检索结果-内蒙古大学图书馆

2019 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2019

作者： Xiang, Rong Liu, Yuan Zhang, Qieshi Cheng, Jun School of Computer Science and Information Security Guilin University of Electronic Technology GuangXi China Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China Chinese University of Hong Kong Hong Kong Hong Kong

ISBN: (纸本)9781728137261

Loop closure detection is a crucial module in simultaneous localization and mapping (SLAM), which reduces accumulative error in building environment map. Traditional appearance-based methods for loop closure detection are vulnerable to environmental variations as they mainly rely on hand-crafted features. The convolutional neural networks (ConvNets) can automatically learn feature representation from original image, and it is more robust to illumination changes. However, the ConvNets methods may fail when the viewpoint changes significantly due to it extract global features. In order to solve the problem mentioned above, in this paper, we design an unsupervised network which combines the advantage of the traditional and ConvNets methods, and propose a new module named spatial pyramid pooling based convolution autoencoder (SPP-CAE). We evaluate the performance of the proposed method on several open datasets using precision-recall metric. The results show that our method is feasible for detecting loops and is more robust than state-of-the-art methods. © 2019 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Integrating Appearance and Motion Cues for Visual Tracking via Spatio-Temporal Prompt

SSRN

引用

SSRN 2025年

作者： Jia, Xianxin Hou, ZhiQiang Wang, Yunlong Yue, Hao Hu, Shuai Ma, Sugang Yang, Xiaobao Pu, Lei School of Communications and Information Engineering School of Artificial Intelligence Xi’ an University of Posts and Telecommunications Xi’an710121 China Key Laboratory of Network Data Analysis and Intelligent Processing of Shaanxi Province Xi’an710121 China School of Computer Science and Technology Xi’an University of Posts and Telecommunications Xi’an710121 China Combat Support College Rocket Force University of Engineering Xi’an710025 China

Rich appearance cues in the template frame and dynamic motion cues between consecutive frames are essential for achieving robust visual tracking. However, most existing tracking methods exhibit limitations in their architectural design, often relying on a single cue while neglecting the other. This lack of integration hinders the effective interaction between different cues, thereby restricting the model’s ability to comprehensively interpret the target characteristics. To address this challenge, we propose a unified spatio-temporal prompt learning framework, ICSPTrack, which systematically captures target appearance and motion information across consecutive ***,theAppearancecueEncoderfirstextractsappearance-relatedfeatures, followed by the Motion Cue Encoder, which derives motion-related representations. These cues are subsequently integrated within the Spatio-Temporal Prompt Decoder to facilitate future reasoning by unifying different information sources. The proposed tracker was trained in an end-to-end manner and rigorously evaluated on seven benchmark datasets, including LaSOT, TNL2K, and TrackingNet. The framework achieved success rates of 72.0%, 58.5%, and 84.4% on LaSOT, TNL2K, and TrackingNet, respectively, while attaining an average overlap rate of 74.7% on GOT-10K. Despite its low computational complexity of only 28.8 GFLOPs, the model demonstrated efficient inference at 56 FPS. Experimental results indicate that the proposed method effectively handles complex tracking scenarios and achieves excellent tracking performance. © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning-Assisted Self-powered and Wearable Optical Sensor Glove for Gesture Recognition

引用

Journal of Lightwave technology 2025年

作者： Zou, Yang Lu, Chenxu Zhang, Chaomao Chen, Guozhen Kuang, Renfei Chen, Zhenshi Min, Rui Huang, Quandong Zhu, Shuyan Peng, Yungen Song, Jingcui Chen, Qingming Sun Yat-Sen University School of Microelectronics Science and Technology Guangdong Zhuhai519082 China Fujian Xiamen361005 China Guangdong 519000 China Sun Yat-Sen University School of Software Engineering Guangdong Zhuhai519082 China Huzhou College School of Electronic Information Zhejiang Huzhou313002 China Beijing Normal University Department of Psychology Faculty of Arts and Sciences Zhuhai519087 China Beijing Normal University Faculty of Psychology Beijing100875 China Sun Yat-sen University School of Electronics and Information Technology Guangdong Provincial Key Laboratory of Optoelectronic Information Processing Chips and Systems Guangzhou510006 China Guangdong University of Technology Institute of Advanced Photonics Technology School of Information Engineering Guangzhou China

