检索结果-内蒙古大学图书馆

7th IEEE International Conference on network Intelligence and Digital Content, IC-NIDC 2021

作者： Chu, Yi Li, Ruixiang Wang, Fang Ren, Junlong Qiao, Yuanyuan Yang, Jie Beijing Laboratory of Advanced Information Networks Beijing Key Laboratory of Network System Architecture and Convergence Beijing100876 China Aisino Corporation The Technology Research Institute Beijing100195 China

ISBN: (纸本)9781665405829

Edge computing is a new paradigm of distributed computing, in which computing offloading attracts wide attention from scholars. Existing work mainly focuses on single-server and single-user, and generally only optimizes energy consumption or execution time respectively. However, optimizing one may lead to the decline in another. In order to remedy this defect, we propose sequence elimination algorithm based on genetic algorithm. The algorithm can optimize energy consumption or execution time respectively in the scenario of multi-user and multi-server. The simulation results show that the sequence elimination algorithm can effectively reduce the energy consumption and execution time in the edge computing offloading problem. © 2021 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Image Segmentation Semantic Communication over Internet of Vehicles

arXiv

引用

arXiv 2022年

作者： Pan, Qiang Tong, Haonan Lv, Jie Luo, Tao Zhang, Zhilong Yin, Changchuan Li, Jianfeng Beijing Laboratory of Advanced Information Network Beijing Key Laboratory of Network System Architecture and Convergence Beijing University of Posts and Telecommunications Beijing100876 China

In this paper, the problem of semantic-based efficient image transmission is studied over the Internet of Vehicles (IoV). In the considered model, a vehicle shares massive amount of visual data perceived by its visual sensors to assist other vehicles in making driving decisions. However, it is hard to maintain a high reliable visual data transmission due to the limited spectrum resources. To tackle this problem, a semantic communication approach is introduced to reduce the transmission data amount while ensuring the semantic-level accuracy. Particularly, an image segmentation semantic communication (ISSC) system is proposed, which can extract the semantic features from the perceived images and transmit the features to the receiving vehicle that reconstructs the image segmentations. The ISSC system consists of an encoder and a decoder at the transmitter and the receiver, respectively. To accurately extract the image semantic features, the ISSC system encoder employs a Swin Transformer based multi-scale semantic feature extractor. Then, to resist the wireless noise and reconstruct the image segmentation, a semantic feature decoder and a reconstructor are designed at the receiver. Simulation results show that the proposed ISSC system can reconstruct the image segmentation accurately with a high compression ratio, and can achieve robust transmission performance against channel noise, especially at the low signal-to-noise ratio (SNR). In terms of mean Intersection over Union (mIoU), the ISSC system can achieve an increase by 75%, compared to the baselines using traditional coding methods. Copyright © 2022, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Adaptive Bitrate Video Semantic Communication over Wireless networks

Adaptive Bitrate Video Semantic Communication over Wireless ...

引用

International Conference on Wireless Communications and Signal Processing (WCSP)

作者： Wentao Gong Haonan Tong Sihua Wang Zhaohui Yang Xinxin He Changchuan Yin Beijing Key Laboratory of Network System Architecture and Convergence Beijing University of Posts and Telecommunications Beijing China College of Information Science and Electronic Engineering Zhejiang University Hangzhou China

This paper investigates the adaptive bitrate (ABR) video semantic communication over wireless networks. In the considered model, video sensing devices must transmit video semantic information to an edge server, to facilitate ubiquitous video sensing services such as road environment monitoring at the edge server in autonomous driving scenario. However, due to the varying wireless network conditions, it is challenging to guarantee both low transmission delay and high semantic accuracy at the same time if devices continuously transmit a fixed bitrate video semantic information. To address this challenge, we develop an adaptive bitrate video semantic communication (ABRVSC) system, in which devices adaptively adjust the bitrate of video semantic information according to network conditions. Specifically, we first define the quality of experience (QoE) for video semantic communication. Subsequently, a swin transformer-based semantic codec is proposed to extract semantic information with considering the influence of QoE. Then, we propose an Actor-Critic based ABR algorithm for the semantic codec to enhance the robustness of the proposed ABRVSC scheme against network variations. Simulation results demonstrate that at low bitrates, the mean intersection over union (MIoU) of the proposed ABRVSC scheme is nearly twice that of the traditional scheme. Moreover, the proposed ABRVSC scheme, which increases the QoE in video semantic communication by 36.57%, exhibits more robustness against network variations compared to both the fixed bitrate schemes and traditional ABR schemes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-View Visual Semantic Embedding for Cross-Modal Image-Text Retrieval

SSRN

引用

SSRN 2024年

作者： Li, Zheng Guo, Caili Wang, Xin Zhang, Hao Hu, Lin Beijing Key Laboratory of Network System Architecture and Convergence Beijing University of Posts and Telecommunications China Beijing Laboratory of Advanced Information Networks Beijing University of Posts and Telecommunications China China Telecom Digital Intelligence Technology Co. Ltd China

