检索结果-内蒙古大学图书馆

14th International Conference on computer Engineering and Networks, CENet 2024

作者： Chen, Keman Shi, Yuhe Yang, Houqun Huang, Jianqiang School of Computer Science and Technology Hainan University Haikou China Haikou Key Laboratory of Deep Learning and Big Data Application Technology Hainan University Hainan Haikou China China Telecom Co. Ltd. Hainan Branch Hainan Haikou China

ISBN: (纸本)9789819642281

The large model is a hot topic in the field of artificial intelligence, attracting more and more attention. This article mainly discusses the principles, advantages, and disadvantages of related technologies from the perspective of the development of LLM. In view of the rapid development of LLM, this article analyzes the problems faced by the current development of LLM and proposes corresponding mitigation measures. At the same time, for the future development of LLM, this article also puts forward the direction and possible development trends of the future research of large models. The purpose of this article is to provide reference for researchers in the field of artificial intelligence and to provide new ideas and suggestions for future research. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： artificial intelligence interpretability LLM Transformer

来源：评论

学校读者我要写书评

暂无评论

SQAT-LD: SPeech Quality Assessment Transformer Utilizing Listener Dependent Modeling for Zero-Shot Out-of-Domain MOS Prediction

SQAT-LD: SPeech Quality Assessment Transformer Utilizing Lis...

引用

IEEE Workshop on Automatic Speech Recognition and Understanding

作者： Kailai Shen Diqun Yan Li Dong Ying Ren Xiaoxun Wu Jing Hu Faculty of Electrical Engineering and Computer Science Ningbo University Zhejiang Key Laboratory of Mobile Network Application Technology

In this paper, we propose the speech quality assessment transformer utilizing listener dependent modeling (SQAT-LD) mean opinion score (MOS) prediction system, which was submitted to the 2023 VoiceMOS Challenge. The system is based on a combination of self-supervised learning (SSL) models and listener-dependent modeling. Due to this challenge’s emphasis on real-world and challenging zero-shot out-of-domain MOS prediction in three different voice evaluation scenarios, we specifically designed a two-branch module to predict scores and weights for each frame, aiming to achieve better generalization. In the challenge, our system achieved fourth place in Track 1a, second place in Track 1b and first place in Track 2. Additionally, we conducted an ablation study to investigate the effectiveness of our proposed method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Coupled Graph Convolution Network for Cross-Scene Multispectral Point Cloud Classification

Coupled Graph Convolution Network for Cross-Scene Multispect...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Mingye Wang Qingwang Wang Tao Shen Jian Song Kunming University of Science and Technology Kunming China Yunnan Key Laboratory of Computer Technologies Application Kunming China

Cross-scene multispectral point cloud classification aims to transfer knowledge of labeled source scenes to improve the discriminability of the model on the unlabeled target scenes. From a novel perspective, we argue that the information transfer between the source and target scenes can be used to solve cross-scene multispectral point cloud classification task. Specifically, we propose a Coupled Graph Convolutional Network (Coupled-GCN) to achieve joint alignment of node- and class-level structures within scenes by passing information between different scenes. To reduce the effect of spectral shift between the source and target scenes and seek scene-invariant intrinsic features, we propose a scene adaptive learning module by optimizing three different loss functions, namely, source classifier loss, domain classifier loss, and target classifier loss as a whole. In the cross-scene multispectral point cloud classification task, the proposed Coupled-GCN can alleviate the spectral shift problem compared to the traditional GCN and achieves an overall F_score of 65.04%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Leveraging Static Relationships for Intra-Type and Inter-Type Message Passing in Video Question Answering

arXiv

引用

arXiv 2025年

作者： Liang, Lili Sun, Guanglu School of Computer Science and Technology Harbin University of Science and Technology Harbin150080 China Heilongjiang Provincial Key Laboratory of Intelligent Information Processing and Application Harbin150080 China

Video Question Answering (VideoQA) is an important research direction in the field of artificial intelligence, enabling machines to understand video content and perform reasoning and answering based on natural language questions. Although methods based on static relationship reasoning have made certain progress, there are still deficiencies in the accuracy of static relationship recognition and representation, and they have not fully utilized the static relationship information in videos for in-depth reasoning and analysis. Therefore, this paper proposes a reasoning method for intra-type and inter-type message passing based on static relationships. This method constructs a dual graph for intra-type message passing reasoning and builds a heterogeneous graph based on static relationships for inter-type message passing reasoning. The intra-type message passing reasoning model captures the neighborhood information of targets and relationships related to the question in the dual graph, updating the dual graph to obtain intra-type clues for answering the question. The inter-type message passing reasoning model captures the neighborhood information of targets and relationships from different categories related to the question in the heterogeneous graph, updating the heterogeneous graph to obtain inter-type clues for answering the question. Finally, the answers are inferred by combining the intra-type and inter-type clues based on static relationships. Experimental results on the ANetQA and Next-QA datasets demonstrate the effectiveness of this method. © 2025, CC BY.

