检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Sun, Qizheng Guo, Caili Yang, Yang Chen, Jiujiu Xue, Xijun Beijing Laboratory of Advanced Information Networks Beijing University of Posts and Telecommunications Beijing100876 China Beijing Key Laboratory of Network System Architecture and Convergence Beijing University of Posts and Telecommunications Beijing100876 China

Conventional image compression methods typically aim at pixel-level consistency while ignoring the performance of downstream AI tasks. To solve this problem, this paper proposes a Semantic-Assisted Image Compression method (SAIC), which can maintain semantic-level consistency to enable high performance of downstream AI tasks. To this end, we train the compression network using semantic-level loss function. In particular, semantic-level loss is measured using gradient-based semantic weights mechanism (GSW). GSW directly consider downstream AI tasks' perceptual results. Then, this paper proposes a semantic-level distortion evaluation metric to quantify the amount of semantic information retained during the compression process. Experimental results show that the proposed SAIC method can retain more semantic-level information and achieve better performance of downstream AI tasks compared to the traditional deep learning-based method and the advanced perceptual method at the same compression ratio. © 2022, CC BY.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

An Effective Routing Mechanism Based on Fuzzy Logic for Software-Defined Data Center networks 6

An Effective Routing Mechanism Based on Fuzzy Logic for Soft...

引用

6th IEEE International Conference on Computer and Communications, ICCC 2020

作者： Xu, Yang Muqing, Wu Guohao, Yao Beijing Laboratory of Advanced Information Networks Beijing Key Laboratory of Network System Architecture and Convergence Beijing University of Posts and Telecommunications Beijing China

ISBN: (纸本)9781728186351

In order to solve the problem of low throughput and poor performance in data center network, this paper proposes a traffic scheduling algorithm exploiting fuzzy logic inference based on Software Defined Networking (SDN). The algorithm uses the characteristics of separation of control and forwarding in SDN architecture to choose paths for data flows by the centralized control of controller. It calculates the candidate path set of accessible paths between the source host and the destination host, then comprehensively considers path hops and bandwidth utilization, evaluates the candidate path using fuzzy logic model, and selects the optimal path. The experimental results show that compared with ECMP, Hedera and FSEM, the proposed algorithm improves the network throughput and load balancing, thus improving the overall network performance of the data center. © 2020 IEEE.

关键词： Fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

MultiModal, Robust and Accurate Hand Tracking 6

MultiModal, Robust and Accurate Hand Tracking

引用

6th IEEE International Conference on Computer and Communications, ICCC 2020

作者： Zhang, Tianyang Xia, Hailun Zhang, Changjian Zeng, Zhimin Beijing Key Laboratory of Networks System Architecture and Convergence Beijing Laboratory of Advanced Information Networks School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing100876 China

ISBN: (纸本)9781728186351

3D hand tracking has a wide application prospect, for instance, in the field of human-computer interaction. Existing generative methods based on model fitting typically obtain good accuracy, but are far less robust to rapid hand motions and gestures with self-occlusions. We thus present a multimodal hand tracking system aiming to boost both accuracy and robustness. An efficient initialization strategy based on image data and inertial sensor data is designed to improve the robustness. A new optimization algorithm is proposed to improve the accuracy further by introducing gradient descent into APSO (Adaptive Particle Swarm Optimization). In addition, we construct a cylinder-cuboid hand model and establish a corresponding cost function. The proposed hand tracking method is evaluated on MSRA14 Dataset and achieves the state-of-the-art result. © 2020 IEEE.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Multi-scale Recalibration with Advanced Geometry Constraints for 3D Human Pose Estimation 6

Multi-scale Recalibration with Advanced Geometry Constraints...

引用

6th IEEE International Conference on Computer and Communications, ICCC 2020

作者： Xiao, Meng Xia, Hailun Xie, Ziwei Feng, Chunyan Beijing Key Laboratory of Networks System Architecture and Convergence Beijing Laboratory of Advanced Information Networks School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing100876 China

ISBN: (纸本)9781728186351

Estimating 3D human poses from a single RGB image is a challenging task in computer vision due to depth ambiguity and lack of unconstrained 3D datasets. Poor exploiting of image cues will lead to inaccurate pose predictions. Previous works try to constrain illegal spatial relations and exploit 2D annotations of in-the-wild images as weak labels. In this paper, we propose to use multi-scale recalibration with stronger geometry constraints to regress 3D pose. The overall network is end-to-end which consists of a 2D pose estimation sub-network and a depth regression subnetwork. Firstly, by adding the residual multi-scale recalibration module to the depth regression sub-network, our approach works better on exploiting the structural information of human poses. Secondly, the advanced geometry constraints are introduced to restrict the human pose from the bone length and joint angle orientation, which shows a better result. Experimental results on the Human3.6m and in-the-wild MPII datasets show the effectiveness and robustness of our method. © 2020 IEEE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

EM-Mamba: An Edge-Mix Enhanced Long-Range Sequential Modeling Mamba for Kidney Segmentation in CT Scans

EM-Mamba: An Edge-Mix Enhanced Long-Range Sequential Modelin...

