检索结果-内蒙古大学图书馆

Causal Attention Transformer for Video Text Retrieval

IET Image Processing 2025年第1期19卷

作者： Lan, Hua Lv, Chaohui School of Information and Communication Engineering Communication University of China Beijing China Key Laboratory of Acoustic Visual Technology and Intelligent Control System Ministry of Culture and Tourism Beijing China

In the metaverse, video text retrieval is an urgent and challenging need for users in social entertainment. The current attention-based video text retrieval models have not fully explored the interaction between video and text, and only brute force feature embedding. Moreover, Due to the unsupervised nature of attention weight training, existing models have weak generalization performance for dataset bias. Essentially, the model learns that false relevant information in the data is caused by confounding factors. Therefore, this article proposes a video text retrieval method based on causal attention transformer. Assuming that the confounding factors affecting the performance of video text retrieval all come from the dataset, a structural causal model that conforms to the video text retrieval task is constructed, and the impact of confounding effects during data training is reduced by adjusting the front door. In addition, we use causal attention transformer to construct a causal inference network to extract causal features between video text pairs, and replace the similarity statistical probability with causal probability in the video text retrieval framework. Experiments are conducted on the MSR-VTT, MSVD, and LSMDC datasets, which proves the effectiveness of the retrieval model proposed in this paper. © 2025 The Author(s). IET Image Processing published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology.

关键词： Interactive computer graphics

来源：评论

学校读者我要写书评

暂无评论

Design of an electronic device for detection of exhaled gas concentration 5

Design of an electronic device for detection of exhaled gas ...

引用

2024 5th International Conference on Electrical, Electronic Information and communication Engineering, EEICE 2024

作者： Fan, Chuanxiu Liu, Xue Yu, Zhichao Du, Changsong Jia, Shengde Liu, Qing Yan, Pengbo Tianjin Key Laboratory of Film Electronic and Communication Device Tianjin University of Technology Tianjin300384 China Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control Tianjin University of Technology Tianjin300384 China Tianjin Chest Hospital Tianjin300384 China

To enable preliminary diagnosis of various diseases in the human body, detecting the concentrations of targeted components in exhaled gases is an effective way without invasive diagnosis. An exhaled gas concentration detection device is proposed in this paper. Firstly, this device employs a high-accuracy analog front end (AFE) for transmitting the concentrations of targeted components to an electronic voltage signal. The core circuit of AFE is a high-precision and low-current constant current source. Secondly, a heating circuit with controllable temperature is also designed to provide an appropriate operating temperature for different types of gas sensor materials. Thirdly, the system applies a microcontroller to directly read multiple-channel gas concentrations and independently control multiple heating circuits. The performance of the device has been validated through simulations. © Published under licence by IOP Publishing Ltd.

关键词： Computer resource management

来源：评论

学校读者我要写书评

暂无评论

Cubesat Optical Crosslink 37

Cubesat Optical Crosslink

引用

Free-Space Laser communications XXXVII 2025

作者： Rose, T.S. Berman, A. Werner, N. Swigart, J. McDonald, E. Lampen, S. Rodriguez, S. Grasso, S. Fortuno, C. Martirosyan, A. Crain, W. Moreno, N. Kinum, G. Electronics and Photonics Laboratory United States xLabs United States Guidance & Control Subdivision Communication Sys & Agile Proc Subdivision Sensors System Subdivision The Aerospace Corporation P.O. Box 92957 Los AngelesCA United States

ISBN: (纸本)9781510684584

A pair of 6U cubesats was recently launched into low-earth orbit (LEO) to demonstrate optical crosslink capability for this class of small vehicles. Over the past several years the Aerospace Corporation has routinely performed one-way optical communication downlinks from LEO cubesats using the attitude control system of the space vehicle to point a body-fixed laser transmitter. For this latest mission, each satellite incorporates a 2.5U lasercom system consisting of a 2W 1064-nm transmitter, a wide field of view Si detector array, an Si avalanche photodiode (APD) communication detector, an InGaAs quad cell, and a fast-steering mirror (FSM) to enable bidirectional communications and independent steering of the transmitter from the vehicle. Data transmission from 50 - 300 Mbps OOK are planned over an intersatellite range of 500 – 1500 km. Pointing alignment, presently being optimized, and initial communication results will be discussed. © 2025 SPIE.

