检索结果-内蒙古大学图书馆

26th European Conference on Artificial Intelligence, ECAI 2023

作者： Chen, Yuchen Ren, Pengfei Wang, Jingyu Sun, Haifeng Qi, Qi Wang, Jing Liao, Jianxin State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications China

ISBN: (纸本)9781643684369

3D hand reconstruction from RGB image has attracted a lot of attention due to its crucial role in human-computer interaction. Nevertheless, it is still challenging to perform 3D hand reconstruction under conditions of hand-object interaction due to severe mutual occlusion. Previous methods usually adopt fixed convolution kernel to extract features. We argue that simply sharing the static filter for all regions is impertinent, given that the occlusion degree varies across different regions, resulting in inconsistent visual representations. To address this issue, we proposed Region-aware Dynamic Filtering Network (RDFNet), which dynamically generates convolution kernels based on the features of different regions, thereby adaptively extracting region-related information. Furthermore, we introduce a dynamic receptive field selection mechanism to determine the most appropriate scale for the convolution kernel. For the severely occluded regions, larger receptive field is needed to capture semantic-related features, while the visible regions are mainly concerned with their own local pattern to accumulate spatial-related features and avoid the interference of irrelevant information. Our proposed RDFNet outperforms state-of-the-art methods by a large margin on several challenging hand-object interaction datasets. © 2023 The Authors.

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

Object-based Multipath Transmission Scheduling Algorithm in Multi-modal Scenarios

Object-based Multipath Transmission Scheduling Algorithm in ...

引用

IEEE Conference on Global Communications (IEEE GLOBECOM) - Intelligent Communications for Shared Prosperity

作者： Zhang, Zhipeng Tian, Ye Yang, Mengyu Gong, Xiangyang Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing Peoples R China

ISBN: (纸本)9798350310900

At present, with the rapid advancement of multimedia technology, more and more multi-modal applications have emerged. The data communication of multi-modal applications involves multiple modalities, and the transmitted data has deadline requirements and block transmission characteristics. However, existing transport layer protocols cannot meet the transmission requirements of applications by perceiving the data attributes and it is difficult to avoid high-priority modalities from excessively seizing transmission resources, resulting in transmission starvation in other modalities. Therefore, this paper considers the data blocks and their transmission requirements of the upper layer application as independent data objects and proposes an object multipath transmission scheduling algorithm (OMTS) that can consider the fairness of multi-modal transmission. OMTS uses reinforcement learning algorithms to comprehensively consider the transmission requirements of data objects and the quality of multipath network transmission, to determine the transmission order and path allocation strategy of objects. In addition, we also design a model structure that separates scheduling and learning, allowing the algorithm to learn more valuable scheduling strategies through continuous interaction with the environment. The comparative experiment of data transmission through the network simulation environment shows that OMTS is superior to existing scheduling algorithms.

关键词： data object multipath transmission transmission scheduling reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

SPSO-Pruner: a network pruning method on YOLOv5 for fewer categories scenarios

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2024年第4期83卷 11493-11506页

作者： Zhang, Yifei Liu, Xinchen Chen, Yan Xie, Linyao Wang, Hongbo Salem, Osman Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China Univ Paris Cite Ctr Borelli UMR 9010 F-75006 Paris France

In recent years, object detection methods based on deep learning have developed rapidly, but we have found that comparing with public datasets, the categories of objects to be recognized in most practical scenarios are relatively small. In such scenarios, we proposed a network pruning method inspired by the PSO algorithm, named SPSO-Pruner to improve the detection accuracy and speed, while reducing the model parameters. To better fit the application scenarios, we used the up-to-date one stage detector - YOLOv5 to adapt to the real-time requirements. Comparing with regular network prune method such as slimming prune, our SPSO-pruner can reach better accuracy with less than 50% parameters. Besides, we proposed an optimization method for confidence Loss of YOLOv5 which can balance the Precision and Recall of our model, the F1 of our method is 4% higher than the baseline model.

