检索结果-南通市图书馆

study of Human Action Recognition Based on Improved spatio-temporal Features

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

International Journal of Automation and computing 2014年第5期11卷 500-509页

作者： Xiao-Fei Ji Qian-Qian Wu Zhao-Jie Ju yang-yang Wang school of Automation Shenyang Aerospace University school of Computing University of Portsmouth

Most of the exist action recognition methods mainly utilize spatio-temporal descriptors of single interest point while ignoring their potential integral information, such as spatial distribution information. By combining local spatio-temporal feature and global positional distribution information(PDI) of interest points, a novel motion descriptor is proposed in this paper. The proposed method detects interest points by using an improved interest point detection method. Then, 3-dimensional scale-invariant feature transform(3D sIFT) descriptors are extracted for every interest point. In order to obtain a compact description and efficient computation, the principal component analysis(PCA) method is utilized twice on the 3D sIFT descriptors of single frame and multiple frames. simultaneously, the PDI of the interest points are computed and combined with the above features. The combined features are quantified and selected and finally tested by using the support vector machine(sVM) recognition algorithm on the public KTH dataset. The testing results have showed that the recognition rate has been significantly improved and the proposed features can more accurately describe human motion with high adaptability to scenarios.

关键词： Action recognition spatio-temporal interest points 3-dimensional scale-invariant feature transform (3D sIFT) positional distribution information dimension reduction

Research on the effect of Reynolds correlation in natural convection film condensation

在线全文

学校读者我要写书评

暂无评论

Nuclear science and Techniques 2017年第6期28卷 169-178页

作者： lei Wu Hai-Jun Jia Xi-Zhen Ma yang liu Xing-Tuan yang Jun Wang Institute of Nuclear and New Energy Technology Collaborative Innovation Center of Advanced Nuclear Energy TechnologyKey Laboratory of Advanced Reactor Engineering and Safety of Ministry of EducationTsinghua University Engineering Physics Institute University of Wisconsin Madison

Film condensation is a vital phenomenon in the nuclear engineering applications,such as the gas-steam pressurizer design,and heat removing on containment in the case of postulated *** number in film condensation can be calculated from either the mass relation or the energy relation,but few researches have distinguished the difference between them at *** paper studies the effect of Reynolds correlation in the natural convection film condensation on the outer *** general forms of the heat transfer coefficient correlation of film condensation are developed in different flow *** simultaneously solving a set of the heat transfer coefficient correlations with Re_(mass) and Re_(energy),the general expressions for Re_(mass) and Re_(energy) and the relation between the corresponding heat transfer coefficients are *** the laminar and wavefree flow regime,Re_(mass) and Re_(energy) are equivalent,while in the laminar and wavy flow regime,Re_(mass) is much smaller than Re_(energy),and the deviation of the corresponding average heat transfer coefficients is about 30% at the *** the turbulent flow regime,the relation of Re_(mass) and Re_(energy)is greatly influenced by Prandtl *** relative deviation of their average heat transfer coefficients is the nonlinear function of Reynolds number and Prandtl *** with experimental results,the heat transfer coefficient calculated from Re_(energy) is more accurate.

关键词： Film condensation Reynolds correlation Heat transfer coefficient Natural convection

Audio-Text Multimodal speech Recognition via Dual-Tower Architecture for Mandarin Air Traffic Control Communications

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第3期78卷 3215-3245页

作者： shuting Ge Jin Ren Yihua shi Yujun Zhang shunzhi yang Jinfeng yang school of Computer science and software Engineering University of Science and Technology LiaoningAnshan114051China Institute of Applied Artificial Intelligence of the Guangdong-Hong Kong-Macao Greater Bay Area Shenzhen Polytechnic UniversityShenzhen518055China shenzhen Institutes of Advanced Technology Chinese Academy of SciencesShenzhen518055China Industrial Training Centre Shenzhen Polytechnic UniversityShenzhen518055China

In air traffic control communications (ATCC), misunderstandings between pilots and controllers could result in fatal aviation accidents. Fortunately, advanced automatic speech recognition technology has emerged as a promising means of preventing miscommunications and enhancing aviation safety. However, most existing speech recognition methods merely incorporate external language models on the decoder side, leading to insufficient semantic alignment between speech and text modalities during the encoding phase. Furthermore, it is challenging to model acoustic context dependencies over long distances due to the longer speech sequences than text, especially for the extended ATCC data. To address these issues, we propose a speech-text multimodal dual-tower architecture for speech recognition. It employs cross-modal interactions to achieve close semantic alignment during the encoding stage and strengthen its capabilities in modeling auditory long-distance context dependencies. In addition, a two-stage training strategy is elaborately devised to derive semantics-aware acoustic representations effectively. The first stage focuses on pre-training the speech-text multimodal encoding module to enhance inter-modal semantic alignment and aural long-distance context dependencies. The second stage fine-tunes the entire network to bridge the input modality variation gap between the training and inference phases and boost generalization performance. Extensive experiments demonstrate the effectiveness of the proposed speech-text multimodal speech recognition method on the ATCC and AIsHEll-1 datasets. It reduces the character error rate to 6.54% and 8.73%, respectively, and exhibits substantial performance gains of 28.76% and 23.82% compared with the best baseline model. The case studies indicate that the obtained semantics-aware acoustic representations aid in accurately recognizing terms with similar pronunciations but distinctive semantics. The research provides a novel modeling pa