Gesture recognition is a vital component of human-computer interaction (HCI), which plays a key role in artificial intelligent (AI) technology. Self-powered, portable and wearable sensors are highly desirable for HCI applications. Optical wearable sensors have gained widespread attention in gesture recognition due to their high sensitivity and great biocompatibility. This paper reports a novel mechanoluminescent (ML) polymer optical fiber-based glove designed for self-powered and portable gesture recognition. The elastic ML optical fiber directly converts finger movements into fluorescence for strain sensing. Combined with the supplementary alumina nanoparticles, the fluorescence intensity of ZnS: Cu ML phosphors has been enhanced by 7 times to achieve a high-performance strain sensor. By integrating five ML fibers into a flexible printed circuit (FPC) with a wireless communication unit, we developed a smart glove capable of gesture detection. With the assistance of machine-learning training, the proposed glove can accurately identify six hand gestures and five grasping actions with recognition accuracies of 100% and 90%, respectively. This portable intelligent glove operates without external light sources and electrical drivers, making it highly suitable for potential applications in HCI and AI fields. © 1983-2012 IEEE.

关键词： Fiber optic sensors

来源：评论

学校读者我要写书评

暂无评论

Multi-objective optimization on multistage half-band FIR filter design using simulated annealing algorithm 21

Multi-objective optimization on multistage half-band FIR fil...

引用

21st IEEE International Conference on High Performance Computing and Communications, 17th IEEE International Conference on Smart City and 5th IEEE International Conference on Data Science and Systems, HPCC/SmartCity/DSS 2019

作者： Zhang, Jin Hu, Wei Wang, Yonghao Zhu, Xiangyu College of Computer Science and Technology Wuhan University of Science and Technology China Hubei Province Key Laboratory of Intelligent Information Processing Real-time Industrial System Wuhan China Digital Media Technology Lab Birmingham City University Birmingham United Kingdom

ISBN: (纸本)9781728120584

The design of a finite impulse response (FIR) digital filter is essentially a multi-parameter and multi-objective optimization problem, different optimization techniques can be utilized to minimize the latency in the live audio processing chain by minimization or maximization of the objective function. Using cascaded FIR filters as anti-aliasing and anti-image filters for high-resolution audio conversion are common. We can optimize the parameters of each stage to achieve the overall performance requirements. the method of modified Simulated Annealing (SA) Algorithm is proposed to resize the best distribution of passband ripple, transition band and stopband attenuation for each level of Multi-stage filter. It shows the proposed a new multi-stage filter design method improves the efficiency of the designed filter in terms of filter cost and group delay comparing with traditional design. © 2019 IEEE.

关键词： FIR filters

来源：评论

学校读者我要写书评

暂无评论

A symmetric uniform formula and sole index method for sieving (twin) primes

TechRxiv

引用

TechRxiv 2020年

作者： Ren, Wei School of Computer Science China University of Geosciences Wuhan430074 China Key Laboratory of Network Assessment Technology CAS Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China Guizhou Provincial Key Laboratory of Public Big Data GuiZhou University Guizhou China

All primes can be indexed by k, as primes must be in the form of 6k+1 or 6k-1. In this paper, we explore for the set of k such that either 6k+1 or 6k-1 is not a prime. Our method provides a uniform formula for k that can sieve primes and twin primes as well. The uniform presents symmetry in terms of k that works as single index in sieving. We also propose a new conjecture that is equivalent to Twin Prime Conjecture but possibly be easier to approach by merely exploring of sole index in term of k. The uniform formula for prime sieving are as follows: k ∈ Sl ⇒ 6k−1 6∈ , where Sl = [−I]6I+1 = [I]6I−1\min([I]6I−1), I ∈ . k ∈ Sr ⇒ 6k + 1 6∈ , where Sr = [−I]6I−1 ∪ ([I]6I+1\min([I]6I+1)), I ∈ . © 2020, CC BY.