关键词： Few classes Network pruning YOLOv5 PSO Loss optimization

来源：评论

学校读者我要写书评

暂无评论

Semantic Clone Detection Based on Code Feature Fusion Learning

引用

INTERNATIONAL JOURNAL OF SOFTWARE ENGINEERING AND KNOWLEDGE ENGINEERING 2023年第7期33卷 1039-1062页

作者： Zhang, Qianjin Jin, Dahai Wang, Yawen Gong, Yunzhan Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China Guangxi Key Lab Cryptog & Informat Secur Guilin 541004 Guangxi Peoples R China

Code clones are duplicated code snippets that significantly threaten software maintenance and the public corpora of code representation learning. Traditionally, code context and its structure information abstract syntax tree (AST), control flow graph (CFG) are typical representations of source code, and context-based models and structure-based models contributed significantly to the development of code clone detection. In this paper, we present a hybrid embedding model for code clone detection (HEM-CCD), a fusion method of token sequential information and graph-based structure information. We insert tokens' global context information encoded by a bi-directional recurrent neural network into the AST-based graph for comprehensive code semantic representation. Then, feeding the graph into a gated graph neural network we generate code semantic vectors for similarity evaluation. We have implemented our model on two public clone datasets (BigCloneBench and GoogleCodeJam), and the results indicate that HEM-CCD outperforms several state-of-the-art approaches.

关键词： Code clone detection code representation learning code semantic understanding graph neural network

来源：评论

学校读者我要写书评

暂无评论

Learning-Based Joint Beamforming and Antenna Movement Design for Movable Antenna Systems

引用

IEEE WIRELESS COMMUNICATIONS LETTERS 2024年第8期13卷 2120-2124页

作者： Weng, Caihao Chen, Yuanbin Zhu, Lipeng Wang, Ying Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China Natl Univ Singapore Dept Elect & Comp Engn Singapore 117583 Singapore

In this letter, we investigate a multi-receiver communication system enabled by movable antennas (MAs). Specifically, the transmit beamforming and the double-side (DS) antenna movement at the transceiver are jointly designed to maximize the sum-rate of all receivers under imperfect channel state information (CSI). Since the formulated problem is non-convex with highly coupled variables, conventional optimization methods cannot solve it efficiently. To address these challenges, an effective learning-based algorithm is proposed, namely heterogeneous multi-agent deep deterministic policy gradient (MADDPG), which incorporates two agents to learn policies for beamforming and movement of MAs, respectively. Based on the offline learning under numerous imperfect CSI, the proposed heterogeneous MADDPG can output the solutions for transmit beamforming and antenna movement in real time. Simulation results validate the effectiveness of the proposed algorithm, and the MA can significantly improve the sum-rate performance of multiple receivers compared to other benchmark schemes.

关键词： Wireless communication Transmitting antennas Transmitters Array signal processing Receiving antennas Radio frequency Vectors Movable antenna (MA) antenna position optimization deep reinforcement learning (DRL) imperfect channel state information (CSI)

来源：评论

学校读者我要写书评

暂无评论

A novel rotor dynamic balancing method based on blade tip clearance measurement without the once per revolution sensor

引用

Chinese Journal of Aeronautics 2025年第2期38卷 445-458页

作者： Weibo LI Weimin WANG Shuai ZHANG Jiale WANG Yulong LIN Tianqing LI Key Lab of Engine Health Monitoring-Control and Networking of Ministry of Education Beijing University of Chemical TechnologyBeijing 100029China State Key Laboratory of High-end Compressor and System Technology Beijing University of Chemical TechnologyBeijing 100029China

