检索结果-内蒙古大学图书馆

31st International Conference on Multimedia Modeling, MMM 2025

作者： Yan, Hao Bai, Jing The School of Computer Science and Engineering North Minzu University Ningxia Yinchuan750021 China The Key Laboratory of Images and Graphics Intelligent Processing of State Ethnic Affairs Commission Ningxia Yinchuan750021 China

ISBN: (纸本)9789819620609

PointCLIP shows that transferring 2D knowledge to zero-shot 3D shape classification tasks can be effective, even without incorporating 3D-specific knowledge. However, the absence of 3D knowledge limits the model’s performance, leading to efforts focused on improving 3D-to-2D projection algorithms. This work advances previous methods by introducing a learnable fine-tuning strategy, called MDT-Net, for Contrastive Language-Image Pre-training (CLIP) on 3D datasets. MDT-Net freezes the CLIP encoder to keep view features aligned with semantic information and incorporates a shape decoder with masked view consistency and attention-guided fusion, enabling more effective fine-tuning of CLIP for 3D tasks. The decoder receives both raw view features and masked view features. In the shallow layers, a mask consistency constraint is utilized between two types of view features to enhance the model’s generalization and robustness. In the deeper layers, attention-guided fusion is introduced to better capture the contextual information between views and compact all view features into one. MDT-Net is evaluated on different benchmarks of 5 datasets for zero-shot classification, achieving a competitive classification accuracy on ModelNet10, ModelNet40, McGill, and ZS3D datasets. These experiment results demonstrate the effectiveness of this approach. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

keycap character detection model based on target classification 7

Keycap character detection model based on target classificat...

引用

2024 7th International Conference on intelligent Manufacturing and Automation, IMA 2024

作者： Xiong, Taiping Zhu, Zhiguo Wang, Tinghao School of Computer and Information Security Guilin University of Electronic Technology Guangxi Guilin541004 China Key Laboratory of Image Graphics and Intelligent Processing in Guangxi Guilin University of Electronic Technology Guangxi Guilin541004 China

The production process of keycaps may result in surface character defects. The existing keycap character defect detection technology has low efficiency and accuracy, hindering the automation of keycap manufacturing. Addressing the challenge of extracting the entire keyboard from illuminated regions, this paper proposes a method using image feature points for template matching to extract the region of interest. Subsequently, leveraging prior knowledge, the paper addresses character segmentation and extraction on the keyboard. For character detection, the paper preprocesses images and classifies them by using an S-VGG network, yielding corresponding labels. © Published under licence by IOP Publishing Ltd.

关键词： Template matching

来源：评论

学校读者我要写书评

暂无评论

Hyper-Tuned Convolutional Neural Networks for Authorship Verification in Digital Forensic Investigations

引用

computers, Materials & Continua 2023年第8期76卷 1947-1976页

作者： Asif Rahim Yanru Zhong Tariq Ahmad Sadique Ahmad Mohammed A.ElAffendi School of Computer and Information Security Guilin University of Electronic TechnologyGuilin541004China Guangxi Key Laboratory of Intelligent Processing of Computer Images and Graphics Guilin University of Electronic TechnologyGuilin541004China School of Information and Communication Guilin University of Electronic TechnologyGuilin541004China EIAS:Data Science and Blockchain Laboratory College of Computer and Information SciencesPrince Sultan UniversityRiyadh11586Saudi Arabia

