检索结果-内蒙古大学图书馆

JNMR: Joint Non-Linear Motion Regression for Video Frame Interpolation

IEEE Transactions on Image Processing 2023年 32卷 5283-5295页

作者： Liu, Meiqin Xu, Chenming Yao, Chao Lin, Chunyu Zhao, Yao Beijing Jiaotong University Institute of Information Science Beijing100044 China Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing100044 China University of Science and Technology Beijing School of Computer and Communication Engineering Beijing100083 China

Video frame interpolation (VFI) aims to generate predictive frames by motion-warping from bidirectional references. Most examples of VFI utilize spatiotemporal semantic information to realize motion estimation and interpolation. However, due to variable acceleration, irregular movement trajectories, and camera movement in real-world cases, they can not be sufficient to deal with non-linear middle frame estimation. In this paper, we present a reformulation of the VFI as a joint non-linear motion regression (JNMR) strategy to model the complicated inter-frame motions. Specifically, the motion trajectory between the target frame and multiple reference frames is regressed by a temporal concatenation of multi-stage quadratic models. Then, a comprehensive joint distribution is constructed to connect all temporal motions. Moreover, to reserve more contextual details for joint regression, the feature learning network is devised to explore clarified feature expressions with dense skip-connection. Later, a coarse-to-fine synthesis enhancement module is utilized to learn visual dynamics at different resolutions with multi-scale textures. The experimental VFI results show the effectiveness and significant improvement of joint motion regression over the state-of-the-art methods. The code is available at https://***/ruhig6/JNMR. © 1992-2012 IEEE.

关键词： Interpolation

来源：评论

学校读者我要写书评

暂无评论

Lightweight Authentication of Devices in Industrial Control Systems 14

Lightweight Authentication of Devices in Industrial Control ...

引用

14th IEEE International Conference on Software engineering and Service Science, ICSESS 2023

作者： Wang, Long Niu, Siqi Zhai, Henggao Fan, Jing Wang, Lei Engineering Research Institute of China National Computer System Beijing China University of Science and Technology Beijing Department of Computer and Communication Engineering Beijing China Coocaa Network Technology Co. Ltd. Guangdong China

ISBN: (纸本)9798350336269

A security authentication protocol based on number theory research unit (NTRU) for industrial control devices is proposed to address the security of data transmission in industrial control systems and the lack of resistance to attacks of security authentication protocols. Most of the original protocols contain complex encryption and decryption operations, which are difficult to run on industrial control devices with simple structures and cannot resist new types of network attacks. In this paper, the protocol takes advantage of the simple operation of NTRU public key encryption system and sets the authorization center to send only the public key of the device in a variant form to achieve the purpose of resisting new attacks such as quantum attacks and internal attacks, and the anti-attack capability is strengthened. © 2023 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Learning from Imperfect Data: Towards Efficient Knowledge Distillation of Autoregressive Language Models for Text-to-SQL

Learning from Imperfect Data: Towards Efficient Knowledge Di...

引用

2024 Findings of the Association for Computational Linguistics, EMNLP 2024

作者： Zhong, Qihuang Chen, Kunfeng Ding, Liang Liu, Juhua Du, Bo Tao, Dacheng School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China The University of Sydney Australia Nanyang Technological University Singapore

ISBN: (纸本)9798891761681

Large Language Models (LLMs) have shown promising performance in text-to-SQL, which involves translating natural language questions into SQL queries. However, current text-to-SQL LLMs are computationally expensive and challenging to deploy in real-world applications, highlighting the importance of compressing them. To achieve this goal, knowledge distillation (KD) is a common approach, which aims to distill the larger teacher model into a smaller student model. While numerous KD methods for autoregressive LLMs have emerged recently, it is still under-explored whether they work well in complex text-to-SQL scenarios. To this end, we conduct a series of analyses and reveal that these KD methods generally fall short in balancing performance and efficiency. In response to this problem, we propose to improve the KD with Imperfect Data, namely KID, which effectively boosts the performance without introducing much training budget. The core of KID is to efficiently mitigate the training-inference mismatch by simulating the cascading effect1 of inference in the imperfect training data. Extensive experiments on 5 text-to-SQL benchmarks show that, KID can not only achieve consistent and significant performance gains (up to +5.83% average score) across all model types and sizes, but also effectively improve the training efficiency. © 2024 Association for Computational Linguistics.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Dynamic Visible Light Positioning Based on Enhanced Visual Target Tracking