引用

Smart World Congress (SWC), IEEE

作者： Shaowei Feng Zheng Li Mengmeng Zheng Yang Yang Xin Wang Caili Guo Beijing Laboratory of Advanced Information Networks Beijing University of Posts and Telecommunications Beijing China China Telecom Digital Intelligence Technology Co. Ltd Beijing China Department of Urology Beijing Friendship hospital Capital Medical University Beijing China Beijing Key Laboratory of Network System Architecture and Convergence Beijing University of Posts and Telecommunications Beijing China

ISBN: (数字)9798331520861

ISBN: (纸本)9798331520878

Manual delineation of the kidney region in CT scans is a laborious process. Although existing models have achieved remarkable success in the realm of automated segmentation, they still encounter challenges in effectively modeling both the global and local information. To address this, we introduce Edge-Mix enhanced Mamba (EM-Mamba) for kidney segmentation, which is designed to capture global and local information from multi-scales. EM-Mamba leverages SegMamba as its backbone, utilizing Mamba’s efficiency in extracting long-range dependencies. To further enhance the model’s integration of local and global information, we introduce the Edge-Mix module, which captures edge information from the shallow layers of the network during the encoding phase and merges it with multi-scale features during the decoding phase. Additionally, a Multi-Scale Convolution (MSC) module is designed to enhance the capability of extracting effective information from 3D medical images, achieving a fusion of rich local and global information across multiple scales. The innovation of the EM-Mamba model lies in its integration of detailed and global information, as well as its robust feature extraction ability in 3D medical image analysis, offering a new solution for precise kidney segmentation. The experimental results show that our framework achieving a Dice score of $\mathbf{9 1 . 9 5}$ % on the KiTS21 dataset and 86.35 % Dice score on our proprietary dataset called Kidney Parenchyma Segmentation (KPS).

关键词： Measurement Image segmentation Solid modeling Technological innovation Three-dimensional displays Image edge detection Computed tomography Feature extraction Kidney Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Graph Optimization Based Localization Algorithm by Fusing VLP and VO

Graph Optimization Based Localization Algorithm by Fusing VL...

引用

International Conference on Wireless Communications and Signal Processing (WCSP)

作者： Minan Guo Bowen Jia Chunyan Feng Zhiyu Zhu Yang Yang Beijing Key Laboratory of Network System Architecture and Convergence School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China China Electronics Standardization Institute Beijing China Beijing Laboratory of Advanced Information Networks School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China

Visible light positioning (VLP) has attracted considerable interest due to its high accuracy and low cost. However, VLP typically requires several light emitting diodes (LEDs) for positioning, which may lead to positioning failure in sparse LED layout or parts of the links are blocked. To address this challenge, we propose a novel graph optimization-based localization algorithm by fusing VLP and visual odometry (VO), termed GO-VLO. In the considered model, a few LEDs are deployed on the ceiling and broadcast positioning information, while a receiver equipped with a camera conducts GO-VLO to achieve precise positioning with limited LEDs. GO-VLO consists of a front end to process positioning information and a back end to further optimize the positioning results. In particular, VLP and VO are first used separately at the front end, thus obtaining two respective positioning results. Then, a visible-light visual odometry fusion mechanism is proposed to fuse the positioning results of VLP and VO preliminarily. To strengthen the constraints between frames and prevent location failure when VLP is unavailable, a novel graph optimization framework is further proposed in the back end, which notably takes the covisible feature points of two successive frames into consideration. Experimental results show that our proposed method attains a positioning accuracy of 4.93 cm in two dimension and 6.20 cm in three dimension under dense LED layout.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cluster-Based Interference-Free MAC Protocol with Load Aware in Software Defined VANET

引用

China Communications 2020年第12期17卷 217-234页

作者： Yangshui Gao Tao Luo Xinxin He Zhilong Zhang Beijing Laboratory of Advanced Information Networks Beijing University of Posts and TelecommunicationsBeijing 100876China Beijing Key Laboratory of Network System Architecture and Convergence Beijing University of Posts and TelecommunicationsBeijing 100876China School of Mathematics and Computer Dali UniversityDali 671003China

In order to reduce the interference,a novel,cluster-based medium access control(MAC)protocol with load aware for VANETs is proposed in this ***,all vehicles on roads are grouped into stable clusters in the light of their direction,number of neighbors,link reliability,and traffic *** utilizing the advantages of centralized control in software defined VANETs(SDVN),cluster stability can be maintained in ***,a contention-free MAC mechanism composed of inter-cluster multi-channel allocation and intra-cluster dynamic TDMA frame allocation is proposed to prevent co-channel interference and hidden terminal *** results show that the proposed protocol outperforms some existing protocols in cluster stability,delivery ratio,throughput and delay performance.

