检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zhao, Weichao Hu, Hezhen Zhou, Wengang Mao, Yunyao Wang, Min Li, Houqiang The CAS Key Laboratory of Technology in Geospatial Information Processing and Application System Department of Electronic Engineering and Information Science University of Science and Technology of China Hefei230027 China The Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei230030 China

Sign language recognition (SLR) has long been plagued by insufficient model representation capabilities. Although current pre-training approaches have alleviated this dilemma to some extent and yielded promising performance by employing various pretext tasks on sign pose data, these methods still suffer from two primary limitations: i) Explicit motion information is usually disregarded in previous pretext tasks, leading to partial information loss and limited representation capability. ii) Previous methods focus on the local context of a sign pose sequence, without incorporating the guidance of the global meaning of lexical signs. To this end, we propose a Motion-Aware masked autoencoder with Semantic Alignment (MASA) that integrates rich motion cues and global semantic information in a self-supervised learning paradigm for SLR. Our framework contains two crucial components, i.e., a motion-aware masked autoencoder (MA) and a momentum semantic alignment module (SA). Specifically, in MA, we introduce an autoencoder architecture with a motion-aware masked strategy to reconstruct motion residuals of masked frames, thereby explicitly exploring dynamic motion cues among sign pose sequences. Moreover, in SA, we embed our framework with global semantic awareness by aligning the embeddings of different augmented samples from the input sequence in the shared latent space. In this way, our framework can simultaneously learn local motion cues and global semantic features for comprehensive sign language representation. Furthermore, we conduct extensive experiments to validate the effectiveness of our method, achieving new state-of-the-art performance on four public benchmarks. The source code are publicly available at https://***/sakura/MASA. Copyright © 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

arXiv

引用

arXiv 2024年

作者： Wu, Hui Wang, Min Zhou, Wengang Li, Houqiang The CAS Key Laboratory of Technology in Geospatial Information Processing and Application System Department of Electronic Engineering and Information Science University of Science and Technology of China Hefei230027 China The Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei230030 China

Asymmetric image retrieval is a task that seeks to balance retrieval accuracy and efficiency by leveraging lightweight and large models for the query and gallery sides, respectively. The key to asymmetric image retrieval is realizing feature compatibility between different models. Despite the great progress, most existing approaches either rely on classifiers inherited from gallery models or simply impose constraints at the instance level, ignoring the structure of embedding space. In this work, we propose a simple yet effective structure similarity preserving method to achieve feature compatibility between query and gallery models. Specifically, we first train a product quantizer offline with the image features embedded by the gallery model. The centroid vectors in the quantizer serve as anchor points in the embedding space of the gallery model to characterize its structure. During the training of the query model, anchor points are shared by the query and gallery models. The relationships between image features and centroid vectors are considered as structure similarities and constrained to be consistent. Moreover, our approach makes no assumption about the existence of any labeled training data and thus can be extended to an unlimited amount of data. Comprehensive experiments on large-scale landmark retrieval demonstrate the effectiveness of our approach. Our code is released at: https://***/MCC-WH/SSP. © 2024, CC BY.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

3D Point Cloud Reconstruction of Vehicle using Inversely Mapping and Voting from CSAR Images

3D Point Cloud Reconstruction of Vehicle using Inversely Map...

引用

IEEE International Conference on Radar

作者： Shanshan Feng Yun Lin Fei Teng Wen Hong Key Laboratory of Technology in Geospatial Information Processing and Application System Aerospace Information Research Institute Chinese Academy of Sciences University of Chinese Academy of Sciences Institute of Electronics Chinese Academy of Sciences Beijing China School of Electronic Information Engineering North China University of Technology Beijing China

ISBN: (纸本)9781665468893

3D reconstruction of object has raised much interest in the field of SAR. The feature of target at multi aspect angles can be obtained from sub-aperture images provided by circular SAR(CSAR), which is conducive to 3D reconstruction. Radargrammetric method is a conventional way to extract DEM while its performance for 3D reconstruction is limited by the image registration. It is difficult to find corresponding points in different sub-aperture images. In this paper, we proposed a method for 3D reconstruction of vehicle based on projections in sub-aperture images. According to the imaging mechanism of CSAR, different targets located on the same iso-range line in the zero doppler plane fall into the same cell. For a projection point, given a series of offsets, the projection point will be mapped inversely to the 3D mesh along the iso-range line. We can obtain candidates of the target. The intersection of iso-range lines can be regarded as voting process. For a candidate, the more times of intersection, the higher the number of votes, and the candidate point will be reserved. This fully excavates the information contained in the angle dimension of CSAR. The proposed approach is verified by the Gotcha Volumetric SAR Data Set.