关键词： Silicon detectors

来源：评论

学校读者我要写书评

暂无评论

Research on Timbre Evaluation Method for Oral Literature

Research on Timbre Evaluation Method for Oral Literature

引用

2023 International Conference on Culture-Oriented Science and Technology, CoST 2023

作者： Bai, Shilei Guo, Shizhen Hu, Chaoyu Zhang, Mengfei Gao, Ying Communication University of China State Key Laboratory of Media Convergence and Communication Beijing China Key Laboratory of Acoustic Visual Technology and Intelligent Control System Ministry of Culture and Tourism Beijing China Beijing China Center for Ethnic and Folk Literature and Art Development Ministry of Culture and Tourism Beijing China

ISBN: (纸本)9798350357998

The oral story culture of ethnic folklore is one of the important components of traditional Chinese culture, and it is of key importance to study the timbre evaluation methods of this type of audio after digital capture. This paper uses subjective timbre evaluation experiments to explore the subjective perceptual characteristics of audio signals of oral story, extracts the objective acoustic parameters of audio timbre based on human vocal principles, auditory perceptual characteristics and speech time domain features, and conducts research on objective timbre evaluation methods based on support vector regression (SVR), random forest regression (RFR), convolutional neural networks (CNN) and long short-term memory networks (LSTM). The results show that the use of feature extraction and non-linear algorithms has good results in the evaluation of oral story timbre. © 2023 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Optimal controller Design for Non-Affine Nonlinear Power systems with Static Var Compensators for Hybrid UAVs

引用

Tsinghua Science and Technology 2022年第1期27卷 196-206页

作者： Yanchu Li Qingqing Ding Shufang Li Stanimir Valtchev Beijing Key Laboratory of Network System Architecture and Convergence Beijing Laboratory of Advanced Information Networkand School of Information&Communication EngineeringBeijing University of Posts and TelecommunicationsBeijing 100876China State Key Laboratory of Control and Simulation of Power System and Generation Equipments Tsinghua UniversityBeijing 100084China the Nova School of Science and Technology(FCT/UNL) Caparica 2829-516LisbonPortugal Technical University of Sofia(TUS) Sofia 2125Bulgaria

A generalized non-affine nonlinear power system model is presented for a single machine bus power system with a Static Var Compensator(SVC)or State Var system(SVS)for hybrid Unmanned Aerial Vehicles(UAVs).The model is constructed by differential algebraic equations on the MATLAB-Simulink platform with the programming technique of its *** the inverse system method and the Linear Quadratic Regulation(LQR),an optimized SVC controller is *** simulations under three fault conditions show that the proposed controller can effectively improve the power system transient performance.

关键词： Static Var Compensator(SVC) Unmanned Aerial Vehicles(UAV) power system non-affine nonlinear control inverse system method Linear Quadratic Regulation(LQR)

来源：评论

学校读者我要写书评

暂无评论

Boosting Unsupervised Monocular Depth Estimation with Auxiliary Semantic Information

引用

China communications 2021年第6期18卷 228-243页

作者： Hui Ren Nan Gao Jia Li State Key Laboratory of Media Convergence and Communication、Key Laboratory of Acoustic Visual Technology and Intelligent Control System Ministry of Culture and Tourism(Communication University of China)、Beijing Key Laboratory of Modern Entertainment Technology(Communication University of China)、School of Information and Communication EngineeringCommunication University of China.No.1Dingfuzhuang StreetChaoyang DistrictBeijing100024China