Authorship verification is a crucial task in digital forensic investigations,where it is often necessary to determine whether a specific individual wrote a particular piece of *** Neural Networks(CNNs)have shown promise in solving this problem,but their performance highly depends on the choice of *** this paper,we explore the effectiveness of hyperparameter tuning in improving the performance of CNNs for authorship *** conduct experiments using a Hyper Tuned CNN model with three popular optimization algorithms:Adaptive Moment Estimation(ADAM),StochasticGradientDescent(SGD),andRoot Mean Squared Propagation(RMSPROP).The model is trained and tested on a dataset of text samples collected from various authors,and the performance is evaluated using accuracy,precision,recall,and F1 *** compare the performance of the three optimization algorithms and demonstrate the effectiveness of hyperparameter tuning in improving the accuracy of the CNN *** results show that the Hyper Tuned CNN model with ADAM Optimizer achieves the highest accuracy of up to 90%.Furthermore,we demonstrate that hyperparameter tuning can help achieve significant performance improvements,even using a relatively simple model architecture like *** findings suggest that the choice of the optimization algorithm is a crucial factor in the performance of CNNs for authorship verification and that hyperparameter tuning can be an effective way to optimize this ***,this paper demonstrates the effectiveness of hyperparameter tuning in improving the performance of CNNs for authorship verification in digital forensic *** findings have important implications for developing accurate and reliable authorship verification systems,which are crucial for various applications in digital forensics,such as identifying the author of anonymous threatening messages or detecting cases of plagiarism.

关键词： Convolutional Neural Network(CNN) hyper-tuning authorship verification digital forensics

来源：评论

学校读者我要写书评

暂无评论

Research on active defense decision-making method for cloud boundary networks based on reinforcement learning of intelligent agent

引用

High-Confidence Computing 2024年第2期4卷 50-61页

作者： Huan Wang Yunlong Tang Yan Wang Ning Wei Junyi Deng Zhiyan Bin Weilong Li School of Computer Science and Technology Guangxi University of Science and TechnologyLiuzhou 545000China Liuzhou Key Laboratory of Big Data Intelligent Processing and Security Liuzhou 545000China Guangxi Education System Network Security Monitoring Center Liuzhou 545000China Center of Graphics and Information Guangxi ECO-Engineering Vocational&Technical CollegeLiuzhou 545004China

The cloud boundary network environment is characterized by a passive defense strategy,discrete defense actions,and delayed defense feedback in the face of network attacks,ignoring the influence of the external environment on defense decisions,thus resulting in poor defense ***,this paper proposes a cloud boundary network active defense model and decision method based on the reinforcement learning of intelligent agent,designs the network structure of the intelligent agent attack and defense game,and depicts the attack and defense game process of cloud boundary network;constructs the observation space and action space of reinforcement learning of intelligent agent in the non-complete information environment,and portrays the interaction process between intelligent agent and environment;establishes the reward mechanism based on the attack and defense gain,and encourage intelligent agents to learn more effective defense *** designed active defense decision intelligent agent based on deep reinforcement learning can solve the problems of border dynamics,interaction lag,and control dispersion in the defense decision process of cloud boundary networks,and improve the autonomy and continuity of defense decisions.

关键词： Active defense decision-making Cloud boundary network security intelligent agent reinforcement learning Offensive and defensive game

来源：评论

学校读者我要写书评

暂无评论

Real-Time 6-DoF Object Pose Estimation Network Based on 2D-3D Coordinate Correspondence 3rd

Real-Time 6-DoF Object Pose Estimation Network Based on 2D-3...

引用

3rd International Conference on Artificial Intelligence, Robotics, and Communication, ICAIRC 2023

作者： Li, Shuai Chen, Jinlong Yang, Minghao Su, Jianhua Guangxi Key Laboratory of Trusted Software Guilin University of Electronic Technology Guangxi Guilin541004 China Key Laboratory of Intelligent Processing of Computer Image and Graphics Guilin University of Electronic Technology Guangxi Guilin541004 China Beijing100190 China HuaiRou Beijing101400 China Beijing100190 China

ISBN: (纸本)9789819721993

Object 6D pose estimation is essential for a variety of applications, including autonomous driving, robotic manipulation, and automated harvesting. Due to the influence of different lighting conditions and occlusions, objects with different poses may exhibit significant variations in appearance in different views. This makes the estimation of the 6D pose of objects from a single RGB image a challenging task. This paper proposes a deep learning network capable of simultaneously detecting and estimating the 6D pose (3D rotation + 3D translation) of target objects. As establishing a large-scale dataset using real data is extremely challenging, this paper introduces an automatic collection scheme based on virtual data generated from real images. We conducted experiments on the generated astronaut dataset using our data collection scheme for 6D pose estimation. The experimental results show that the accuracy of 6D pose estimation based on the ADD metric is 96%. Therefore, this method has significant potential and can be extended to other downstream tasks. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Chinese Text Summarization Generation Based on Transformer and Temporal Convolutional Network 2

Chinese Text Summarization Generation Based on Transformer a...