关键词： Point cloud compression Space vehicles Image registration Three-dimensional displays Imaging Radar imaging Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Descriptor systems State-space Conditions to Guarantee Negative Imaginary Properties without Minimality Restrictions

Descriptor Systems State-space Conditions to Guarantee Negat...

引用

IEEE Annual Conference on Decision and Control

作者： Junlin Xiong Alexander Lanzon Ian R. Petersen CAS Key Lab of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei 230026 China Control Systems Centre School of Electrical and Electronic Engineering University of Manchester Manchester M13 9PL U.K. School of Engineering and Information Technology University of New South Wales at the Australian Defence Force Academy Canberra ACT 2600 Australia

ISBN: (纸本)9781479978878

This paper is concerned with negative imaginary lemmas for descriptor systems. Without the minimal state-space realization assumption, sufficient conditions are developed for a negative imaginary lemma and a strictly negative imaginary lemma, respectively. As corollaries, sufficient conditions are derived to ensure the systems are both admissible and negative imaginary. Also, new sufficient negative imaginary lemmas are found for standard linear systems as special cases. The developed negative imaginary lemmas are applicable to descriptor systems with impulse modes. Two examples are used to illustrate the theory.

关键词： Theorem Negative Linear system Descriptors Lemma Sufficient conditions

来源：评论

学校读者我要写书评

暂无评论

Pattern Analysis and Placement Optimization of the Four-horn Monopulse for Terahertz Communication

Pattern Analysis and Placement Optimization of the Four-horn...

引用

Cross Strait Quad-Regional Radio Science and Wireless technology Conference (CSRWTC)

作者： Yong-Han Lu Zhong-bo Zhu Jing Ma Bin Shi Yu-ting Zhang Lin Peng Key Laboratory of Microwave and Optical Wave Application Technology Guilin University of Electronic Technology Guilin Guangxi China National Key Laboratory of Science and Technology on Space Microwave Xi'an China Science and Technology on Special System Simulation Laboratory Beijing Simulation Center Beijing China Guangxi Key Laboratory of Optoelectronic Information Processing School of Optoelectronic Engineering Guilin University of Electronic Technology Guilin China

The mobile node communication in terahertz monopulse system requires narrow beam to align with the mobile target precisely. In this paper, the radiation pattern of four-horn monopulse antenna is analyzed by use of the geometric optics (GO) and aperture field integration method (AFIM), and an efficient placement optimization to reduce the beamwidth of four-horn monopulse is presented. The optimization combines the genetic algorithm (GA) with GO-AFIM. The GA is employed to seek the optimal positions of the four horns, and the GO and AFIM are introduced into the fitness function of GA to evaluate the individual fitness. The optimization result has narrowed the beamwidth and enhanced gain of radiation pattern. Compared with the simulation in full wave software, the proposed method costs less time in pattern analysis and performs more efficiently in placement optimization.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A TOPSAR Calibration Method For processing system Of GF3 Next Generation

A TOPSAR Calibration Method For Processing System Of GF3 Nex...