引用

China communications 2023年第10期20卷 276-291页

作者： Xiangyu Liu Jingyu Hao Lei Guo Song Song School of Information Science and Engineering Shenyang Ligong UniversityShenyang 110158China Department of Computer Science and Engineering Southern University of Science and TechnologyShenzhen 518055China School of Computer Science and Engineering Northeastern UniversityShenyang 110819China School of Communication and Information Engineering Chongqing University of Posts and TelecommunicationsChongqing 400065China Hangzhou Institute of Advanced Technology Hangzhou 310056China Institute of Intelligent Communications and Network Security Chongqing University of Posts and TelecommunicationsChongqing 400065China

In visible light positioning systems,some scholars have proposed target tracking algorithms to balance the relationship among positioning accuracy,real-time performance,and ***,there are still two problems:(1)When the captured LED disappears and the uncertain LED reappears,existing tracking algorithms may recognize the landmark in error;(2)The receiver is not always able to achieve positioning under various moving *** this paper,we propose an enhanced visual target tracking algorithm to solve the above ***,we design the lightweight recognition/demodulation mechanism,which combines Kalman filtering with simple image preprocessing to quickly track and accurately demodulate the ***,we use the Gaussian mixture model and the LED color feature to enable the system to achieve positioning,when the receiver is under various moving *** results show that our system can achieve high-precision dynamic positioning and improve the system’s comprehensive performance.

关键词： visible light positioning visual target tracking gaussian mixture model kalman filtering system performance

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Segmentation network Based on Weak Supervision for COVID-19 Detection 9th

A Lightweight Segmentation Network Based on Weak Supervisio...

引用

9th International Forum on Digital Multimedia communication, IFTC 2022

作者： Lu, Fangfang Liu, Tianxiang Tang, Chi Zhang, Zhihao Zhai, Guangtao Min, Xiongkuo Sun, Wei College of Computer Science and Technology Shanghai University of Electric Power Shanghai China Institute of Image Communication and Network Engineering Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9789819908554

The Coronavirus Disease 2019 (COVID-19) outbreak in late 2019 threatens global health security. Computed tomography (CT) can provide richer information for the diagnosis and treatment of COVID-19. Unfortunately, labeling of COVID-19 lesion chest CT images is an expensive affair. We solved the challenge of chest CT labeling by simply marking point annotations to the lesion areas, i.e., by marking individual pixels for each lesion area in the chest CT scan. It takes only a few seconds to complete the labeling using this labeling strategy. We also designed a lightweight segmentation model with approximately 10% of the number of model parameters of the conventional model. So, the proposed model segmented the lesions of a single image in only 0.05 s. In order to obtain the shape and size of lesions from point labels, the convex-hull based segmentation (CHS) loss function is proposed in this paper, which enables the model to obtain an approximate fully supervised performance on point labels. The experiments were compared with the current state-of-the-art (SOTA) point label segmentation methods on the COVID-19-CT-Seg dataset, and our model showed a large improvement: IoU improved by 28.85%, DSC improved by 28.91%, Sens improved by 13.75%, Spes improved by 1.18%, and MAE decreased by 1.10%. Experiments on the dataset show that the proposed model combines the advantages of lightweight and weak supervision, resulting in more accurate COVID-19 lesion segmentation results while having only a 10% performance difference with the fully supervised approach. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Dual Radial-Resonant Wide Beamwidth Circular Sector Microstrip Patch Antennas

引用

Chinese Journal of Electronics 2023年第4期32卷 710-719页

作者： MAO Xiaohui LU Wenjun JI Feiyan XING Xiuqiong ZHU Lei Jiangsu Key Laboratory of Wireless Communications Nanjing University of Posts and Telecommunications Key Laboratory of Wireless Sensor Network & Communication Shanghai Institute of Microsystem and Information Technology Chinese Academy of Sciences Department of Electrical and Computer Engineering Faculty of Science and Technology University of Macau