引用

2nd International Conference on Electronic Information Technology, EIT 2023

作者： Huang, Wenming Zhou, Yaowei Xiao, Yannan Wen, Yayuan Deng, Zhenrong School of Computer and Information Security Guilin University of Electronic Technology Guangxi Guilin China Guangxi Key Laboratory of Image and Graphics Intelligent Processing Guangxi Guilin China College of Electronic Engineering Guangxi Normal University Guangxi Guilin China

ISBN: (数字)9781510666627

ISBN: (纸本)9781510666610

The recurrent neural network model based on attention mechanism has achieved good results in the text summarization generation task, but such models have problems such as insufficient parallelism and exposure bias. In order to solve the above problems, this paper proposes a two-stage Chinese text summarization generation method based on Transformer and temporal convolutional network. The first stage uses a summary generation model that fuses Transformer and a temporal convolutional network, and generates multiple candidate summaries through beam search at the decoding end. In the second stage, contrastive learning is introduced, and the candidate summaries are sorted and scored using the Roberta model to select the final summary. Through experiments on the Chinese short text summarization dataset LCSTS, ROUGE was used as the evaluation method to verify the effectiveness of the proposed method on Chinese text summarization. © 2023 SPIE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Power equipment fault entity recognition based on BERT-CRF model 5

Power equipment fault entity recognition based on BERT-CRF m...

引用

5th International Conference on Artificial Intelligence and computer Science, AICS 2023

作者： Zhang, Yanfang Zhong, Yanru Luo, Xiaonan Guangxi Key Laboratory of Intelligent Processing of Computer Images and Graphic Guilin University of Electronic Technology Guangxi Guilin541004 China National Local Joint Engineering Research Center of Satellite Navigation and Location Service Guilin University of Electronic Technology Guangxi Guilin541004 China

ISBN: (纸本)9781510668621

With the ongoing development of the national power grid, fault data from power equipment exhibits various characteristics, including a wide range of entity types, weak interrelationships, and high complexity. Consequently, traditional methods fail to extract adequate entity information and struggle with situations involving the multiple meanings of terminology in different contexts. To tackle these challenges, this paper proposes a method for recognizing power equipment fault entities based on the BERT-CRF model. The method initially employs web crawlers to retrieve literature related to power equipment faults. It then inductively designs five distinct types of power equipment fault entities and annotates a dataset accordingly. Subsequently, the BERT model is combined with the CRF model to recognize power equipment fault entities. The experimental results are then compared with those of the BiLSTM-CRF model and other domain datasets to evaluate the impact of power equipment fault entity types and label quantities. The experimental results confirm the feasibility and effectiveness of the BERT-CRF model, enabling the extraction of a wider range of power equipment fault entities from a smaller corpus of data. © 2023 SPIE.

关键词： Web crawler

来源：评论

学校读者我要写书评

暂无评论

Photovoltaic Array Fault Detection Based on Manifold Learning and Neural Network 5

Photovoltaic Array Fault Detection Based on Manifold Learnin...

引用

5th International Conference on computer Vision, Image and Deep Learning, CVIDL 2024

作者： Wang, Kai Zhong, Yanru Luo, Xiaonan Guilin University of Electronic Science and Technology Guangxi Key Laboratory of Intelligent Processing of Computer Images and Graphic Guilin China Guilin University of Electronic Science and Technology Satellite Navigation Positioning and Location Services National and Local Joint Engineering Research Center Guilin China

