fast speed even when there are numerous objects in a single engineering drawing. © 2024, CC BY-NC-SA.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

Category-aware Filtering for Open-set Semi-Supervised Object Detection

Category-aware Filtering for Open-set Semi-Supervised Object...

引用

computer Vision, Image and Deep Learning (CVIDL), International Conference on

作者： Yiqi Zou Kuo Wang Dongyu Zhang Mingzhi Mao Guanbin Li School of Computer Science and Engineering Sun Yat-sen University Guangzhou China School of Software Engineering Sun Yat-sen University Zhuhai China

ISBN: (数字)9798350373820

ISBN: (纸本)9798350373837

Semi-Supervised Object Detection (SSOD) has gained significant interest in recent years. However, the majority of existing methods are based on the close-set assumption. In this paper, we address a challenging but more practical scenario, Open-Set Semi-Supervised Object Detection (OSSOD), where out-of-distribution (OOD) samples are contained in unlabeled data. The previous approach employs an offline detector to eliminate OOD pseudo labels, which is intricate and time-consuming. And the limited availability of labeled data hampers the performance of the OOD detector. In contrast, we propose a simple yet effective approach that facilitates the detector’s performance in open scenarios. Specifically, we employ soft-distribution on all identified instances as our training objective to enhance the model’s feature extraction capability. And we further design a radius-aware matching approach to filter OOD samples according to categories with varying diversity in unlabeled data. Our category-aware design has been proven effective through extensive experiments, surpassing current state-of-the-art work.

关键词： Training Matched filters Image recognition Filtering Object detection Detectors Streaming media

来源：评论

学校读者我要写书评

暂无评论

Contrastive Deep Nonnegative Matrix Factorization For Community Detection

Contrastive Deep Nonnegative Matrix Factorization For Commun...

引用

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

作者： Yuecheng Li Jialong Chen Chuan Chen Lei Yang Zibin Zheng School of Computer Science and Engineering Sun Yat-sen University Guangzhou China School of Software Engineering Sun Yat-sen University Zhuhai China

Recently, nonnegative matrix factorization (NMF) has been widely adopted for community detection, because of its better interpretability. However, the existing NMF-based methods have the following three problems: 1) they directly transform the original network into community membership space, so it is difficult for them to capture the hierarchical information; 2) they often only pay attention to the topology of the network and ignore its node attributes; 3) it is hard for them to learn the global structure information necessary for community detection. Therefore, we propose a new community detection algorithm, named Contrastive Deep Nonnegative Matrix Factorization (CDNMF). Firstly, we deepen NMF to strengthen its capacity for information extraction. Subsequently, inspired by contrastive learning, our algorithm creatively constructs network topology and node attributes as two contrasting views. Furthermore, we utilize a debiased negative sampling layer and learn node similarity at the community level, thereby enhancing the suitability of our model for community detection. We conduct experiments on three public real graph datasets and the proposed model has achieved better results than state-of-the-art methods. Code available at https://***/6lyc/***.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EU-Nets: Enhanced, Explainable and Parsimonious U-Nets

arXiv

引用

arXiv 2025年

作者： Sun, Bohang Liò, Pietro School of Information and Software Engineering University of Electronic Science and Technology of China China Department of Computer Science and Technology University of Cambridge United Kingdom

In this study, we propose MHEX+, a framework adaptable to any U-Net architecture. Built upon MHEX+, we introduce novel U-Net variants, EU-Nets, which enhance explainability and uncertainty estimation, addressing the limitations of traditional U-Net models while improving performance and stability. A key innovation is the Equivalent Convolutional Kernel, which unifies consecutive convolutional layers, boosting interpretability. For uncertainty estimation, we propose the collaboration gradient approach, measuring gradient consistency across decoder layers. Notably, EU-Nets achieve an average accuracy improvement of 1.389% and a variance reduction of 0.83% across all networks and datasets in our experiments, requiring fewer than 0.1M parameters. © 2025, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

dgQuEST: Accelerating Large Scale Quantum Circuit Simulation through Hybrid CPU-GPU Memory Hierarchies 18th

dgQuEST: Accelerating Large Scale Quantum Circuit Simulation...

引用

18th IFIP WG 10.3 International Conference on Network and Parallel Computing, NPC 2021

作者： Feng, Tianyu Chen, Siyan You, Xin Zhong, Shuzhang Yang, Hailong Luan, Zhongzhi Qian, Depei State Key Laboratory of Software Development Environment Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China

ISBN: (纸本)9783030935702

With the advancement of quantum computing, verifying the correctness of the quantum circuits becomes critical while developing new quantum algorithms. Constrained by the obstacles of building practical quantum computers, quantum circuit simulation has become a feasible approach to develop and verify quantum algorithms. Although there are many quantum simulators available, they either achieve low performance on CPUs, or limited simulation scale (e.g., number of qubits) on GPUs due to limited memory capacity. Therefore, we propose dgQuEST, a novel acceleration method that utilizes hybrid CPU-GPU memory hierarchies for large-scale quantum circuit simulation across multiple nodes. dgQuEST adopts efficient memory management and communication schemes to leverage the distributed CPU and GPU memories for accelerating large-scale quantum simulation. Our evaluation demonstrates that dgQuEST achieves an average speedup of 403 × compared to QuEST on quantum circuit simulation with 32 qubits, and scales to quantum circuit simulation with 35 qubits on two GPU nodes, far beyond the state-of-the-art implementation HyQuas can support. © 2022, IFIP International Federation for Information Processing.