Visual Semantic Embedding (VSE) is a dominant method for cross-modal image-text retrieval. The purpose of VSE is to learn an embedding space where images can be embedded close to the corresponding captions. However, there are large intra-class variations in image-text data. Multiple captions describing the same image may be described from different views, and descriptions of different views are often dissimilar. The VSE method embeds samples from the same class in similar positions, which suppresses intra-class variations and leads to inferior generalization. This paper proposes a Multi-View Visual Semantic Embedding (MV-VSE) framework that learns multiple embeddings for an image, explicitly modeling intra-class variation. Our framework only needs to additionally train multiple visual feature aggregators to learn multi-view visual embeddings without changing the backbone network. To optimize the MV-VSE framework, a multi-view triplet loss is proposed, which jointly optimizes multi-view embeddings while retaining intra-class variation. Recently, large-scale Vision-Language Pre-training (VLP) has become a new paradigm for cross-modal image-text retrieval. To allow our framework to be flexibly applied to the traditional VSE models and VSE-based VLP models, we incorporate the contrastive loss commonly used in VLP and the triplet loss into a unified loss, and further propose a multi-view unified loss. Our framework can be applied plug-and-play to traditional VSE models and VSE-based VLP models without excessively increasing model complexity. Experimental results on the image-text retrieval benchmark datasets demonstrate that applying our framework can boost the retrieval performance of current VSE models. The code is available at https://***/AAA-Zheng/MV-VSE. © 2024, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Residual attention fusion network for single image super-resolution 2

Residual attention fusion network for single image super-res...

引用

2021 2nd International Conference on Signal Processing and Computer Science, SPCS 2021

作者： Zhang, Hao Lan, Chuwen Gao, Zehua School of Information and Communication Engineering Beijing Laboratory of Advanced Information Networks Beijing Key Laboratory of Network System Architecture and Convergence Beijing University of Posts and Telecommunications Beijing100876 China

Recently, a very deep convolutional neural network (CNN) demonstrated influential performance in the field of single image super-resolution (SISR). However, most of the CNN-based methods focus on designing deeper and wider network structures alone and do not use the hierarchical and global features in the input image. Therefore, we proposed a residual attention fusion network (RAFN), which is an improved residual fusion (RF) framework, to effectively extract hierarchical features for use in single-image super-resolution. The proposed framework comprises two residual fusion structures composed of several residual and fusion modules, and a continuous memory mechanism is realized by adding a long and short jump connection. The network focuses on learning more effective features. Furthermore, to maximize the power of the RF framework, we introduced global context attention (GCA) module that can model the global context and capture long-distance dependencies. The final RAFN was constructed by applying the proposed RF framework to the GCA blocks. Extensive experiments showed that the proposed network achieved improved performance in the SISR method with fewer parameters, as compared to the methods proposed in previous studies. © 2021 Institute of Physics Publishing. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Graph Semantics Based Neighboring Attentional Entity Alignment for Knowledge Graphs 17th

Graph Semantics Based Neighboring Attentional Entity Alignme...

引用

17th International Conference on Intelligent Computing, ICIC 2021

作者： Wang, Hanchen Li, Jianfeng Luo, Tao Beijing Laboratory of Advanced Information Networks and Beijing Key Laboratory of Network System Architecture and Convergence School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing100876 China

ISBN: (纸本)9783030845285

Entity alignment is the task of matching entities in different knowledge graphs if they refer to the same real-world identity. A promising method for entity alignment is to use embedding methods to learn knowledge graph representations and align entities by measuring their embedding distance. However, when dealing with the challenge of structural heterogeneity between knowledge graphs, most existing entity alignment methods ignored the potential evidence provided by entity and relation semantics. In this paper, an entity alignment framework that incorporates graph semantic information with neighboring attention is proposed. The framework leverages both entity and relation semantic information by introducing the attention mechanism into a graph convolutional network module. In particular, an attention mechanism about neighboring relation semantic information is developed in the proposed framework to learn entity representations as well as to ignore unimportant neighborhoods. The experimental results on the real-world dataset WK3L demonstrates that the proposed framework consistently outperforms other state-of-the-art models. © 2021, Springer Nature Switzerland AG.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Adaptive Bitrate Video Semantic Communication over Wireless networks

arXiv

引用

arXiv 2023年

作者： Gong, Wentao Tong, Haonan Wang, Sihua Yang, Zhaohui He, Xinxin Yin, Changchuan Beijing Key Laboratory of Network System Architecture and Convergence Beijing University of Posts and Telecommunications Beijing China College of Information Science and Electronic Engineering Zhejiang University Hangzhou China

关键词： Wireless networks

来源：评论

学校读者我要写书评

暂无评论

Time Error Bound of Deterministic Transmission in Cross-Domain Time-Sensitive networking

Time Error Bound of Deterministic Transmission in Cross-Doma...

