检索结果-内蒙古大学图书馆

3rd International Conference on Electronic Information engineering, Big Data, and computer Technology, EIBDCT 2024

作者： Bao, Yuhan Wang, Xiaobin Wang, Tianlei Tan, Zhen Pu, Yanling Chen, Keyu School of Computer Science and Engineering Uestc Chengdu China

ISBN: (纸本)9781510680449

Semantic understanding of point clouds is a major task in 3D scenes. Due to the enormous number of points within point clouds, it is strait to process point clouds directly. Generally, previous work follow a sampler-extractor structure to get high-level semantic features. Previous sampling strategies in the sampler stuck in upholding local density while guaranteeing a predetermined number of sampled points. We propose a density-adaptive sampling strategy. In the extractor, PointNN introduces a non-parameter framework. However, it ignores the positional distance among points. We introduce a position-sensitive feature extraction module inspired by PointNN. We conduct comprehensive experiments to validate the effectiveness of our method. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Digital twin empowered lightweight and efficient blockchain for dynamic internet of vehicles

引用

Digital Communications and Networks 2024年第6期10卷 1698-1707页

作者： Haoye Chai Supeng Leng Jianhua He Ke Zhang School of Information and Communication Engineering University of Electronic Science and Technology of China(UESTC)Chengdu611731China Shenzhen Institute for Advanced Study UESTCShenzhen518000China School of Computer Science and Electronic Engineering University of EssexColchesterCO43SQUK

The Internet of Vehicles(Io V)has great potential for Intelligent Transportation Systems(ITS),enabling interactive vehicle applications,such as advanced driving and *** is crucial to ensure the reliability during the vehicle-to-vehicle interaction *** the emerging blockchain has superiority in handling security-related issues,existing blockchain-based schemes show weakness in highly dynamic Io *** the transaction broadcast and consensus process require multiple rounds of communication throughout the whole network,while the high relative speed between vehicles and dynamic topology resulting in the intermittent connections will degrade the efficiency of *** this paper,we propose a Digital Twin(DT)-enabled blockchain framework for dynamic Io V,which aims to reduce both the communication cost and the operational latency of *** address the dynamic context,we propose a DT construction strategy that jointly considers the DT migration and blockchain computing ***,a communication-efficient Local Perceptual Multi-Agent Deep Deterministic Policy Gradient(LPMA-DDPG)algorithm is designed to execute the DT construction strategy among edge servers in a decentralized *** simulation results show that the proposed framework can greatly reduce the communication cost,while achieving good security *** dynamic DT construction strategy shows superiority in operation latency compared with benchmark *** decentralized LPMA-DDPG algorithm is helpful for implementing the optimal DT construction strategy in practical ITS.

关键词： Digital twin Blockchain Internet of vehicles Multi-agent DDPG

来源：评论

学校读者我要写书评

暂无评论

Train Once, Deploy Anywhere: Edge-Guided Single-source Domain Generalization for Medical Image Segmentation 7

Train Once, Deploy Anywhere: Edge-Guided Single-source Domai...

引用

7th International Conference on Medical Imaging with Deep Learning, MIDL 2024

作者： Jiang, Jun Gu, Shi Shenzhen Institute for Advanced Study UESTC Shenzhen China School of Computer Science and Engineering UESTC Chengdu China

In medical image analysis, unsupervised domain adaptation models require retraining when receiving samples from a new data distribution, and multi-source domain generalization methods might be infeasible when there is only a single source domain. These will pose formidable obstacles to model deployment. To this end, we take the"Train Once, Deploy Anywhere" as our objective and consider a challenging but practical problem: Single-source Domain Generalization (SDG). Meanwhile, we note that (i) the medical image segmentation applications where generalization errors often come from imprecise predictions at the ambiguous boundary of anatomies and (ii) the edge of the image is domain-invariant, which can reduce the domain shift between the source and target domain in all network layers. Specifically, we borrow the prior knowledge from Digital Image Processing and take the edge of the image as input to enhance the model attention at the boundary of anatomies and improve the generalization performance on unknown target domains. Extensive experiments on three typical medical image segmentation datasets, which cover cross-sequence, cross-center, and cross-modality settings with various anatomical structures, demonstrate our method achieves superior generalization performance compared to the state-of-the-art SDG methods. The code is available at https://***/thinkdifferentor/EGSDG. © 2024 CC-BY 4.0, J.J. & S.G.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Enhanced Structural Information Over-sampling with Graph Neural Networks for Imbalanced Node Classification on Graphs 5

Enhanced Structural Information Over-sampling with Graph Neu...