In this article, a design approach to a radial-resonant wide beamwidth circular sector patch antenna is advanced. As properly evolved from a U-shaped d ipole, a prototype magnetic dipole can be fit in the radial direction of a circular sector patch radiator, with its length set as the positive odd-integer multiples of onequarter wavelength. In this way, multiple TM0m（m = 1,2,...） modes resonant circular sector patch antenna with short-circuited circumference and widened E-plane beamwidth can be realized by proper excitation and perturbations. Prototype antennas are then designed and fabricated to validate the design approach. Experimental results reveal that the E-plane beamwidth of a dual-resonant antenna fabricated on air/Teflon substrate can be effectively broadened to 128°/120°, with an impedance bandwidth of 17.4%/7.1%, respectively. In both cases, the antenna heights are strictly limited to no more than 0.03-guided wavelength. It is evidently validated that the proposed approach can effectively enhance the operational bandwidth and beamwidth of a microstrip patch antenna while maintaining its inherent low profile merit.

关键词： Geometry Patch antennas Perturbation methods Prototypes Magnetic resonance Microstrip antennas Bandwidth

来源：评论

学校读者我要写书评

暂无评论

HY-PC:Enabling Consistent Positioning and communication Using Visible Light

引用

China communications 2023年第4期20卷 180-194页

作者： Xiangyu Liu Yaoheng Chen Lei Guo Song Song School of Information Science and Engineering Shenyang Ligong UniversityShenyang 110158China Department of Computer Science and Engineering Southern University of Science and TechnologyShenzhen 518055China School of Communication and Information Engineering Chongqing University of Posts and TelecommunicationsChongqing 400065China Hangzhou Institute of Advanced Technology Hangzhou 310056China Institute of Intelligent Communications and Network Security Chongqing University of Posts and TelecommunicationsChongqing 400065China

Visible light(VL)plays an important role in achieving high-precision positioning and low bit error radio(BER)data ***,most VL-based systems can not achieve positioning and communication,*** are two problems:1)the hybrid systems are difficult to extract distinguishable positioning beacon features without affecting communication performance,2)in the hybrid systems,the lost data bits in the inter-frame gap(IFG)are hard to recover,which affects positioning and communication ***,in this article,we propose a novel VL-based hybrid positioning and communication system,named HY-PC system,to solve the above ***,we propose the robust T-W mapping for recognizing specific Light Emitting Diodes(LEDs),which can provide stable LED recognition accuracy without adding extra beacon data and does not decrease the communication ***,we also propose the novel linear block coding and bit interleaving mechanism,which can recover the lost data bits in the IFG and improve data communication ***,we use commercial off-the-shelf devices to implement our HY-PC system,extensive experimental results show that our HY-PC system can achieve consistent high-precision positioning and low-BER data communication,simultaneously.

关键词： visible light positioning visible light communication T-W Mapping linear block coding bit interleaving

来源：评论

学校读者我要写书评

暂无评论

Pushing AI to wireless network edge: an overview on integrated sensing, communication, and computation towards 6G

引用

Science China(Information Sciences) 2023年第3期66卷 7-25页

作者： Guangxu ZHU Zhonghao LYU Xiang JIAO Peixi LIU Mingzhe CHEN Jie XU Shuguang CUI Ping ZHANG Shenzhen Research Institute of Big Data Future Network of Intelligence Institute (FNii) The Chinese University of Hong Kong (Shenzhen) School of Science and Engineering (SSE) The Chinese University of Hong Kong (Shenzhen) State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics Peking University Department of Electrical and Computer Engineering and Institute for Data Science and Computing University of Miami Peng Cheng Laboratory State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications

Pushing artificial intelligence(AI) from central cloud to network edge has reached board consensus in both industry and academia for materializing the vision of artificial intelligence of things(AIoT) in the sixth-generation(6G) era. This gives rise to an emerging research area known as edge intelligence, which concerns the distillation of human-like intelligence from the vast amount of data scattered at the wireless network edge. Typically, realizing edge intelligence corresponds to the processes of sensing, communication,and computation, which are coupled ingredients for data generation, exchanging, and processing, ***, conventional wireless networks design the three mentioned ingredients separately in a task-agnostic manner, which leads to difficulties in accommodating the stringent demands of ultra-low latency, ultra-high reliability, and high capacity in emerging AI applications like auto-driving and metaverse. This thus prompts a new design paradigm of seamlessly integrated sensing, communication, and computation(ISCC) in a taskoriented manner, which comprehensively accounts for the use of the data in downstream AI tasks. In view of its growing interest, this study provides a timely overview of ISCC for edge intelligence by introducing its basic concept, design challenges, and enabling techniques, surveying the state-of-the-art advancements, and shedding light on the road ahead.

关键词： sixth-generation (6G) edge intelligence artificial intelligence of things (AIoT) integrated sensing communication and computation (ISCC)

来源：评论

学校读者我要写书评

暂无评论

Error Analysis of Spherically Constrained Least Squares Reformulation in Solving the Stackelberg Prediction Game 38

Error Analysis of Spherically Constrained Least Squares Refo...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Li, Xiyuan Liu, Weiwei School of Computer Science Wuhan University China National Engineering Research Center for Multimedia Software Wuhan University China Institute of Artificial Intelligence Wuhan University China Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China

The Stackelberg prediction game (SPG) is a popular model for characterizing strategic interactions between a learner and an adversarial data provider. Although optimization problems in SPGs are often NP-hard, a notable special case involving the least squares loss (SPG-LS) has gained significant research attention recently [1, 2, 3]. The latest state-of-the-art method for solving the SPG-LS problem is the spherically constrained least squares reformulation (SCLS) method proposed in the work of [3]. However, the paper [3] lacks theoretical analysis on the error of the SCLS method, which limits its large-scale applications. In this paper, we investigate the estimation error between the learner obtained by the SCLS method and the actual learner. Specifically, we reframe the estimation error of the SCLS method as a Primary Optimization (PO) problem and utilize the Convex Gaussian min-max theorem (CGMT) to transform the PO problem into an Auxiliary Optimization (AO) problem. Subsequently, we provide a theoretical error analysis for the SCLS method based on this simplified AO problem. This analysis not only strengthens the theoretical framework of the SCLS method but also confirms the reliability of the learner produced by it. We further conduct experiments to validate our theorems, and the results are in excellent agreement with our theoretical predictions. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Spectrum Usage Anomaly Detection from Sub-Sampled Data Stream via Deep Neural network

引用

Journal of communications and Information networks 2023年第1期8卷 13-23页

作者： Han Zhang Jian Yang Junting Chen Yue Gao Institute for Communication Systems the University of SurreyGuildford GU27XHUK Mobile Communications Innovation Center China Academy of Information and Communications TechnologyBeijing 100191China Future Network Intelligence Institute(FNii)and School of Science and Engineering the Chinese University of Hong KongShenzhen 518172China School of Computer Science Fudan UniversityShanghai 200433China.Institute for Communication Systemsthe University of SurreyGuildford GU27XHUK

Anomaly detection is an essential part of any practical system in order to remedy any malfunction and accident early to create a secure and robust *** users and malfunctioning cognitive radio(CR)devices may cause severe interference to legitimate ***,there are no effective methods to detect spontaneous and irregular anomaly behaviors in sub-sampling data stream from wideband compressive spectrum sensing as an important function of a CR *** this article,to detect anomaly utilization of spectrum from sub-sampled data stream,a multiple layer perceptron/feed-forward neural network(FFNN)based solution is *** proposed solution would learn the pattern of legitimate and anomalous usages autonomously without expert's *** proposed neural network(NN)framework has also shown benefits such as more than 80%faster detection speed and lower detection error rate.

关键词： compressive sensing(CS) machine learning(ML) multicoset sampling anomaly detection

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：