关键词： Number theory

来源：评论

学校读者我要写书评

暂无评论

Spectral-Spatial Weighted Sparse Nonnegative Tensor Factorization for Hyperspectral Unmixing

Spectral-Spatial Weighted Sparse Nonnegative Tensor Factoriz...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Shaoquan Zhang Guorong Zhang Chengzhi Deng Jun Li Shengqian Wang Jun Wang Antonio Plaza Jiangxi Province Key Laboratory of Water Information Cooperative Sensing and Intelligent Processing Nanchang Institute of Technology Nanchang China Guangdong Provincial Key Laboratory of Urbanization and Geo-simulation School of Geography and Planning Sun Yat-sen University Guangzhou China Hyperspectral Computing Laboratory Escuela Politécnica University of Extremadura Cáceres Spain

ISBN: (数字)9781728163741

ISBN: (纸本)9781728163758

Hyperspectral unmixing aims to decompose a hyperspectral image (HSI) into a collection of constituent materials, or end-members, and their corresponding abundance fractions. Recently, nonnegative tensor factorization (NTF)-based spectral unmixing methods have attracted significant attention owing to their outstanding performance when representing an HSI without any information loss. However, tensor factorization-based HSI methods do not fully exploit the spatial contextual information present in the scene. Besides, these approaches are sensitive to low signal-to-noise ratio (SNR) in HSIs. To address this limitation, we propose a new spectral-spatial weighted sparse nonnegative tensor factorization (SSWNTF) method to preserve the spatial details in the abundance maps via the spectral and spatial weighting factors. Our experiments with simulated data sets certified that the proposed method outperforms other advanced methods.

关键词： Hyperspectral imaging Tensors Signal to noise ratio Signal processing algorithms Matrix decomposition Sparse matrices Noise measurement

来源：评论

学校读者我要写书评

暂无评论

DeepACC:Automate Chromosome Classification based on Metaphase Images using Deep Learning Framework Fused with Prior Knowledge

arXiv

引用

arXiv 2020年

作者： Luo, Chunlong Yu, Tianqi Luo, Yufan Wang, Manqing Yu, Fuhai Li, Yinhao Tian, Chan Qiao, Jie Xiao, Li Key Laboratory of Intelligent Information Processing Advanced Computer Research Center Institute of Computing Technology Chinese Academy of Sciences Beijing China Peking University Third Hospital Beijing China School of Computer and Control Engineering University of Chinese Academy of China

Chromosome classification is an important but difficult and tedious task in karyotyping. Previous methods only classify manually segmented single chromosome, which is far from clinical practice. In this work, we propose a detection based method, DeepACC, to locate and fine classify chromosomes simultaneously based on the whole metaphase image. We firstly introduce the Additive Angular Margin Loss to enhance the discriminative power of model. To alleviate batch effects, we transform decision boundary of each class case-by-case through a siamese network which make full use of prior knowledges that chromosomes usually appear in pairs. Furthermore, we take the clinically seven group criterion as a prior knowledge and design an additional Group Inner-Adjacency Loss to further reduce inter-class similarities. 3390 metaphase images from clinical laboratory are collected and labelled to evaluate the performance. Results show that the new design brings encouraging performance gains comparing to the state-of-the-art baselines. Copyright © 2020, The Authors. All rights reserved.

关键词： Chromosomes

来源：评论

学校读者我要写书评

暂无评论

A budget constraint incentive mechanism in spatial-temporal mobile crowdsensing 21

A budget constraint incentive mechanism in spatial-temporal ...

引用

作者： Kong, Xujiao Li, Peng Zhang, Tao Tu, Meimei Liu, Qin College of Computer Science and Technology Wuhan University of Science and Technology China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System China Department of Computer Science New York Institute of Technology United States School of Cyber Science and Engineering Wuhan University China

ISBN: (纸本)9781728120584

Mobile crowdsensing is an effective way to collect sensing data about regions of interest. Effective incentive mechanisms are invaluable in mobile crowd sensing, for recruiting a number of mobile users to fulfill coverage requirement in the interested regions. In this paper, we exploit the potential of mobile users by designing a spatial-temporal crowd sensing incentive mechanism for smartphone users. We first use the logistic regression technique to mine user preferences from the user's historical data. Then, we propose a sub-module approximation algorithm to solve the participant recruitment problem, which is proved to be an NP-hard problem. Moreover, we design the winner auction algorithm (WAA) based on the reverse auction mechanism to solve the critical payment allocation problem. Finally, we demonstrate that our mechanism achieves truthfulness, individual rationality, and high computation efficiency through both theoretical analysis and experimental simulation. © 2019 IEEE.