关键词： Question answering

来源：评论

学校读者我要写书评

暂无评论

Graph Neural Network with Multi-Kernel Learning for Multispectral Point Cloud Classification

Graph Neural Network with Multi-Kernel Learning for Multispe...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Zifeng Zhang Qingwang Wang Mingye Wang Tao Shen Kunming University of Science and Technology Kunming China Yunnan Key Laboratory of Computer Technologies Application Kunming China

Multispectral point clouds provide the data basis for finer land cover classification due to the simultaneous spatial and spectral information. How to jointly utilize spatial-spectral information becomes a hot research direction. Benefiting from the excellent performance of graph neural networks (GNNs) on non-Euclidean data, it is well suited to modelling multispectral point clouds to achieve higher classification accuracy. This paper proposes a novel graph convolutional networks with multi-kernel learning (GCN-MKL) for adaptively constructing a graph of multispectral point cloud for finer classification. Specifically, we use multiple base kernels to map the multispectral point cloud into a high-dimensional feature space and learn a linear combination of base kernels through a multi-kernel learning mechanism embedded in the network. The learned multi-kernel graph can effectively measure the high-dimensional similarity between multispectral points. Experimental results demonstrate that the proposed GCN-MKL outperforms several state-of-the-art methods on a real multispectral point cloud.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Communication Countermeasure Strategy Decision-Making Based on Incomplete Information Game

Communication Countermeasure Strategy Decision-Making Based ...

引用

International Conference on Advanced Communication technology (ICACT)

作者： Jinyue Liu Xiang Gao Haowei Yang Jihao Zhang Yuhan Liu Peng Gong National Key Laboratory of Mechatronic Engineering and Control School of Mechatronical Engineering Beijing Institute of Technology Beijing China Institute of Computer Application Technology Norinco Group Beijing China

ISBN: (数字)9791188428137

ISBN: (纸本)9798331507602

In modern battlefields, the stability of wireless communications is crucial for intelligence transmission, command coordination, and maintaining strategic advantage. However, with the rapid advancement of communication technologies, the electromagnetic environment has become increasingly complex, making intelligent decision-making in communication countermeasures a prominent research focus. However, most existing studies adopt deep learning and reinforcement learning methods, which require extensive data samples and computational resources. To address these limitations, this paper proposes a game-theoretic model for intelligent radio communication countermeasures under incomplete information. It quantitatively evaluates common attack and defense tactcis used in communication countermeasures and explores the mixed-strategy equilibrium of the game when both the attackers and defenders consist of multiple types. Furthermore, simulation-based comparative analyses are conducted to assess the factors influencing the utility of both the attacker and defender. The findings offer theoretical insights and decision-making support for the deployment of communication countermeasure strategies in practical military operations, contributing to significant strategic value.

关键词： Wireless communication Military communication Deep learning Decision making Games Reinforcement learning Communications technology Stability analysis Radio communication countermeasures Electromagnetics

来源：评论

学校读者我要写书评

暂无评论

A framework based on sparse representation model for time series prediction in smart city

引用

Frontiers of computer Science 2021年第1期15卷 99-111页

作者： Zhiyong YU Xiangping ZHENG Fangwan HUANG Wenzhong GUO Lin SUN Zhiwen YU College of Mathematics and Computer Science Fuzhou UniversityFuzhou 350108China Hangzhou Key Laboratory for IoT Technology&Application Zhejiang University City CollegeHangzhou 310015China School of Computer Science Northwestern Polytechnical UniversityXi’an 710072China

Smart city driven by Big Data and Internet of Things(loT)has become a most promising trend of the *** one important function of smart city,event alert based on time series prediction is faced with the challenge of how to extract and represent discriminative features of sensing knowledge from the massive sequential data generated by IoT *** this paper,a framework based on sparse representa-tion model(SRM)for time series prediction is proposed as an efficient approach to tackle this *** dividing the over-complete dictionary into upper and lower parts,the main idea of SRM is to obtain the sparse representation of time series based on the upper part firstly,and then realize the prediction of future values based on the lower *** choice of different dictionaries has a significant impact on the performance of *** paper focuses on the study of dictionary construction strategy and summarizes eight variants of *** results demonstrate that SRM can deal with different types of time series prediction flexibly and effectively.

关键词： sparse representation smart city time series prediction dictionary construction

来源：评论

学校读者我要写书评

暂无评论

GCFuzz: An Intelligent Method for Generating IoT Protocols Test Cases Using GAN with CVAE 7th

GCFuzz: An Intelligent Method for Generating IoT Protocols ...

