检索结果-内蒙古大学图书馆

GTE: learning code AST representation efficiently and effectively

Science China(Information Sciences) 2025年第3期68卷 393-394页

作者： Yihao QIN Shangwen WANG Bo LIN Kang YANG Xiaoguang MAO College of Computer Science and Technology National University of Defense Technology Key Laboratory of Software Engineering for Complex Systems National University of Defense Technology

With the development of deep learning in recent years, code representation learning techniques have become the foundation of many software engineering tasks such as program classification [1] and defect detection. Earlier approaches treat the code as token sequences and use CNN, RNN, and the Transformer models to learn code representations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A comprehensive survey on graph neural network accelerators

引用

Frontiers of computer Science 2025年第2期19卷 11-29页

作者： Jingyu LIU Shi CHEN Li SHEN School of Computer National University of Defense TechnologyChangsha 410073China Key Laboratory of Advanced Microprocessor Chips and Systems Changsha 410073China

Deep learning has gained superior accuracy on Euclidean structure data in neural *** a result,nonEuclidean structure data,such as graph data,has more sophisticated structural information,which can be applied in neural networks as well to address more complex and practical ***,actual graph data obeys a power-law distribution,so the adjacent matrix of a graph is random and *** processing accelerator(GPA)is designed to handle the problems ***,graph computing only processes 1-dimensional *** graph neural networks(GNNs),graph data is ***,GNNs include the execution processes of both traditional graph processing and neural network,which have irregular memory access and regular computation,*** obtain more information in graph data and require better model generalization ability,the layers of GNN are deeper,so the overhead of memory access and computation is *** present,GNN accelerators are designed to deal with this *** this paper,we conduct a systematic survey regarding the design and implementation of GNN ***,we review the challenges faced by GNN accelerators,and existing related works in detail to process ***,we evaluate previous works and propose future directions in this booming field.

关键词： graph neural network accelerators graph convolutional networks design space exploration deep learning domain-specific architecture

来源：评论

学校读者我要写书评

暂无评论

FDCPNet:feature discrimination and context propagation network for 3D shape representation

引用

虚拟现实与智能硬件(中英文) 2025年第1期7卷 83-94页

作者： Weimin SHI Yuan XIONG Qianwen WANG Han JIANG Zhong ZHOU State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang UniversityBeijing 100191China

Background Three-dimensional(3D)shape representation using mesh data is essential in various applications,such as virtual reality and simulation *** methods for extracting features from mesh edges or faces struggle with complex 3D models because edge-based approaches miss global contexts and face-based methods overlook variations in adjacent areas,which affects the overall *** address these issues,we propose the Feature Discrimination and Context Propagation Network(FDCPNet),which is a novel approach that synergistically integrates local and global features in mesh *** FDCPNet is composed of two modules:(1)the Feature Discrimination Module,which employs an attention mechanism to enhance the identification of key local features,and(2)the Context Propagation Module,which enriches key local features by integrating global contextual information,thereby facilitating a more detailed and comprehensive representation of crucial areas within the mesh *** Experiments on popular datasets validated the effectiveness of FDCPNet,showing an improvement in the classification accuracy over the baseline ***,even with reduced mesh face numbers and limited training data,FDCPNet achieved promising results,demonstrating its robustness in scenarios of variable complexity.

关键词： 3D shape representation Mesh model MeshNet Feature discrimination Context propagation

来源：评论

学校读者我要写书评

暂无评论

Can i Get There? Negotiated User-to-User Teleportations in Social VR

引用

IEEE Transactions on Visualization and computer Graphics 2025年第5期31卷 2320-2330页

作者： Wang, Miao Shu, Wen-Tong Li, Yi-Jun Li, Wanwan School of Computer Science and Engineering State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing100191 China Zhongguancun Laboratory Beijing100094 China Tsinghua University Department of Computer Science and Technology Beijing100084 China Tandy School of Computer Science University of Tulsa Tulsa United States

The growing adoption of social virtual reality (VR) platforms underscores the importance of safeguarding personal VR space to maintain user privacy and security. Teleportation, a prevalent instantaneous locomotion method in VR, facilitates user engagement but can also inadvertently intrude upon personal VR space, thereby raising privacy concerns. This paper introduces three innovative negotiated teleportation techniques designed to secure user-to-user teleportation and protect personal space privacy, all under a unified small-group development framework. We have designed and evaluated three types of negotiated teleportation techniques: Sector technique for directional control, Distance technique for minimum social distance control, and Area technique for defining circular permissible teleportation areas. These techniques foster a collaborative approach to selecting teleportation points that respect personal space. To evaluate the efficacy of these techniques, we conducted a user study with 20 participants who performed social tasks within a virtual campus environment. The findings demonstrate that our techniques significantly enhance privacy protection and alleviate anxiety associated with unwanted proximity in social VR. © 1995-2012 IEEE.