关键词： SDVN MAC co-channel interference non-safety services cluster

来源：评论

学校读者我要写书评

暂无评论

Accurate Positioning with Single Vision Beacon: A Spatial Geometry Based Algorithm

Accurate Positioning with Single Vision Beacon: A Spatial Ge...

引用

International Conference on Wireless Communications and Signal Processing (WCSP)

作者： Boyu Yang Yang Yang Caili Guo Zhiyu Zhu Xuefei Wang Beijing Key Laboratory of Network System Architecture and Convergence School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China Beijing Laboratory of Advanced Information Networks School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China China Spacesat Co. Ltd Beijing China

This paper proposes a visual positioning algorithm based on feature points and triangular structures on a quick response code (V-FTQ), which can achieve precise position and orientation estimation using only a monocular camera and a single quick response (QR) code beacon. In the considered system, a few QR codes are placed on the ceiling, and a user holds a camera in hand to capture one QR code for positioning. In particular, we first propose an efficient matching mechanism to match the feature points of the captured QR beacon to their projections in the image plane of the camera. Then, based on the geometry relations between the feature points and their projections, V-FTQ is able to calculate the coordinates of the feature points in the camera coordinate. Next, the pose and position of the user are estimated based on linear algebra and spatial geometry. Finally, a singular solution elimination scheme is further proposed to effectively eliminate incorrect solutions estimated by V-FTQ, remaining correct pose and position. The simulation results demonstrate that V-FTQ outperforms similar algorithms in terms of precision and robustness to noise.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Large Scale Model Enabled Semantic Communications Based on Robust Knowledge Distillation

Large Scale Model Enabled Semantic Communications Based on R...

引用

IEEE Conference on Global Communications (GLOBECOM)

作者： Kuiyuan Ding Fangfang Liu Yang Yang Mingzhe Chen Caili Guo Beijing Key Laboratory of Network System Architecture and Convergence School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China Department of Electrical and Computer Engineering and the Institute for Data Science and Computing University of Miami Coral Gables FL USA Beijing Laboratory of Advanced Information Networks School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China

ISBN: (数字)9798350351255

ISBN: (纸本)9798350351262

Large scale artificial intelligence (AI) models possess excellent capabilities in semantic representation and understanding, making them particularly well-suited for semantic encoding and decoding. However, the substantial scale of these AI models imposes unacceptable computational resources and communication delays. To address this issue, we propose a semantic communication scheme based on robust knowledge distillation (RKD-SC) for large scale model enabled semantic communications. In the considered system, a transmitter extracts the features of the source image for robust transmission and accurate image classification at the receiver. To effectively utilize the superior capability of large scale model while make the cost affordable, we first transfer knowledge from a large scale model to a smaller scale model to serve as the semantic encoder. Then, to enhance the robustness of the system against channel noise, we propose a channel-aware autoencoder (CAA) based on the Transformer architecture. Experimental results show that the encoder of proposed RKD-SC system can achieve over 93.3% of the performance of a large scale model while compressing 96.67% number of parameters. Code: https://***/echojayne/RKD-SC.

关键词： Transmitters Computational modeling Noise Autoencoders Receivers Semantic communication Transformers Feature extraction Robustness Decoding

来源：评论

学校读者我要写书评

暂无评论

FC-BET: A Fast Consecutive Beam Tracking Scheme for MmWave Vehicular Communications

FC-BET: A Fast Consecutive Beam Tracking Scheme for MmWave V...

引用

IEEE Conference on Wireless Communications and Networking

作者： Chen Wang Yawen Chen Zhaoming Lu Xiangming Wen Zifan Wang Luhan Wang Beijing Key Laboratory of Network System Architecture and Convergence Beijing Laboratory of Advanced Information Networks Beijing University of Posts and Telecommunications Beijing China

ISBN: (纸本)9781728195056;9781728195063

Millimeter wave (mmWave) communication is a promising technique to meet the demands of data-rate hungry applications in vehicular networks. Multiple-input multiple-output (MIMO) and beamforming technique are usually adopted in mmWave communications to overcome the high path and penetration losses. However, the high mobility of vehicles would result in significant beam training overhead in the mmWave vehicular communications. Hence, in this paper, a fast consecutive beam tracking (FC-BET) scheme based on long short-term memory (LSTM) is proposed. By predicting beam angles through the LSTM network consecutively, the overhead caused by frequent beam training in mmWave vehicular communications can be reduced. To evaluate the proposed scheme, a time series channel dataset is built by using sequential vehicle information generated from road traffic simulation software named “Simulation of Urban MObility (SUMO)”. Simulation results show that the FCBET scheme can significantly reduce overhead with an acceptable loss in spectral efficiency compared with conventional beam training schemes.

关键词： Training Spectral efficiency Simulation Roads Time series analysis Traffic control Loss measurement

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：