引用

7th International Conference on Attacks and Defenses for Internet-of-Things, ADIoT 2024

作者： Zhong, Ming Zeng, Zisheng Guo, Yijia Zhao, Dandan Zhang, Bo Li, Shenghong Peng, Hao Ding, Zhiguo School of Computer Science and Technology Zhejiang Normal University Zhejiang Jinhua China Key Laboratory of Intelligent Educational Technology and Application in Zhejiang Normal University Jinhua321004 China School of Cyber Science and Engineering Shanghai Jiao Tong University Shanghai China School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai200240 China

ISBN: (纸本)9783031855924

The importance of Internet of Things (IoT) systems security cannot be ignored, particularly in the realm of communication. IoT protocols serve as standards for communication and interaction among devices in IoT environments. This paper enhances IoT security by identifying and exposing protocol vulnerabilities through fuzzing, a crucial method for discovering security flaws. Traditional generation-based fuzzers require reverse engineering to understand protocol grammar and generate test cases. In this paper, we propose an intelligent method called GCFuzz, which generates high-quality test cases without prior knowledge of the protocol. To understand different classes of protocol grammar, GCFuzz applies Generative Adversarial Networks (GAN) with Conditional Variational Autoencoders (CVAE) to train a generative model on various classes of protocol messages. After training, the model generates fake but credible messages. Additionally, to accurately cluster real protocol messages, we devise a novel clustering method based on a keyword. Results show that, compared to GANFuzz, Peach, BooFuzz, and Sulley, the test cases generated by GCFuzz have stronger targeting and less redundancy, while GCFuzz has higher accurate testing efficiency. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Catrack: Condition-Aware Multi-Object Tracking with Temporally Enhancedappearance Features

SSRN

引用

SSRN 2024年

作者： Cao, Jinli Wang, Yanchao Li, Run Zhang, Dawei Li, Minglu Zheng, Zhonglong School of Computer Science and Technology Zhejiang Normal University China State Key Laboratory of CAD&CG Zhejiang University China Key Laboratory of Intelligent Education Technology Application of Zhejiang Province China Department of Computer Science and Information Technology La Trobe University Australia

Multiple Object Tracking (MOT) is a critical task in computer vision with a wide range of practical applications. However, current methods often use a uniform approach for associating all targets, overlooking the varying conditions of each target. This can lead to performance degradation, especially in crowded scenes with dense targets. To address this issue, we propose a novel Condition-Aware Tracking method (CATrack) to differentiate the appearance feature flow for targets under different conditions. Specifically, we propose three designs for data association and feature update. First, we develop an Adaptive Appearance Association Module (AAAM) that selects suitable track templates based on detection conditions, reducing association errors in long-tail cases like occlusions or motion blur. Second, we design an ambiguous track filtering Selective Update strategy (SU) that filters out potential low-quality embeddings. Thus, the noise accumulation in the maintained track feature will also be reduced. Meanwhile, we propose a confidence-based Adaptive EMA (AEMA) method for the feature state transition. By adaptively adjusting the weights of track and detection embeddings, our AEMA better preserves high-quality target features. By integrating the above modules, CATrack enhances the discriminative capability of appearance features and improves the robustness of appearance-based associations. Extensive experiments on the MOT17 and MOT20 benchmarks validate the effectiveness of the proposed CATrack. Notably, the state-of-the-art results on MOT20 demonstrate the superiority of our method in highly crowded scenarios. © 2024, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

RailPC: A large-scale railway point cloud semantic segmentation dataset

引用

CAAI Transactions on Intelligence technology 2024年第6期9卷 1548-1560页

作者： Tengping Jiang Shiwei Li Qinyu Zhang Guangshuai Wang Zequn Zhang Fankun Zeng Peng An Xin Jin Shan Liu Yongjun Wang Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application Nanjing Normal UniversityNanjingChina Technology Innovation Center for Integrated Applications in Remote Sensing and Navigation Ministry of Natural ResourcesNanjingChina Eastern Institute of Technology(EIT) NingboChina Tianjin Key Laboratory of Rail Transit Navigation Positioning and Spatio-temporal Big Data Technology TianjinChina College of Computer Science and Engineering Northwest Normal UniversityLanzhouChina Mckelvey School of Engineering Washington University in St.LouisSt.LouisMissouriUSA School of Electronic and Information Engineering Ningbo University of TechnologyNingboChina

Semantic segmentation in the context of 3D point clouds for the railway environment holds a significant economic value,but its development is severely hindered by the lack of suitable and specific ***,the models trained on existing urban road point cloud datasets demonstrate poor generalisation on railway data due to a large domain gap caused by non-overlapping special/rare categories,for example,rail track,track bed *** harness the potential of supervised learning methods in the domain of 3D railway semantic segmentation,we introduce RailPC,a new point cloud *** provides a large-scale dataset with rich annotations for semantic segmentation in the railway ***,RailPC contains twice the number of annotated points compared to the largest available mobile laser scanning(MLS)point cloud dataset and is the first railway-specific 3D dataset for semantic *** covers a total of nearly 25 km railway in two different scenes(urban and mountain),with 3 billion points that are finely labelled as 16 most typical classes with respect to railway,and the data acquisition process is completed in China by MLS *** extensive experimentation,we evaluate the performance of advanced scene understanding methods on the annotated dataset and present a synthetic analysis of semantic segmentation *** on our findings,we establish some critical challenges towards railway-scale point cloud semantic *** dataset is available at https://***/NNU-GISA/GISA-RailPC,and we will continuously update it based on community feedback.

关键词： data benchmark MLS point clouds railway scene semantic segmentation

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：