关键词： speech-text multimodal automatic speech recognition semantic alignment air traffic control communications dual-tower architecture

Recrystallization Behavior of Deformed Austenite in High strength Microalloyed Pipeline steel

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Iron and steel Research International 2009年第1期16卷 75-80页

作者： yang Jing-hong lIU Qing-you sUN Dong-bai lI Xiang-yang school of Material science and Engineering University of Science and Technology Beijing Beijing 100083 China state Key laboratory of Advanced steel Processes and Products China Iron and Steel Research Institute GroupBeijing 100081 China

Using methods of single-hit hot compression and stress relaxation after deformation on a Gleeble 1500D thermomechanical simulator, the curves of flow stress and stress relaxation, the microstructure and the recrystallization behavior of Nb-V-Ti high strength microalloyed low carbon pipeline steel were studied, and the influence of the thermomechanical treatment parameters on dynamic and static recrystallization of the steel was investigated. It was found that microalloying elements improved the deformation activation energy and produced a retardation of the recrystallization due to the solid solution and precipitation pinning. The deformation conditions such as deformation temperature, strain, and strain rate influenced the recrystallization kinetics and the microstructure respectively. Equations obtained can be used to valuate and predict the dynamic and static recrystallizations.

关键词： dynamic recrystallization static recrystallization microalloyed steel austenite

CTsN: Predicting cloth deformation for skeleton-based characters with a two-stream skinning network

在线全文

学校读者我要写书评

暂无评论

Computational Visual Media 2024年第3期10卷 471-485页

作者： Yudi li Min Tang Yun yang Ruofeng Tong shuangcai yang Yao li Bailin An Qilong Kou College of Computer science and Technology Zhejiang UniversityHangzhou 310058China Aurora studios TencentShenzhen 518057China

We present a novel learning method using a two-stream network to predict cloth deformation for skeleton-based *** characters processed in our approach are not limited to humans,and can be other targets with skeleton-based representations such asfish or *** use a novel network architecture which consists of skeleton-based and mesh-based residual networks to learn the coarse features and wrinkle features forming the overall residual from the template cloth *** network may be used to predict the deformation for loose or tight-fitting *** memory footprint of our network is low,thereby resulting in reduced computational *** practice,a prediction for a single cloth mesh for a skeleton-based character takes about 7 ms on an nVidia GeForce RTX 3090 *** to prior methods,our network can generate finer deformation results with details and wrinkles.

关键词： cloth deformation learning network skinning

Construction and application of high-quality genome-scale metabolic model of Zymomonas mobilis to guide rational design of microbial cell factories

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

synthetic and systems Biotechnology 2023年第3期8卷 498-508页

作者： Yalun Wu Qianqian Yuan Yongfu yang Defei liu shihui yang Hongwu Ma state Key laboratory of Biocatalysis and Enzyme Engineering School of Life SciencesHubei UniversityWuhan430062HubeiChina Biodesign Center Key Laboratory of Systems Microbial BiotechnologyTianjin Institute of Industrial BiotechnologyChinese Academy of SciencesTianjin300308China Hubei Key laboratory of Applied Mathematics Faculty of Mathematics and StatisticsHubei UniversityWuhan430062HubeiChina Artificial Intelligence and Knowledge Engineering lab School of Computer Science and Information EngineeringHubei UniversityWuhan430062HubeiChina