引用

Asia Communications and Photonics Conference and Exhibition (ACP)

作者： Hao Ma Hongxing Li Li Chen Dong Zhao Xiaoyu Zhao Kai Xia Guochu Shou Beijing Key Laboratory of Network System Architecture and Convergence School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China Center of National Railway Intelligent Transportation System Engineering and Technology China Academy of Railway Sciences Corporation Limited Beijing China

Based on coupled network theory, a bounded time error model for network determinism is proposed. The limit of traffic scheduling performance affected by time synchronization error in cross-domain time-sensitive networ... 详细信息

ISBN: (数字)9798350379266

ISBN: (纸本)9798350379273

关键词： Asia Prototypes Logic gates Optical fiber communication Delays Planning Synchronization Time factors Photonics Business

来源：评论

学校读者我要写书评

暂无评论

Multicast SFC Embedding in Software-Defined SAGIN with Heterogeneous network Resources

Multicast SFC Embedding in Software-Defined SAGIN with Heter...

引用

IEEE Conference on Wireless Communications and networking

作者： Deyang Sun Hang Li Zixuan Kong Zhenghe Zhu Yawen Chen Zhaoming Lu Xiangming Wen Beijing Key Laboratory of Network System Architecture and Convergence Beijing China Beijing Laboratory of Advanced Information Networks Beijing China Beijing University of Posts and Telecommunications Beijing China Network and Information Technology Center Changchun Institute of Optics Fine Mechanics and Physics (CIOMP) Chinese Academy of Sciences Changchun China

ISBN: (数字)9798350303582

ISBN: (纸本)9798350303599

Space-Air-Ground Integrated network (SAGIN) is emerged as a promising paradigm to realize the vision of global coverage of sixth generation (6G) communication network. As an efficient communication pattern, multicast communication can be widespread among the ever increasing communication requests in the seamless access SAG IN. However, given the extensive network scale, time varying characteristic and heterogeneity of SAG IN, the coordination of heterogeneous networks brings challenges to resource allocation. With virtualization technologies, the physical resources within SAGIN can be virtualized as Virtual network Functions (VNFs) in virtual resource pool. To ensure that multicast services can be provided, the network deploys Multicast Service Function Chains (MSFCs) where the service flows is processed by VNFs in order during the transmission. In this paper, we study the problem of jointly optimizing VNF placement and multicast routing within SAG IN while considering that different network segments are equipped with different physical network resources and cost coefficients. We formulate it as an Integer Linear Programming (ILP) problem with the objective of maximizing network revenue while minimizing resource cost of computation and bandwidth. Since it is NP-hard, a low complexity heuristic algorithm is developed to find an efficient solution within polynomial time. Simulation results demonstrate the effectiveness of our proposed model and algorithm, and the deployment cost and blocking rate can be significantly reduced in SAGIN compared with independent terrestrial network.

关键词： Costs Multicast algorithms Service function chaining Simulation Heuristic algorithms Computational modeling Space-air-ground integrated networks

来源：评论

学校读者我要写书评

暂无评论

A Unified Framework of Data Augmentation Using Large Language Models for Text-Based Cross-Modal Retrieval

SSRN

引用

SSRN 2024年

作者： Si, Lijia Guo, Caili Li, Zheng Yang, Yang Beijing Key Laboratory of Network System Architecture and Convergence Beijing University of Posts and Telecommunications Beijing China Beijing Laboratory of Advanced Information Networks Beijing University of Posts and Telecommunications Beijing China China Telecom Digital Intelligence Technology Co. Ltd Beijing China

Text-based cross-modal retrieval (TCMR) is an information retrieval task that aims to find semantically equivalent content from other modalities given a textual ***, collecting well-labeled data for TCMR is very expensive and time-consuming, which highly affects the performance of ***, large language models (LLMs) have approached or even surpassed the human level on many natural language processing tasks, which inspires us to try to use LLM for data augmentation of TCMR ***, data augmentation using LLMs also faces significant challenges, particularly the hallucination problem of LLMs and the fusion of augmented data with the original *** this paper, we propose LLM-DA++, a unified framework for data augmentation using large language models that is applied to text-based cross-modal retrieval ***-DA++ includes the training and inference sub-frameworks, both leveraging LLMs to rewrite texts, enhancing vocabulary diversity and sentence structure while retaining key *** order to alleviate the hallucinations problem of LLMs, a Text Faithfulness Filter is introduced in LLM-DA++ to filter out unfaithful rewritten texts. In addition, a Balanced Sampling Strategy is introduced in LLM-DA++ to balance the contributions of original and augmented *** experiments on three cross-modal retrieval tasks, text-based audio retrieval, text-based person retrieval, and text-based motion retrieval, show that LLM-DA++ can significantly improve the retrieval performance of existing TCMR tasks, validating the effectiveness of LLM-DA++.The code is available at https://***/slj5/LLM-DA-plus-plus. © 2024, The Authors. All rights reserved.

关键词： Semantics

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：