Learning-based multi-task models have been widely used in various scene understanding tasks,and complement each other,i.e.,they allow us to consider prior semantic information to better infer *** boost the unsupervised monocular depth estimation using semantic segmentation as an auxiliary *** address the lack of cross-domain datasets and catastrophic forgetting problems encountered in multi-task training,we utilize existing methodology to obtain redundant segmentation maps to build our cross-domain dataset,which not only provides a new way to conduct multi-task training,but also helps us to evaluate results compared with those of other *** addition,in order to comprehensively use the extracted features of the two tasks in the early perception stage,we use a strategy of sharing weights in the network to fuse cross-domain features,and introduce a novel multi-task loss function to further smooth the depth *** experiments on KITTI and Cityscapes datasets show that our method has achieved state-of-the-art performance in the depth estimation task,as well improved semantic segmentation.

关键词： unsupervised monocular depth estimation semantic segmentation multi-task model

来源：评论

学校读者我要写书评

暂无评论

A Classification and Recognition Model of Distributed Resources Based on Feature Extraction

A Classification and Recognition Model of Distributed Resour...

引用

2023 IEEE International Conference on Energy Technologies for Future Grids, ETFG 2023

作者： Zhu, Yu Yang, Le Yang, Xizai Lu, Jiaxin Wang, Yuqing Wang, Fei State Grid Shaanxi Electric Power Co. Ltd. Information and Communication Company Information and Communication Technology R & D Center Xi'an710048 China State Key Laboratory of Power System Operation and Control Tsinghua University Beijing100084 China

ISBN: (纸本)9781665471640

The extensive integration of distributed resources such as distributed photovoltaic system and electric vehicles enhances the uncertainty of the load side greatly. Corresponding demand response strategies can be developed for different distributed resource types and characteristics of households' load, which is of great significance for new energy consumption and stable operation of the power system. However, only the net load power of households can be obtained through smart meters instead of the distributed resource types of households. Based on this, a distributed resource classification and identification model based on feature extraction is proposed in this paper, and effectively solves the problems of low accuracy and strong data dependence of existing recognition methods. Firstly, a generalized weather class generation algorithm based on clustering and voting is established, which is used to determine the weather class of each day to provide a basis for the following feature extraction. Then, based on the typical net load profiles under different generalized weather classes, a two-stage feature extraction and a classification identification model based on integrated learning algorithms are established to identify whether a user contains DPVS and EV, respectively. Finally, based on the category labels of each user for each stage, the final classification of the category to which the user belongs is carried out. Simulation experiments show that the recognition model built using the typical features extracted in the paper has good recognition accuracy. © 2023 IEEE.

关键词： classification and recognition Distributed photovoltaics system electric vehicles ensemble learning feature extraction

来源：评论

学校读者我要写书评

暂无评论

The Regional Distributed PV Ultra-short-term Power Forecasting Based on Static-dynamic Spatiotemporal Correlation Modeling

The Regional Distributed PV Ultra-short-term Power Forecasti...

引用

2023 IEEE International Conference on Energy Technologies for Future Grids, ETFG 2023

作者： Zhu, Yu Yang, Le Yang, Xizai Xu, Fei Su, Zinuo Zhen, Zhao Information and Communication Technology R & D Center State Grid Shaanxi Electric Power Co. Ltd. Information and Communication Company Xi'an710048 China State Key Laboratory of Power System Operation and Control Tsinghua University Beijing100084 China

