检索结果-南通市图书馆

Editorial for Special Issue on Multi-modal Representation Learning

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Machine Intelligence Research 2024年第4期21卷 615-616页

作者： Deng-Ping Fan Nick Barnes ming-ming cheng Luc Van Gool Nankai University China&ETH ZirichSwitzerland Australian National University Australia Nankai University China ETH Zirich Switzerland

The past decade has witnessed the impressive and steady development of single-modal AI technologies in several fields,thanks to the emergence of deep *** studied,however,is multi-modal AI-commonly considered the next generation of AI-which utilizes complementary context concealed in different-modality inputs to improve *** naturally learn to form a global concept from multiple modalities(i.e.,sight,hearing,touch,smell,and taste),even when some are incomplete or ***,in addition to the two popular modalities(vision and language),other types of data such as depth,infrared information,and events are also important for multi-modal learning in real-world scenes.

关键词： modal utilize incomplete

D2ANet:Difference-aware attention network for multi-level change detection from satellite imagery

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computational Visual Media 2023年第3期9卷 563-579页

作者： Jie Mei Yi-Bo Zheng ming-ming cheng TMCC CSNankai UniversityTianjin 300350China State Key Laboratory of Earth Surface Processes and Resource Ecology Faculty of Geographical ScienceBeijing Normal UniversityBeijing 100875China

Recognizing dynamic variations on the ground,especially changes caused by various natural disasters,is critical for assessing the severity of the damage and directing the disaster ***,current workflows for disaster assessment usually require human analysts to observe and identify damaged buildings,which is labor-intensive and unsuitable for large-scale disaster *** this paper,we propose a difference-aware attention network(D2ANet)for simultaneous building localization and multi-level change detection from the dual-temporal satellite *** the differences in different channels in the features of pre-and post-disaster images,we develop a dual-temporal aggregation module using paired features to excite change-sensitive channels of the features and learn the global change *** the nature of building damage caused by disasters is diverse in complex environments,we design a difference-attention module to exploit local correlations among the multi-level changes,which improves the ability to identify damage on different *** experiments on the large-scale building damage assessment dataset xBD demonstrate that our approach provides new state-of-the-art *** code is publicly available at https://***/mj129/D2ANet.

关键词： change detection building localization sate-llite imagery dual-temporal aggregation difference attention

Visual attention network

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computational Visual Media 2023年第4期9卷 733-752页

作者： Meng-Hao Guo cheng-Ze Lu Zheng-Ning Liu ming-ming cheng Shi-Min Hu Department of Computer Science Tsinghua UniversityBeijingChina Nankai University TianjinChina Fitten Tech BeijingChina

While originally designed for natural language processing tasks,the self-attention mechanism has recently taken various computer vision areas by ***,the 2D nature of images brings three challenges for applying self-attention in computer vision:(1)treating images as 1D sequences neglects their 2D structures;(2)the quadratic complexity is too expensive for high-resolution images;(3)it only captures spatial adaptability but ignores channel *** this paper,we propose a novel linear attention named large kernel attention(LKA)to enable self-adaptive and long-range correlations in self-attention while avoiding its ***,we present a neural network based on LKA,namely Visual Attention Network(VAN).While extremely simple,VAN achieves comparable results with similar size convolutional neural networks(CNNs)and vision transformers(ViTs)in various tasks,including image classification,object detection,semantic segmentation,panoptic segmentation,pose estimation,*** example,VAN-B6 achieves 87.8%accuracy on ImageNet benchmark,and sets new state-of-the-art performance(58.2%PQ)for panoptic ***,VAN-B2 surpasses Swin-T 4%mloU(50.1%vs.46.1%)for semantic segmentation on ADE20K benchmark,2.6%AP(48.8%vs.46.2%)for object detection on COCO *** provides a novel method and a simple yet strong baseline for the *** code is available at https://***/Visual-Attention-Network.

关键词： vision backbone deep learning ConvNets attention

SAM struggles in concealed scenes—empirical study on “Segment Anything”

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2023年第12期66卷 278-280页

作者： Ge-Peng JI Deng-Ping FAN Peng XU Bowen ZHOU ming-ming cheng Luc VAN GOOL School of Computing Australian National University Computer Vision Lab(CVL) ETH Zurich Department of Electronic Engineering Tsinghua University College of Computer Science Nankai University

Large models open up new opportunities for artificial intelligence. In the past few months, there has been a boom in training foundation models on the vast linguistic corpus to produce amazing applications, e.g., Chat GPT, *** natural language processing and multimodal learning communities have been revolutionized. Large models’ capacity for generalization and emergent makes it easy for users to believe that large models can solve anything.

关键词：

An improved initial rotor position estimation method using high-frequency pulsating voltage injection for PMSM

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Defence Technology（防务技术） 2024年第3期33卷 19-29页

作者： Yang Jiang ming cheng School of Electrical Engineering Southeast UniversityNanjing 210096China

High frequency pulsating voltage injection method is a good candidate for detecting the initial rotor position of permanent magnet synchronous ***,traditional methods require a large number of filters,which leads to the deterioration of system stability and dynamic *** order to solve these problems,a new signal demodulation method is proposed in this *** proposed new method can directly obtain the amplitude of high-frequency current,thus eliminating the use of filters,improving system stability and dynamic performance and saving the work of adjusting filter *** addition,a new magnetic polarity detection method is proposed,which is robust to current measurement ***,experiments verify the effectiveness of the method.