The existence of the aeroengine casing,limited monitoring points,and multi-fault characteristics make obtaining the rotor’s vibration transmission characteristics challenging,resulting in difficulties accurately identifying the rotor *** paper utilizes a high-frequency composite sensor to monitor the engine’s blade tip clearance(BTC)and extracts unbalanced information from BTC signals for rotor dynamic balancing,while avoiding the need for the once per revolution(OPR)***,the vibration characteristics of the rotor-blade system under multi-fault conditions are ***,based on BTC measurement,a none OPR method and an unbalance identification method are proposed,in which the radial vibration of the blade tip in the BTC signals at different speeds is extracted and operated in the time domain to obtain the rotor unbalanced vibration,the signal is reconstructed,and cross-correlation analysis is used to accurately identify the magnitude and phase of the unbalanced ***,a rotor test bench is utilized for experimental *** results reveal that the dynamic balancing method based on the BTC signal can more precisely identify the rotor unbalance than the traditional rotor dynamic balancing *** application of this technique will effectively improve engine health management and fault prediction.

关键词： Aeroengine Rotor unbalance Composite sensor None once per revolution Blade tip clearance Dynamic balancing

来源：评论

学校读者我要写书评

暂无评论

Dynamic Network Slice for Bursty Edge Traffic

引用

IEEE-ACM TRANSACTIONS ON networking 2024年第4期32卷 3142-3157页

作者： Han, Rongxin Wang, Jingyu Qi, Qi Chen, Dezhi Zhuang, Zirui Sun, Haifeng Fu, Xiaoyuan Liao, Jianxin Guo, Song Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China Hong Kong Polytech Univ Dept Comp Hong Kong Peoples R China

Edge network slicing promises better utilization of network resources by dynamically allocating resources on demand. However, addressing the imbalance between slice resources and user demands becomes challenging when complex user behaviors lead to bursty traffic within the edge network. Hence, we propose a comprehensive dynamic slice strategy with two coupled sub-strategies (i) bursty-sensitive slice resource coordination and (ii) proactive demand resource matching to find an optimal balance. For obtaining stable strategies, the edge network with bursty traffic is formulated as a bi-level Lyapunov optimization problem. Then we propose a resource allocation and request redirection (RA-RR) algorithm with polynomial complexity by introducing deep reinforcement learning to guarantee real-time. Specifically, two agents are trained to solve two sub-strategies, and the Lyapunov drift-plus-penalty function is used as the reward to keep queues stable. RA-RR is responsive to fluctuations in demand and realizes an efficient interaction of coupled decision-making. Moreover, a training method based on alternating optimization is designed to ensure convergence of the RA-RR algorithm. Experiments demonstrate that the proposal can maximize network revenue while ensuring the stability of slice services when edge traffic bursts, and has an average improvement of 20.4% compared with comparisons.

关键词： Dynamic scheduling Resource management Optimization Vehicle dynamics Training Convergence Task analysis edge network slice bursty traffic Lyapunov theory deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Cache-Assisted Collaborative Task Offloading and Resource Allocation Strategy: A Metareinforcement Learning Approach

引用

IEEE INTERNET OF THINGS JOURNAL 2022年第20期9卷 19823-19842页

作者： Chen, Shiyou Rui, Lanlan Gao, Zhipeng Li, Wenjing Qiu, Xuesong Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China

Multiaccess edge computing (MEC) provides users with better Quality of Experience (QoE) via offloading tasks to the nearby edge. However, the emergence of new Internet of Things applications with multiple tasks and repeated requests brings redundant computation and transmission to the edge. Meanwhile, the current offloading method based on deep reinforcement learning (DRL) has low sampling efficiency and slow convergence issues for training in a changing environment. Therefore, improving QoE of computation offloading services is still the ultimate challenge. In this article, we devise a collaboration of computing and cache resources among multiple edge nodes, which could reduce redundant computation and transmission. Specifically, we formulate a cache-assisted computation offloading process as a QoE-aware utility maximization problem based on multidimensional indicators. Then, we propose a cache-assisted collaborative task offloading and resource allocation strategy to solve it. This strategy is decomposed into two subproblems. First, to determine and obtain task cache state, we propose a collaborative task caching algorithm, which can improve the hit rate of tasks while balancing network overhead. Second, to acquire offloading and resource allocation decisions efficiently, we propose a metareinforcement learning-based cache-assisted computation offloading method (MCCOM), which can achieve rapid offloading decisions with a few gradient updates and samples. The optimization problem was transformed into multiple Markov decision processes (multiple MDPs). The improved learning process includes metapolicy learning that adapts to multiple Markov decision processes (MDPs) and policy learning for a specific MDP based on metapolicy. Simulation results show that our proposed method outperforms baselines in terms of QoE indicators while achieving rapid convergence and decisions.