关键词： Approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

Budget constraint roadside units placement for traffic flows monitoring system with reliability in vehicular networks 21

Budget constraint roadside units placement for traffic flows...

引用

作者： Jiang, Peng Li, Peng Zhang, Tao Huang, Weiyi He, Heng Nie, Lei Liu, Qin College of Computer Science and Technology Wuhan University of Science and Technology China Hubei Province Key Laboratory of Intelligent Information Processing Real-time Industrial System China Department of Computer Science New York Institute of Technology United States School of Cyber Science and Engineering Wuhan University China

ISBN: (纸本)9781728120584

In Traffic Flows Monitoring System (TFMS), the key problem is how to install Roadside Units (RSUs) reliably to monitor traffic flows with the constrained budget. The reliability of Traffic Flows Monitoring System(TFMS) is determined by the number of RSUs each traffic flow pass through, and the RSUs placement number is determined by the budget and the placement strategy. In this paper, we investigate the budget constraint RSUs placement problem for traffic flows monitoring system with reliability in vehicular networks. Given a budget constraint, the problem is how to install RSUs to ensure the reliability of TFMS, that is each traffic flow pass through RSUs as many as possible with the limited budget. We prove that this problem is NP-hard. Then, we propose two greedy algorithms to solve the problem according to the pigeonhole principle. Moreover, approximation ratios of proposed algorithms are given. Finally, we verify the feasibility of proposed algorithms through extensive experiments, and the results show that the proposed algorithms are superior to the other algorithms. © 2019 IEEE.

关键词： Reliability

来源：评论

学校读者我要写书评

暂无评论

Selective oxidation of benzyl alcohol to benzaldehyde using palladium nanoparticle-loaded poly(ionic liquid)s catalysts

引用

Molecular Catalysis 2025年 584卷

作者： Liu, Yaping Pan, Chao Qiu, Xiaomin Zhang, Hailin Feng, Haijun Tang, Yubao Shang, Zhijie Song, Hongbing College of Chemical Engineering Qingdao University of Science and Technology Zhengzhou Road No.53 Qingdao 266042 China China University of Petroleum (Beijing) School of Chemical Engineering and Environment State Key Laboratory of Heavy Oil Processing Beijing 102249 China School of Computer and Software Shenzhen Institute of Information Technology Guangdong Shenzhen 518172 China College of Chemistry and Molecular Engineering Qingdao University of Science and Technology Zhengzhou Road No.53 Qingdao 266042 China

The conversion of readily accessible chemicals into high-value-added products is a key process in industrial chemistry. This research showcases an efficient transformation of benzyl alcohol to benzaldehyde utilizing poly(ionic liquid)s (PILs) supported Pd-based catalysts. The catalyst's properties were thoroughly characterized using FT-IR, SEM, TEM, XPS, and TG, confirming the successful fabrication of stable Pd/PILs catalysts. The porous architecture of the PILs material enhances palladium nanoparticle adhesion, while its structure promotes intimate contact between the catalyst and substrate, facilitating the oxidation process. With just 0.1 g of 1 % Pd/PIL-2 catalyst, the reaction at 110 °C, 4 MPa O2 for 4 h achieve a 82.16 % conversion of benzyl alcohol with absolute selectivity to benzaldehyde. Theoretical calculations elucidated the interactions between Pd6 clusters, PIL, and benzyl alcohol. Furthermore, the Fukui function and optimized electrostatic potential diagrams identified reactive sites, providing insights into the potential reaction mechanism.

关键词： Benzaldehyde Benzyl alcohol Green oxidation Poly(ionic liquid)s Theoretical calculations

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：