引用

Asian and Pacific Conference on Synthetic Aperture Radar (APSAR)

作者： Di Yin Bing Han Jili Sun Aiping Chen Liangbo Zhao Xinzhe Yuan Lihua Zhong Yuxin Hu University of Chinese Academy of Sciences Beijing China Institute of Electronics Chinese Academy of Sciences Beijing China Beijing Institute of Telemetry and Telecommunications Technology Beijing China Chinese Academy of Space Technology China Beijing China National Satellite Ocean Application Service State Oceanic Administration Beijing China Key Laboratory of Technology in Geo-Spatial Information Processing and Application Systems Institute of Electronics Chinese Academy of Sciences Beijing China

ISBN: (数字)9781728129129

ISBN: (纸本)9781728129136

TOPSAR is an earth-imaging technique, which can provide wide swath coverage. The paper introduces a TOPSAR focusing and calibrating experiment based on the TOPSAR data acquired by Gaofen3(GF3). In this paper, we firstly derive the processor calibration factors under the demands of keeping signal energy invariant. After that, we fully analyze the impact of antenna electronic steering on TOPSAR products. Aimed to be applied to TOPSAR mode processing system of a SAR satellite, the next generation of GF3, calibration methods to processor and electronic steering was proposed in this paper.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Two-Stage OD Flow Prediction for Emergency in Urban Rail Transit

引用

IEEE Transactions on Intelligent Transportation systems 2024年第1期25卷 920-928页

作者： Zhu, Guangyu Ding, Jiacun Wei, Yun Yi, Yang Xu, Sendren Sheng-Dong Wu, Edmond Q. Beijing Jiaotong University Key Lab. of Transport Industry of Big Data Application Technologies for Comprehensive Transport The Beijing Research Center of Urban Traffic Information Sensing and Service Technologies Beijing100044 China Beijing Mass Transit Railway Operation Corporation Ltd. Beijing100014 China Yangzhou University College of Information Engineering Yangzhou225127 China National Taiwan University of Science and Technology Automation and Control Center The Graduate Institute of Automation and Control Taipei106335 Taiwan Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China The Shanghai Engineering Research Center of Intelligent Control and Management Department of Automation Shanghai200240 China

Urban rail transit (URT) is vulnerable to natural disasters and social emergencies including fire, storm and epidemic (such as COVID-19), and real-time origin-destination (OD) flow prediction provides URT operators with important information to ensure the safety of URT system. However, hindered by the high dimensionality of OD flow and the lack of supportive information reflecting the real-time passenger flow changes, study in this area is at the beginning stage. A novel model consisting of two stages is proposed for OD flow prediction. The first stage predicts the inflows of all stations by Long Short-Term Memory (LSTM) in real time, where the dimension is reduced compared with predicting OD flows directly. In the second stage, the notion of separation rate, namely, the proportion of inbound passengers bounding for another station, is estimated. Finally, The OD flow is predicted by multiplying the inflow and separation rate. Experiments based on Hangzhou Metro dataset show the proposed model outperforms the contrast model in weighted mean average error (WMAE) and weighted mean square error (WMSE). Results also suggest that the proposed prediction model performs better on weekdays than on weekends, and with greater accuracy on larger OD flows. © 2000-2011 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Optimal denial-of-service attack energy management over an SINR-based network

arXiv

引用

arXiv 2018年

作者： Qin, Jiahu Li, Menglin Shi, Ling Kang, Yu Department of Automation University of Science and Technology of China Hefei230027 China Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Clear Water Bay Kowloon Hong Kong Department of Automation State Key Laboratory of Fire Science Institute of Advanced Technology University of Science and Technology of China Hefei230027 China Key Laboratory of Technology in Geo-Spatial Information Processing and Application Systems Chinese Academy of Sciences Beijing100190 China

We consider a scenario in which a DoS attacker with the limited power resource and the purpose of degrading the system performance, jams a wireless network through which the packet from a sensor is sent to a remote estimator to estimate the system state. To degrade the estimation quality most effectively with a given energy budget, the attacker aims to solve the problem of how much power to obstruct the channel each time, which is the recently proposed optimal attack energy management problem. The existing works are built on an ideal network model in which the packet dropout never occurs when the attack is absent. To encompass wireless transmission losses, we introduce the signal-to-interference-plus-noise ratio-based network. First we focus on the case when the attacker employs the constant power level. To maximize the expected terminal estimation error at the remote estimator, we provide some sufficient conditions for the existence of an explicit solution to the optimal static attack energy management problem and the solution is constructed. Compared with the existing result in which corresponding sufficient conditions work only when the system matrix is normal, the obtained conditions in this paper are viable for a general system and shown to be more relaxed. For the other important index of system performance, the average expected estimation error, the associated sufficient conditions are also derived based on a different analysis approach with the existing work. And a feasible method is presented for both indexes to seek the optimal constant attack power level when the system fails to meet the proposed sufficient conditions. Then when the real-time ACK information can be acquired, the attacker desires a time-varying power attack strategy, based on which a Markov decision process (MDP) based algorithm is designed to solve the optimal dynamic attack energy management problem. We further study the optimal tradeoff between attack energy and system degradation. Spec