关键词： Task analysis Quality of experience Collaboration Resource management Internet of Things Adaptation models Mobile handsets Computation offloading edge cache metareinforcement learning (meta-RL) Quality of Experience (QoE)

来源：评论

学校读者我要写书评

暂无评论

An Early Collision Detection Scheme for LEO Satellite Based on Cyclic Shift Offset 9

An Early Collision Detection Scheme for LEO Satellite Based ...

引用

9th International Conference on Communication and Information Processing, ICCIP 2023

作者： Li, Lihua Chang, Kexin Huang, Jiping Wang, Qiushi State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications China

ISBN: (纸本)9798400708909

In order to enhance collision detection efficiency when massive machine-type devices attempt access based on low earth orbiting (LEO) satellite scenario in 6G Non-Terrestrial Networks (NTN), an early collision detection scheme based on cyclic shift offset is proposed. By leveraging the initial cycle shift value as the identification of different preambles, and the same cyclic shift step value to ensure the quantities of cyclic shift indexes of different preambles, the proposed scheme can identify different devices based on cyclic shift offset and has improvement of collision detection probability and load monitoring accuracy and decline of collision detection error probablity, compared with the existing collision detection scheme. © 2023 Copyright held by the owner/author(s)

关键词： Orbits

来源：评论

学校读者我要写书评

暂无评论

DirectL: Efficient Radiance Fields Rendering for 3D Light Field Displays

引用

ACM TRANSACTIONS ON GRAPHICS 2024年第6期43卷 1-19页

作者： Yang, Zongyuan Liu, Baolin Song, Yingde Xiong, Yongping Yi, Lan Zhang, Zhaohe Yu, Xunbo Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing Peoples R China Beijing Univ Posts & Telecommun Beijing Peoples R China Beijing Univ Posts & Telecommun State Key Lab Informat Photon & Opt Commun Beijing Peoples R China

Autostereoscopic display technology, despite decades of development, has not achieved extensive application, primarily due to the daunting challenge of three-dimensional (3D) content creation for non-specialists. The emergence of Radiance Field as an innovative 3D representation has markedly revolutionized the domains of 3D reconstruction and generation, simplifying 3D content creation for common users and broadening the applicability of Light Field Displays (LFDs). However, the combination of these two technologies remains largely unexplored. The standard paradigm to create optimal content for parallax-based light field displays demands rendering at least 45 slightly shifted views preferably at high resolution per frame, a substantial hurdle for real-time rendering. We introduce DirectL, a novel rendering paradigm for Radiance Fields on autostereoscopic displays with lenticular lens. By thoroughly analyzing the interleaved mapping of spatial rays to screen sub-pixels, we accurately render only the light rays entering the human eye and propose subpixel repurposing to significantly reduce the pixel count required for rendering. Tailored for the two predominant radiance fields-Neural Radiance Fields (NeRFs) and 3D Gaussian Splatting (3DGS), we propose corresponding optimized rendering pipelines that directly render the light field images instead of multi-view images, achieving state-of-the-art rendering speeds on autostereoscopic displays. Extensive experiments across various autostereoscopic displays and user visual perception assessments demonstrate that DirectL accelerates rendering by up to 40 times compared to the standard paradigm without sacrificing visual quality. Its rendering process-only modification allows seamless integration into subsequent radiance field tasks. Finally, we incorporate DirectL into diverse applications, showcasing the stunning visual experiences and the synergy between Light Field Displays and Radiance Fields, which reveals the immense p

关键词： Radiance fields Light field displays

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：