关键词： Virtual environments

来源：评论

学校读者我要写书评

暂无评论

Listen With Seeing: Cross-Modal Contrastive Learning for Audio-Visual Event Localization

引用

IEEE Transactions on Multimedia 2025年 27卷 2650-2665页

作者： Sun, Chao Chen, Min Zhu, Chuanbo Zhang, Sheng Lu, Ping Chen, Jincai Huazhong University of Science and Technology Wuhan National Laboratory for Optoelectronics Key Laboratory of Information Storage System Engineering Research Center of Data Storage Systems and Technology Ministry of Education of China School of Computer Science and Technology Wuhan430074 China South China University of Technology School of Computer Science and Engineering Guangzhou510640 China Pazhou Laboratory Guangzhou510640 China

In real-world physiological and psychological scenarios, there often exists a robust complementary correlation between audio and visual signals. Audio-Visual Event Localization (AVEL) aims to identify segments with Audio-Visual Events (AVEs) that contain both audio and visual tracks in unconstrained videos. Prior studies have predominantly focused on audio-visual cross-modal fusion methods, overlooking the fine-grained exploration of the cross-modal information fusion mechanism. Moreover, due to the inherent heterogeneity of multi-modal data, inevitable new noise is introduced during the audio-visual fusion process. To address these challenges, we propose a novel Cross-modal Contrastive Learning Network (CCLN) for AVEL, comprising a backbone network and a branch network. In the backbone network, drawing inspiration from physiological theories of sensory integration, we elucidate the process of audio-visual information fusion, interaction, and integration from an information-flow perspective. Notably, the Self-constrained Bi-modal Interaction (SBI) module is a bi-modal attention structure integrated with audio-visual fusion information, and through gated processing of the audio-visual correlation matrix, it effectively captures inter-modal correlation. The Foreground Event Enhancement (FEE) module emphasizes the significance of event-level boundaries by elongating the distance between scene events during training through adaptive weights. Furthermore, we introduce weak video-level labels to constrain the cross-modal semantic alignment of audio-visual events and design a weakly supervised cross-modal contrastive learning loss (WCCL Loss) function, which enhances the quality of fusion representation in the dual-branch contrastive learning framework. Extensive experiments conducted on the AVE dataset for both fully supervised and weakly supervised event localization, as well as Cross-Modal Localization (CML) tasks, demonstrate the superior performance of our model compa

关键词： Information fusion

来源：评论

学校读者我要写书评

暂无评论

Knowledge As Not Only Justified True Beliefs in Vision

引用

IEEE/CAA Journal of Automatica Sinica 2025年第2期12卷 297-299页

作者： Wenbo Zheng Fei-Yue Wang IEEE School of Computer Science and Artificial Intelligence Wuhan University of Technology Sanya Science and Education Innovation Park of Wuhan University of Technology the State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences

COMPUTATIONAL knowledge vision [1] is emphasized as a novel perspective or field in this paper. It first proposes the visual hierarchy and its connection to knowledge, stating that knowledge is a justified true belief. To further the previous research, we concisely summarize our recent works and suggest a new direction that knowledge is also a thought framework in vision.

关键词： Computational modeling Visualization Artificial intelligence Data models Visual perception Visual databases Training data

来源：评论

学校读者我要写书评

暂无评论

CNN-Based Multi-Output and Multi-Task Regression for Supershape Reconstruction from 3D Point Clouds

Informatica (Slovenia)

引用

Informatica (Slovenia) 2025年第5期49卷 37-48页

作者： Remmach, Hassnae Razak, Siti Fatimah Abdul Ullah, Arif Yogarayan, Sumendra Sayeed, Md Shohel Mrhari, Amine Computer Systems Engineering Laboratory Cadi Ayyad University Marrakesh40000 Morocco Faculty of Information Science and Technology Multimedia University Ayer Keroh75450 Malaysia Research in Computer Science Laboratory Faculty of Sciences Ibn Tofail University Kenitra Morocco

In a number of industries, including computer graphics, robotics, and medical imaging, three-dimensional reconstruction is essential. In this research, a CNN-based Multi-output and Multi-Task Regressor with deep learning capabilities is proposed for three-dimensional object reconstruction from 3D point cloud. Our approach is grounded in the original Point Net architecture, which addresses the difficulties associated with convolution when applied to point clouds. Firstly, this paper is modified using a Multi-Output Regressor to accurately recreate Super forms from 3D point clouds. Using this method, we first extract features from the 3D point cloud using Point Net. After that, a Multi-Output Regressor receives these data and uses them to anticipate the Super shape parameters needed to reconstruct the shape. Taking in the data, the Multi-Output Regressor retrieved characteristics from Point Net and simultaneously predicts several outcomes. Second, a Multi-Task Regressor is used to modify the Point Net. The network gains from the capacity to transfer knowledge from one task to another, improving the model's overall performance. The model would forecast the ten parameters needed to create the shape in the case of rebuilding Super shapes. The test findings were better than expected;they are intriguing in terms of prediction accuracy and cost, and they update the result by 80%, which is a good accomplishment for the study. © 2025 Slovene Society Informatika. All rights reserved.