引用

5th International Conference on Machine Learning, Big Data and Business Intelligence, MLBDBI 2023

作者： Tan, Zhen Li, Jie Bao, Yuhan Pu, Yanling Uestc School of Computer Science and Engineering Chengdu China

ISBN: (纸本)9798350359930

Graph neural networks play a crucial role in various fields of artificial intelligence, but graph structures themselves have the problem of imbalanced nodes. Currently, many oversampling methods have been proposed to address this problem. However, the combination of Graph Neural Networks(GNNs) and over-sampling methods still needs further exploration, for example, global information is always ignored. To address this issue, this paper proposes a novelty framework called Enhanced Structural Information Over-sampling (ESIO-GCN), which combines GNNs with enhanced global structural information and deep over-sampling. Over-sampling is carried out in the middle embedding layer of ESIO-GCN. In addition, this paper also explores different over-sampling strategies. We evaluate ESIO-GCN on several standard semi-supervised node classification datasets and achieved significant improvements on all datasets. © 2023 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Analyzing topics in social media for improving digital twinning based product development

引用

Digital Communications and Networks 2024年第2期10卷 273-281页

作者： Wenyi Tang Ling Tian Xu Zheng Ke Yan School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengdu611731China

Digital twinning enables manufacturers to create digital representations of physical entities,thus implementing virtual simulations for product *** efforts of digital twinning neglect the decisive consumer feedback in product development stages,failing to cover the gap between physical and digital *** work mines real-world consumer feedbacks through social media topics,which is significant to product *** specifically analyze the prevalent time of a product topic,giving an insight into both consumer attention and the widely-discussed time of a *** primary body of current studies regards the prevalent time prediction as an accompanying task or assumes the existence of a preset ***,these proposed solutions are either biased in focused objectives and underlying patterns or weak in the capability of generalization towards diverse *** this end,this work combines deep learning and survival analysis to predict the prevalent time of *** propose a specialized deep survival model which consists of two *** first module enriches input covariates by incorporating latent features of the time-varying text,and the second module fully captures the temporal pattern of a rumor by a recurrent network ***,a specific loss function different from regular survival models is proposed to achieve a more reasonable *** experiments on real-world datasets demonstrate that our model significantly outperforms the state-of-the-art methods.

关键词： Digital twinning Product development Topic analysis Social media

来源：评论

学校读者我要写书评

暂无评论

ALF: Adaptive Label Finetuning for Scene Graph Generation 21

ALF: Adaptive Label Finetuning for Scene Graph Generation

引用

21st International computer Conference on Wavelet Active Media Technology and Information Processing, ICCWAMTIP 2024

作者： Qisheng, Chen School of Computer Science and Engineering UESTC Center For Future Media Chengdu611730 China

ISBN: (纸本)9798331519254

Scene Graph Generation (SGG) is a task to identify relationships between subjects and objects in images. However, the task is significantly hindered by the long-tail distribution of relational labels, which often biases predictions toward generic or coarse categories. To resolve this, researchers have explored data transfer techniques that refine coarse-grained predicates into more detailed fine-grained labels. These approaches, however, face two key challenges: 1) the failure to account for the contextual constraints dictated by subject-object pairs, which can result in inaccurate label refinements, and 2) the reliance on additional retraining phases, which increases computational complexity. To address these issues, a novel plug-and-play one-stage data transfer framework, termed Adaptive Label Finetuning (ALF), has been proposed. ALF integrates two main modules: Adaptive Label Construction (ALC) and Adaptive Iterative Learning (AIL). Experiments demonstrate that ALF significantly outperforms conventional methods like Motif, achieving a 16% improvement in the mean Recall metrics. © 2024 IEEE.

关键词： Coarse-grained modeling

来源：评论

学校读者我要写书评

暂无评论

On large language models safety,security,and privacy:A survey

引用

Journal of Electronic science and Technology 2025年第1期23卷 1-21页

作者： Ran Zhang Hong-Wei Li Xin-Yuan Qian Wen-Bo Jiang Han-Xiao Chen School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengdu611731China

The integration of artificial intelligence(AI)technology,particularly large language models(LLMs),has become essential across various sectors due to their advanced language comprehension and generation *** their transformative impact in fields such as machine translation and intelligent dialogue systems,LLMs face significant *** challenges include safety,security,and privacy concerns that undermine their trustworthiness and effectiveness,such as hallucinations,backdoor attacks,and privacy *** works often conflated safety issues with security *** contrast,our study provides clearer and more reasonable definitions for safety,security,and privacy within the context of *** on these definitions,we provide a comprehensive overview of the vulnerabilities and defense mechanisms related to safety,security,and privacy in ***,we explore the unique research challenges posed by LLMs and suggest potential avenues for future research,aiming to enhance the robustness and reliability of LLMs in the face of emerging threats.