关键词： Signal interference

来源：评论

学校读者我要写书评

暂无评论

Adaptive Cohen's Class Time-Frequency Distribution

arXiv

引用

arXiv 2024年

作者： Cui, Manjun Zhang, Zhichao Han, Jie Chen, Yunjie Cao, Chunzheng The School of Mathematics and Statistics Nanjing University of Information Science and Technology Nanjing210044 China The Key Laboratory of System Control and Information Processing Ministry of Education Shanghai200240 China The Key Laboratory of Computational Science and Application of Hainan Province Haikou571158 China The School of Remote Sensing and Geomatics Engineering Nanjing University of Information Science and Technology Nanjing210044 China

The fixed kernel function-based Cohen's class time-frequency distributions (CCTFDs) allow flexibility in denoising for some specific polluted signals. Due to the limitation of fixed kernel functions, however, from the view point of filtering they fail to automatically adjust the response according to the change of signal to adapt to different signal characteristics. In this letter, we integrate Wiener filter principle and the time-frequency filtering mechanism of CCTFD to design the least-squares adaptive filter method in the Wigner-Ville distribution (WVD) domain, giving birth to the least-squares adaptive filter-based CCTFD whose kernel function can be adjusted with the input signal automatically to achieve the minimum mean-square error denoising in the WVD domain. Some examples are also carried out to demonstrate that the proposed adaptive CCTFD outperforms some state-of-the-arts in noise suppression. Copyright © 2024, The Authors. All rights reserved.

关键词： Adaptive filters

来源：评论

学校读者我要写书评

暂无评论

UJN-Land: A Large-Scale High-Resolution Parcel of Land of Multi-temporal Dataset with CNN Based Semantic Segmentation Analysis 7th

UJN-Land: A Large-Scale High-Resolution Parcel of Land of Mu...

引用

7th International Conference on Life system Modeling and Simulation, LSMS 2021, and the 7th International Conference on Intelligent Computing for Sustainable Energy and Environment, ICSEE 2021

作者： Shen, Yuan Wang, Yulin Yang, Shiyong Li, Yan Han, Shiyuan Liu, Zhen Xu, Tao School of Information Science and Engineering University of Jinan Jinan250022 China Highresolution Earth Observation System Shandong Center of Data and Application University of Jinan Jinan250022 China Shandong Provincial Key Laboratory of Network Based Intelligent Computing University of Jinan Jinan250022 China Shandong Institutes of Industrial Technonlogy Jinan250102 China Land Spatial Data and Remote Sensing Technology Institute of Shandong Province Jinan250002 China

ISBN: (纸本)9789811672125

Semantic segmentation of land in remote sensing images plays an important role in urban management and rural planning, and can provide intelligent analysis for urban development. Convolutional neural network (CNN) based methods have achieved good performance in object detection in computer vision, which benefits from the popularity of large-scale datasets. However, most of segmentation of land dataset were constructed based on various satellite images and samples that lack the number and diversity of existing datasets. These problems have brought challenges to the improvement and application of CNN based land parcel segmentation methods. This paper presented a large-scale high-resolution land dataset based on CNN analysis. More than 200,000 images of 256*256 pixels were obtained from Gaofen satellite images with a spatial resolution of 0.8 m, in which four category samples were manually annotated. In the experiment, three CNN based semantic segmentation methods were used as experimental baseline methods. The experimental results showed that the availability of the UJN-Land dataset is beneficial to the planning and management of cultivated land. © 2021, Springer Nature Singapore Pte Ltd.

关键词： 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：