关键词： Initial position detection Signal demodulation algorithm Magnetic polarity detection Filter elimination

维普期刊数据库

Analytical Solution of a Fractional-slot Double-layer-winding Open-slot Vernier Permanent Magnet Machine with Tooth Tips

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Electrical Engineering 2024年第2期10卷 44-58页

作者： Weibing Wang ming cheng School of Electric Power Engineering Nanjing Institute of TechnologyNanjing 211167China School of Electrical Engineering Southeast UniversityNanjing 210096China

An analytical solution(ANA)for a fractional-slot double-layer-winding open-slot vernier permanent magnet(VPM)machine with tooth tips is *** vector potential equations are analytically solved using the technique of variable separation in four subdomains in a two-dimensional polar coordinate *** on the solved magnetic vector potential,the flux density distribution,torque,flux linkage,inductance,electromotive force(EMF)and power factor are analytically *** 18-slot/32-rotor-pole prototype is analyzed,and the results match well with the finite element analysis(FEA),which validates that the ANA consumes less time than ***,the tooth tips are optimized using the ANA to improve the average ***,the ANA can be used to evaluate the demagnetization withstand capabilities of permanent *** material utilization,slot-filling factor,EMF,and torque are compared between the models with three and four ***,an experimental prototype is constructed and tested,and the results validate the ANA.

关键词： Analytical solution magnetic field vernier permanent magnet machine subdomain optimization demagnetization

Classification of complete 3-dimensional self-shrinkers in the Euclidean space R^(4)

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China Mathematics 2024年第4期67卷 873-882页

作者： Qing-ming cheng Zhi Li Guoxin Wei Department of Applied Mathematics Faculty of ScienceFukuoka UniversityFukuoka 814-0180Japan College of Mathematics and Information Science Henan Normal UniversityXinxiang 453007China School of Mathematical Sciences South China Normal UniversityGuangzhou 510631China

In this paper,we completely classify 3-dimensional complete self-shrinkers with the constant norm S of the second fundamental form and the constant f3in the Euclidean space R^(4),where hij’s are components of the sec... 详细信息

关键词： mean curvature ow self-shrinker the generalized maximum principle

维普期刊数据库

Attention mechanisms in computer vision:A survey

在线全文

学校读者我要写书评

暂无评论

Computational Visual Media 2022年第3期8卷 331-368页

作者： Meng-Hao Guo Tian-Xing Xu Jiang-Jiang Liu Zheng-Ning Liu Peng-Tao Jiang Tai-Jiang Mu Song-Hai Zhang Ralph R.Martin ming-ming cheng Shi-Min Hu BNRist Department of Computer Science and TechnologyTsinghua UniversityBeijing 100084China TKLNDST College of Computer ScienceNankai UniversityTianjin 300350China School of Computer Science and Informatics Cardiff UniversityCardiffUK

Humans can naturally and effectively find salient regions in complex *** by this observation,attention mechanisms were introduced into computer vision with the aim of imitating this aspect of the human visual *** an attention mechanism can be regarded as a dynamic weight adjustment process based on features of the input *** mechanisms have achieved great success in many visual tasks,including image classification,object detection,semantic segmentation,video understanding,image generation,3D vision,multimodal tasks,and self-supervised *** this survey,we provide a comprehensive review of various attention mechanisms in computer vision and categorize them according to approach,such as channel attention,spatial attention,temporal attention,and branch attention;a related repository https://***/MenghaoG uo/Awesome-Vision-Attentions is dedicated to collecting related *** also suggest future directions for attention mechanism research.

关键词： attention transformer computer vision deep learning salience

维普期刊数据库

Planning of DC Electric Spring with Particle Swarm Optimization and Elitist Non-dominated Sorting Genetic Algorithm

在线全文

学校读者我要写书评

暂无评论

CSEE Journal of Power and Energy Systems 2024年第2期10卷 574-583页

作者： Qingsong Wang Siwei Li Hao Ding ming cheng Giuseppe Buja School of Electrical Engineering and Jiangsu Provincial Key Laboratory of Smart Grid Technology and Equipment Southeast UniversityNanjing 210096China School of Software Engineering Southeast universitySuzhou 215123China

This paper addresses the planning problem of parallel DC electric springs (DCESs). DCES, a demand-side management method, realizes automatic matching of power consumption and power generation by adjusting non-critical load (NCL) and internal storage. It can offer higher power quality to critical load (CL), reduce power imbalance and relieve pressure on energy storage systems (RESs). In this paper, a planning method for parallel DCESs is proposed to maximize stability gain, economic benefits, and penetration of RESs. The planning model is a master optimization with sub-optimization to highlight the priority of objectives. Master optimization is used to improve stability of the network, and sub-optimization aims to improve economic benefit and allowable penetration of RESs. This issue is a multivariable nonlinear mixed integer problem, requiring huge calculations by using common solvers. Therefore, particle Swarm optimization (PSO) and Elitist non-dominated sorting genetic algorithm (NSGA-II) were used to solve this model. Considering uncertainty of RESs, this paper verifies effectiveness of the proposed planning method on IEEE 33-bus system based on deterministic scenarios obtained by scenario analysis.

关键词： DC distribution network DC electric spring non-dominated sorting genetic algorithm particle swarm optimization renewable energy source