关键词： Large language models Privacy issues Safety issues Security issues

来源：评论

学校读者我要写书评

暂无评论

Seeing and Reasoning:A Simple Deep Learning Approach to Visual Question Answering

引用

Big Data Mining and Analytics 2025年第2期8卷 458-478页

作者： Rufai Yusuf Zakari Jim Wilson Owusu Ke Qin Tao He Guangchun Luo School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengdu 611731China

Visual Question Answering(VQA)is a complex task that requires a deep understanding of both visual content and natural language *** challenge lies in enabling models to recognize and interpret visual elements and to reason through questions in a multi-step,compositional *** propose a novel Transformer-based model that introduces specialized tokenization techniques to effectively capture intricate relationships between visual and textual *** model employs an enhanced self-attention mechanism,enabling it to attend to multiple modalities simultaneously,while a co-attention unit dynamically guides focus to the most relevant image regions and question ***,a multi-step reasoning module supports iterative inference,allowing the model to excel at complex reasoning *** experiments on benchmark datasets demonstrate the model’s superior performance,with accuracies of 98.6%on CLEVR,63.78%on GQA,and 68.67%on VQA *** studies confirm the critical contribution of key components,such as the reasoning module and co-attention mechanism,to the model’s *** analysis of the learned attention distributions further illustrates the model’s dynamic reasoning process,adapting to task ***,our study advances the adaptation of Transformer architectures for VQA,enhancing both reasoning capabilities and model interpretability in visual reasoning tasks.

关键词： machine learning deep learning Visual Question Answering(VQA) multi-step reasoning computer vision

来源：评论

学校读者我要写书评

暂无评论

A 3D System for Generating Z-Direction Multiple Microscopic Images Based on Deep Learning 6

A 3D System for Generating Z-Direction Multiple Microscopic ...

引用

6th IEEE International Conference on Power, Intelligent Computing and Systems, ICPICS 2024

作者： Wang, Yufei School of Optoelectronic Science and Engineering Uestc Chengdu China

ISBN: (纸本)9798350374315

With the development of artificial intelligence technology, people have begun to study methods based on deep learning to reconstruct the geometric morphology of three-dimensional objects. In the early stage of the project, we first discussed obtaining the height information of various points on the surface of the object through clustering evaluation algorithm, and then reconstructing the point cloud representation of the object. Based on deep learning methods, we completed the surface reconstruction of the object, but this method did not achieve the expected experimental results. This article proposes a method based on deep learning that combines multi focus image fusion and depth estimation. Firstly, a multi focus image fusion algorithm is used to preprocess the collected microscopic images to obtain a globally clear image. Then, depth estimation is performed on this clear image to obtain the height information of the object surface, and three-dimensional point cloud data is reconstructed. Finally, we also explored the three-dimensional reconstruction of cell microscopy images using transmissive lighting. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Exploring Potential Barrier Estimation Mechanism Based on Quantum Dynamics Framework

引用

Chinese Journal of Electronics 2025年第1期34卷 350-364页

作者： Quan Tang Peng Wang Chengdu Institution of Computer Application Chinese Academy of Science University of Chinese Academy of Sciences School of Computer Science and Engineering Southwest Minzu University

Due to the probability characteristics of quantum mechanism, the combination of quantum mechanism and intelligent algorithm has received wide attention. Quantum dynamics theory uses the Schr?dinger equation as a quantum dynamics equation. Through three approximation of the objective function, quantum dynamics framework(QDF) is obtained which describes basic iterative operations of optimization algorithms. Based on QDF, this paper proposes a potential barrier estimation(PBE) method which originates from quantum mechanism. With the proposed method, the particle can accept inferior solutions during the sampling process according to a probability which is subject to the quantum tunneling effect, to improve the global search capacity of optimization *** effectiveness of the proposed method in the ability of escaping local minima was thoroughly investigated through double well function(DWF), and experiments on two benchmark functions sets show that this method significantly improves the optimization performance of high dimensional complex functions. The PBE method is quantized and easily transplanted to other algorithms to achieve high performance in the future.

关键词： Potential energy Electric potential Shape Heuristic algorithms Estimation Tunneling Linear programming Approximation algorithms Iterative algorithms Optimization

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：