High-quality genome-scale metabolic models(GEMs)could play critical roles on rational design of microbial cell factories in the classical Design-Build-Test-learn cycle of synthetic biology *** of the constant establishment and update of GEMs for model microorganisms such as Escherichia coli and saccharomyces cerevisiae,high-quality GEMs for non-model industrial microorganisms are still *** mobilis *** ZM4 is a non-model ethanologenic microorganism with many excellent industrial characteristics that has been developing as microbial cell factories for biochemical *** five GEMs of *** have been constructed,these models are either generating ATP incorrectly,or lacking information of plasmid genes,or not providing standard format *** this study,a high-quality GEM iZM516 of *** ZM4 was *** information from the improved genome annotation,literature,datasets of Biolog Phenotype Microarray studies,and recently updated Gene-Protein-Reaction information was combined for the curation of ***,516 genes,1389 reactions,1437 metabolites,and 3 cell compartments are included in iZM516,which also had the highest MEMOTE score of 91%among all published GEMs of *** growth was then predicted by iZM516,which had 79.4%agreement with the experimental results of the substrate *** addition,the potential endogenous succinate synthesis pathway of *** ZM4 was proposed through simulation and analysis using ***,metabolic engineering strategies to produce succinate and 1,4-butanediol(1,4-BDO)were designed and then simulated under anaerobic condition using *** results indicated that 1.68 mol/mol succinate and 1.07 mol/mol 1,4-BDO can be achieved through combinational metabolic engineering strategies,which was comparable to that of the model species *** study thus not only established a high-quality GEM iZM516 to help understand and design microbial cell fac

关键词： Genome-scale metabolic models(GEMss) Non-model industrial microorganism Zymomonas mobilis Biolog phenotype microarray succinate 1,4-Butanediol

Research on Improving Artistry of Exhibitions in History Museums in China

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Contemporary social sciences 2024年第2期9卷 85-96页

作者： yang Yuli yang Xiannong sichuan Academy of social sciences ChengduSichuan610071China

Chinese civilization,with its long and continuous history and rich cultural heritage,plays a central role in China’s dialogue with other ***,it is necessary to collect and refine the defining symbols and best elements of Chinese culture and showcase them to the world;develop discourse and narrative systems with Chinese characteristics,better tell China’s stories,and make China’s voice *** effort can help Chinese civilization shine globally,interact with other civilizations,and promote its communication and influence *** China,history museums,as physical carriers of Chinese civilization,are an important component in developing Chinese discourse and narrative systems and an important channel to better tell China’s stories and make China’s voice *** the artistry of museum exhibitions caters to the public’s growing demand for a more enriching cultural experience and substantially promotes Chinese culture on a global *** the communication of Chinese civilization as the main focal point,this study investigated the current issues related to the artistry of history museum exhibitions in China and defined the artistry of history museum exhibitions and their *** on an in-depth analysis of the artistry of historical museum exhibitions within China,this paper enumerated the areas where improvements could be made to enhance exhibition artistry,intending to promote the communication of Chinese civilization.

关键词： history museums artistry aesthetics communication of Chinese culture Chinese civilization

Advancements in theory of GHG observation from space

在线全文

学校读者我要写书评

暂无评论

science Bulletin 2016年第5期61卷 349-352页

作者： Yi liu Dongxu yang Key laboratory of Middle Atmosphere and Global Environment Observation Institute of Atmospheric Physics (IAP) Chinese Academy of Sciences (CAS)

As a large developing country,China has the highest level of greenhouse gas(GHG)*** Chinese government is seeking sustainable development and trying to reduce GHG *** the scientific perspective,there

关键词：温室气体排放气体观测二氧化碳排放量发展中国家空间可持续发展中国政府气候变化

Dynamic slAM Visual Odometry Based on Instance segmentation:A Comprehensive Review

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第1期78卷 167-196页

作者： Jiansheng Peng Qing yang Dunhua Chen Chengjun yang Yong Xu Yong Qin College of Automation Guangxi University of Science and TechnologyLiuzhou545000China Department of Artificial Intelligence and Manufacturing Hechi UniversityHechi547000China

Dynamic simultaneous localization and Mapping(slAM)in visual scenes is currently a major research area in fields such as robot navigation and autonomous ***,in the face of complex real-world envi-ronments,current dynamic slAM systems struggle to achieve precise localization and map *** the advancement of deep learning,there has been increasing interest in the development of deep learning-based dynamic slAM visual odometry in recent years,and more researchers are turning to deep learning techniques to address the challenges of dynamic *** to dynamic slAM systems based on deep learning methods such as object detection and semantic segmentation,dynamic slAM systems based on instance segmentation can not only detect dynamic objects in the scene but also distinguish different instances of the same type of object,thereby reducing the impact of dynamic objects on the slAM system’s *** article not only introduces traditional dynamic slAM systems based on mathematical models but also provides a comprehensive analysis of existing instance segmentation algorithms and dynamic slAM systems based on instance segmentation,comparing and summarizing their advantages and *** comparisons on datasets,it is found that instance segmentation-based methods have significant advantages in accuracy and robustness in dynamic ***,the real-time performance of instance segmentation algorithms hinders the widespread application of dynamic slAM *** recent years,the rapid development of single-stage instance segmentationmethods has brought hope for the widespread application of dynamic slAM systems based on instance ***,possible future research directions and improvementmeasures are discussed for reference by relevant professionals.

关键词： Dynamic slAM instance segmentation visual odometry