ISBN: (纸本)9781665471640

Accurate prediction of distributed photovoltaic power can help the arrange the scheduling plan reasonably to Maintain the safe and stable operation of the distribution network. However, distributed photovoltaic power generation exists lack of meteorological data and real-time monitoring data, the distribution range is large and dispersed, the installed capacity is relatively small and so on, the centralized photovoltaic power prediction method is not applicable to distributed photovoltaic power prediction, so it is necessary to carry out a regional power prediction study for distributed photovoltaic. Distributed PV is located in close proximity, in a similar external environment, and the power output between stations has strong spatial and temporal correlation, which can be captured to improve the accuracy of power forecasting. To this end, a regional distributed PV power prediction model based on static-dynamic spatiotemporal correlation modeling is proposed. The k-means is firstly used to cluster the regional distributed photovoltaic sites into several sub-regions, according to the geographical location and output characteristics that reflect the long-term static correlation between power stations. Then, graph convolutional neural network are applied to capture the dynamic correlation between subregions according to the power. In this way, the static and dynamic correlation are effectively considered in power prediction modeling, and the prediction accuracy has been improved. The superiority of the proposed method is verified by a real world dataset in China. © 2023 IEEE.

关键词： distributed photovoltaic graph convolution Regional power prediction

来源：评论

学校读者我要写书评

暂无评论

A novel 2 × 1 UWB-MIMO flower bouquet shaped antenna using CSRR reducing mutual coupling for wireless communication systems

A novel 2 × 1 UWB-MIMO flower bouquet shaped antenna using ...

引用

2024 International Conference on Circuit, systems and communication, ICCSC 2024

作者： Dihaji, Naima Nasraoui, Hanane Das, Sudipta El Aoufi, Jamal Kchikach, Mustapha International Academy of Civil Aviation Power Electronics and System Control Lab Higher National School of Mines Rabat Laboratory of Aeronautical Telecommunication Mohammed Vi Rabat Morocco Imps College of Engineering and Technology Department of Electronics and Communication Engineering West Bengal Chandipur India International Academy of Civil Aviation Laboratory of Aeronautical Telecommunication Mohammed Vi Nouaceur Morocco Higher National School of Mines Rabat Power Electronics and System Control Lab Rabat Morocco

ISBN: (纸本)9798350365306

In this article, a 2 × 1 UWB-MIMO flower bouquet has been discussed using a low-cost FR-4-epoxy material for wireless communication systems. This antenna provides a wider bandwidth impedance of [3.42-14.64] GHz. The reflection coefficient of the proposed work achieves - 35.04 dB. For the aims of reducing mutual coupling, a CSRR was etched on the top and the bottom of the radiation element and the isolation achieves 44.58 dB at 11.63 GHz. Furthermore, theECC parameter is less than 0.002 and the diversity gain is close to 10 dB. Moreover, the TARC parameter is low of - 10dB throughout the operating bandwidth. Therefore, the proposed design is a good choice for wireless communication systems. © 2024 IEEE.

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

Semantic Analysis and Modeling of the Color of Stage Costume – A Case Study of “The Painting Journey”

Semantic Analysis and Modeling of the Color of Stage Costume...

引用

Culture-Oriented Science and Technology (CoST), International Conference on

作者： Wenli Huang Bowen Liu Fang Sun Shuang Wang State Key Laboratory of Media Convergence and Communication Communication University of China China Key Laboratory of Acoustic Visual Technology and Intelligent Control System (Communication University of China) China Beijing Key Laboratory of Modern Entertainment Technology (Communication University of China) China

ISBN: (数字)9798350380347

ISBN: (纸本)9798350380354

The creation of Chinese dance dramas plays an important role in the dissemination of Chinese culture in the context of pluralistic unity. As one of the outstanding poetry dramas in the past two years, “The Journey of a Legendary Landscape Painting” (JLLP) has rich national cultural connotations and aesthetic value in its stage costume colors. This article first studied the data extraction method of stage costume colors based on clustering and association rule mining, and constructed the color dataset for JLLP. On this basis, the color semantic mining and extraction including subjective and objective factors were conducted. Finally, combined with color semantics, the character personality of JLLP was further analyzed. The research results show that the color extraction method designed in this article can accurately preserve the color characteristics of stage costumes. In addition, the costume colors of JLLP play a good supporting role in shaping the character personality.

关键词： Humanities Costs Correlation Image color analysis Databases Semantics Clustering algorithms

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：