关键词： Circuit simulation

来源：评论

学校读者我要写书评

暂无评论

Sliced Maximal Information Coefficient: A Training-Free Approach for Image Quality Assessment Enhancement

arXiv

引用

arXiv 2024年

作者： Xiao, Kang Wang, Xu He, Yulin Chen, Baoliang Shen, Xuelin Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China School of Computer Science South China Normal University Guangzhou China

Full-reference image quality assessment (FR-IQA) models generally operate by measuring the visual differences between a degraded image and its reference. However, existing FR-IQA models including both the classical ones (e.g., PSNR and SSIM) and deep-learning based measures (e.g., LPIPS and DISTS) still exhibit limitations in capturing the full perception characteristics of the human visual system (HVS). In this paper, instead of designing a new FR-IQA measure, we aim to explore a generalized human visual attention estimation strategy to mimic the process of human quality rating and enhance existing IQA models. In particular, we model human attention generation by measuring the statistical dependency between the degraded image and the reference image. The dependency is captured in a training-free manner by our proposed sliced maximal information coefficient and exhibits surprising generalization in different IQA measures. Experimental results verify the performance of existing IQA models can be consistently improved when our attention module is incorporated. The source code is available at https://***/KANGX99/SMIC. Copyright © 2024, The Authors. All rights reserved.

关键词： Image correlation

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Multimodal Graph Contrastive Semantic Anchor Space Dynamic Knowledge Distillation Network for Cross-Media Hash Retrieval

Unsupervised Multimodal Graph Contrastive Semantic Anchor Sp...

引用

International Conference on Data engineering

作者： Yang Yu Meiyu Liang Mengran Yin Kangkang Lu Junping Du Zhe Xue Beijing Key Laboratory of Intelligent Communication Software and Multimedia School of Computer Science (National Pilot Software Engineering School) Beijing University of Posts and Telecommunications Beijing China

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

Cross-media hash retrieval are efficient and effective techniques for retrieval on multi-media database. The success of the Multimodal Large Models (MLM) provides a valuable direction to enhance the accuracy of multimodal hash retrieval, which achieves decent retrieval accuracy with finetuning the pretrained multimodal large models, but their massive model parameters significantly reduce retrieval efficiency. Knowledge Distillation (KD) methods enable small models to learn from the knowledge of larger models, achieving a reduction in model parameter count while ensuring a certain level of accuracy. However, current KD methods face challenges when applied in the multimodal domain, as it requires preserving the multimodal semantic information while minimizing accuracy degradation. To address these challenges, we propose a novel unsupervised multimodal graph contrastive semantic anchor space dynamic knowledge distillation network for cross-media hash retrieval (GASKN). Firstly, to obtain a multimodal semantic anchor space, we construct a large multimodal fusion teacher model using the BEiT-3 model as the backbone. This teacher model is capable of encoding data from different modalities, such as images and text, using the same multimodal encoder to acquire multimodal hash codes that contain rich information from both modalities simultaneously. Secondly, to ensure efficient retrieval capabilities for the student model, we utilize the ALBERT text encoding model and the BiFormer image encoding model as the compact student model's backbones. This allows us to build a lightweight student model with only a twentieth of the parameter count of the teacher model. We propose a dynamic knowledge distillation technique to transfer the multimodal semantic anchor space knowledge embedded in the multimodal large teacher model to the lightweight student model as much as possible. Thirdly, to further distill the structural knowledge of the semantic anchor space from the teacher model to

关键词： Knowledge engineering Degradation Accuracy Image coding Databases Heuristic algorithms Semantics

来源：评论

学校读者我要写书评

暂无评论

Data Centric Blockchain Based Evaluation Approach to Analyze E-Commerce Reviews Using Machine and Deep Learning Techniques 20

Data Centric Blockchain Based Evaluation Approach to Analyze...

引用

20th International computer Conference on Wavelet Active Media Technology and Information Processing, ICCWAMTIP 2023

作者： Acheampong, Edward Mensah Zhou, Shijie Liao, Yongjian Atandoh, Peter Addo, Daniel Antwi-Boasiako, Emmanuel Nkrumah, Rose Aggrey, Esther Stacy E.B. Appiah-Twum, Michael School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China Ghana Institute of Management and Public Administration Department of Computer Science Ghana University of Cape Coast Department of Basic Education Ghana School of Resource and Environment University of Electronic Science and Technology of China Chengdu China

ISBN: (纸本)9798350318982

Machine and deep learning techniques are now essential for many different kinds of solutions in many areas, applications, and businesses. Analyzing e-commerce reviews using machine and deep learning techniques can motivate a company to make more wise decisions regarding the quality and services it offers. But issues can occur if there is insufficient high-quality data for the training, scalability, and upkeep of learning models. To address these important issues, we suggest a data-centric learning architecture that makes use of a blockchain and Interplanetary File System (IPFS)-based storage. Our architecture provides secure and cost-effective data storage and an incentive mechanism. Our experiment shows that as the dataset gets bigger, the Naïve Bayes (NB) and the Support Vector Machine (SVM) models get 2% more accurate, the Convolutional Neural Network (CNN) model gets 4% more accurate, and the Long Short-Term Memory (LSTM) model gets 3 % more accurate. The deep learning models exhibited higher accuracy rates than the machine learning models because hidden layers of deep learning possess the ability to extract intricate syntactic features from the review text. © 2023 IEEE.

关键词： Customer satisfaction

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：