ISBN: (纸本)9798350373820

This paper endeavors to devise an ingenious methodology rooted in artificial intelligence, which, in turn, can be effectively employed to identify sundry categories of faults that are closely associated with photovoltaic arrays. This novel approach amalgamates the manifold learning algorithm with a formidable multilayer perceptron neural network (MLP). Intriguingly, it substantiates that the initial reduction in data dimensionality is achieved through the remarkable Isomap algorithm. Consequently, this compressed data is seamlessly channeled into the MLP, thereby yielding remarkable outcomes concerning fault detection. To validate and scrutinize the aforementioned proposition, a quintessential circuit representing a photovoltaic array is initially simulated utilizing the venerable Matlab/Simulink tool. During this simulation, an extensive corpus of both normal and faulty data is meticulously generated. Subsequently, the manifold learning algorithm is artfully applied to drastically diminish the dimensionality of this extensive dataset The resultant compressed data is then deftly fed into the MLP, allowing it to discern the salient characteristics pertaining to the sundry fault types. Through incessant iterations of intensive training, these faults can be astutely detected and discerned with remarkable accuracy. The results conclusively demonstrate the efficacy of combining manifold-based learning and multilayer perceptron neural network in detecting faults in photovoltaic arrays. The proposed method achieves high precision and effectiveness, surpassing the traditional approach by 2.52%. © 2024 IEEE.

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

DKD2L: Dual Knowledge Distillation Dynamic Learning for sketch-based 3D shape retrieval

DKD2L: Dual Knowledge Distillation Dynamic Learning for sket...

引用

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

作者： Yawen Su Jing Bai Gan Lin School of Computer Science and Engineering North Minzu University Yinchuan China The Key Laboratory of Images & Graphics Intelligent Processing of State Ethnic Affairs Commission

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Sketch-based 3D shape retrieval has become a prominent area of research in computer vision, confronting challenges related to the inherent diversity and abstraction of sketches, as well as inter-domain discrepancies. This paper introduces a novel approach called Dual Knowledge Distillation Dynamic Learning (DKD 2 L) aimed at enhancing the extraction of spatio-temporal features for sketch-based 3D shape retrieval. We develop a temporal feature extraction network to effectively capture the dynamic temporal characteristics of sketches and improve retrieval efficiency through temporal knowledge distillation. Additionally, to tackle intra-class variation and inter-class imbalance, we apply semantic knowledge distillation, enabling the 3D shape network to guide the sketch network in capturing common semantic information. This approach facilitates precise cross-modal alignment and enhances retrieval accuracy. Extensive experiments on two benchmark datasets demonstrate that DKD 2 L surpasses existing state-of-the-art methods.

关键词： Knowledge engineering computer vision Three-dimensional displays Shape Semantics Signal processing Benchmark testing Feature extraction Acoustics Speech processing

来源：评论

学校读者我要写书评

暂无评论

Research on Chinese Summary Generation Based on Pointer key Information 5

Research on Chinese Summary Generation Based on Pointer Key ...

引用

5th International Conference on computer Information Science and Application Technology, CISAT 2022

作者： Huang, Wenming Bu, Xianghui Xiao, Yannan Wen, Yayuan Deng, Zhenrong School of Computer and Information Security Guilin University of Electronic Technology Guangxi Guilin China Guangxi Key Laboratory of Image and Graphics Intelligent Processing Guangxi Guilin China College of Electronic Engineering Guangxi Normal University Guangxi Guilin China

ISBN: (纸本)9781510660076

Sequence-to-sequence models provide a feasible new approach for generative text summarization, but these models are not able to accurately reproduce factual details and subject information. To address the problem of unconstrained and uncontrollable content generation of generative text summarization models, this paper proposes a generative summarization method KGIT that uses Transformer as a skeleton and incorporates both BERT pre-training model and keyword information. The model uses a comprehensive keyword extraction algorithm, uses two results extracted by LSTM and TextRank as vocabularies respectively, and uses pointers keywords are selected and the extracted keywords are used as the guiding information to generate the summary based on the guiding information. KGIT model can associate the source text and keywords to avoid generating a summary of irrelevant topics. The ROUGE value is used as the evaluation criterion for text summaries, and the summaries generated by the KGIT model can contain more key information and are more accurate and readable when compared with the mainstream summary generation models on the NLPCC2017 Chinese news summary dataset. © 2022 SPIE.

关键词： Natural language processing systems

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：