关键词： 3D reconstruction

来源：评论

学校读者我要写书评

暂无评论

A sentiment analysis of the Ukraine-Russia War tweets using knowledge graph convolutional networks

引用

International Journal of Information technology (Singapore) 2025年 1-18页

作者： Menaouer, Brahami Fairouz, Safa Meriem, Mohammed Boulekbachi Mohammed, Sabri Nada, Matta LABAB Laboratory Computer Systems Engineering Department National Polytechnic School of Oran Oran Algeria Computer Systems Engineering Department National Polytechnic School of Oran Oran Algeria TechCICO Laboratory University of Technology of Troyes Troyes France

Nowadays, social networks play a critical role in online social discourse, particularly during major events such as elections, health crises, and wars. Furthermore, individuals have spent significant time on social networks that consume news and express their opinions and viewpoints on various topics, namely, the Russia-Ukraine War. The Ukraine-Russia War is one of the most complicated and unfortunate events of this decade, with many aspects to be considered to have an informed opinion. For this reason, sentiment analysis research can be useful in analyzing sentiments or opinions about the Ukraine-Russia war, such as Twitter (X) posts. In this study, we propose a new deep learning-based sentiment classification model called "Knowledge Graph Convolutional Networks" that predicts and analyzes sentiments concerning the Russia-Ukraine war. There were 500,000 tweets collected in total, however only 410,428 were left for sentiment analysis after cleaning, lemmatization stemming, and deleting duplicate tweets. Results show that "war", "people", "world", "putin", "energy", "gas", "weapon", and "peace" were some of the most frequently occurring words in the tweets. The main aim of this work is to develop a robust system that provides an understanding of public sentiment towards the Russia-Ukraine war on the X platform. Experimental results demonstrate that it is possible to obtain more accurate sentiment classification results by the proposed method. They also have managerial, economic, and research implications. © Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： Classification Decision support systems Graph Convolutional Networks (GCN) Knowledge graph Knowledge management Opinion mining Twitter sentiment analysis Ukraine-Russia War

来源：评论

学校读者我要写书评

暂无评论

Improve GMRACCF Qualifications via Collaborative Filtering in Vehicle Sales Chain

引用

Tsinghua Science and technology 2025年第1期30卷 247-261页

作者： Beiteng Yang Haibin Zhu Dongning Liu School of Computer Science and Technology Guangdong University of TechnologyGuangzhou 510000China Collaborative Systems Laboratory Nipissing UniversityNorth BayP1B 8L7Canada

The Vehicle Allocation Problem(VAP)in the vehicle sales chain has three bottlenecks in *** first is to collect relevant cooperation or conflict information,the second is to accurately quantify and analyze other factors affecting the distribution of cars,and the third is to establish a stable and rapid response to the vehicle allocation management *** order to improve the real-time performance and reliability of vehicle allocation in the vehicle sales chain,it is crucial to find a method that can respond quickly and stabilize the vehicle allocation ***,this paper addresses these issues by extending Group Multi-Role Assignment with Cooperation and Conflict Factors(GMRACCF)from a new *** the logical reasoning of closure computation,the KD45 logic algorithm is used to find the implicit cognitive Cooperation and Conflict Factors(CCF).Therefore,a collaborative filtering comprehensive evaluation method is proposed to help administrators determine the influence weight of CCFs and Cooperation Scales(CSs)on the all-round performance according to their *** on collaborative filtering,semantic modification is applied to resolve conflicts among ***-scale simulation results show that the proposed method is feasible and robust,and provides a reliable decision-making reference in the vehicle sales chain.

关键词： Vehicle Allocation Problem(VAP) Group Multi-Role Assignment with Cooperation and Conflict Factors(GMRACCF) KD45 logic algorithm collaborative filtering semantic modification Cooperation and Conflict Factors(CCFs) Cooperation Scale(CS)

来源：评论

学校读者我要写书评

暂无评论

Broadband single-polarization single-mode low confinement loss hollow core anti-resonant fiber with semi-elliptical nested tube

引用

Optical and Quantum Electronics 2025年第4期57卷 1-12页

作者： Lin, Wen Fei, Yihong Wang, Ning Jia, Hongzhi Engineering Research Center of Optical Instruments and Systems Ministry of Education Shanghai Key Laboratory of Modern Optical Systems School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai200093 China

In this paper, a hollow-core anti-resonant optical fibre containing a semi-elliptical nested tube is proposed, which has the characteristics of single-polarization, large bandwidth, single-mode and low confinement loss. By optimizing the structural design, the polarization extinction ratio (PER) of the fiber reaches 21,0183 at a wavelength of 1.55 μm, and the y-polarized fundamental mode loss is only 0.00086 dB/m. By changing the material and thickness of the semi-ellipsoidal nested tube, a large bandwidth of 280 nm was achieved in the wavelength range of 1.51-1.78 μm, with loss limited to less than 0.001 dB/m within the bandwidth range. The PER and higher-order mode extinction ratio of 4870, 1487, respectively. The loss remains below 0.01 dB/m when the bending radius exceeds 4.5 cm. Therefore, it is expected that this optical fiber can be used in optical devices such as fiber optic sensors, fiber optic lasers and fiber optic gyroscopes. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Single mode fibers

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：