检索结果-内蒙古大学图书馆

The Spatiotemporal Fusion for Nighttime Light Based on SDGSAT-1 and VIIRS Data

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Zhang, Shuyan Ma, Yong Chen, Hongyu Shang, Erping Yao, Wutao Yang, Jin He, Guojin Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China State Key Laboratory of Media Convergence Production Technology and Systems Beijing100803 China Institute of Optoelectronics Fudan University Shanghai200433 China

Nighttime light (NTL) remote sensing has emerged as a pivotal tool across diverse fields, such as urban expansion, socioeconomic estimation, light pollution, and energy analysis. However, existing NTL datasets with different scales exhibit shortcomings including low-spatial resolution, infrequent updates, and inadequate observation timing, hindering their suitability for large-scale fine-grained applications. To address these challenges, this study designs the NTL spatiotemporal fusion (STF) strategy, which amalgamates the strengths of multisource NTL data, including spatiotemporal super resolution (STSR) and local NTL recovery (LNR). Leveraging data from the Visible Infrared Imaging Radiometer Suite (VIIRS) and Sustainable Development Goals Satellite-1 (SDGSAT-1), the study constructs the STF-NTL dataset to analyze NTL trends in France. The research demonstrates that, compared with alternative super-resolution (SR) methods, the STSR approach excels in texture structure and evaluation accuracy. The improved module in STSR achieves superior image quality by balancing image error and human visual perception. Furthermore, STF-NTL data following LNR exhibits enhanced matching accuracy with impervious surfaces compared with other NTL datasets, aligning more closely with economic development and urbanization trends. Application of the STF-NTL dataset in France reveals an increase in NTL area in 2022 relative to 2012, rectifying statistical disparities observed with VIIRS data. Analysis indicates that regional conflicts, energy crises, and policy shifts influenced fluctuations in monthly NTL across France in 2022. The period from March to September 2022 demonstrates a strong correlation between NTL changes and the electricity market, while post-September dynamics are predominantly shaped by energy-saving policies. The STF-NTL datasets can be produced on a global scale, offering enhanced accuracy in reflecting economic, urban, and societal conditions. © 2025 IEEE.

关键词： Infrared imaging

来源：评论

学校读者我要写书评

暂无评论

A Novel Neural Network-based Data Observation Method for Zeeman Detection 41

A Novel Neural Network-based Data Observation Method for Zee...

引用

第41届中国控制会议

作者： Shuhan Li Yonxing Wang Zizhao Chen UWC Changshu China State Key Laboratory of Media Convergence Production Technology and Systems Xinhua News Agency

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Zeeman effect characterizes the phenomenon that a spectral line is split into several components in the presence of a static magnetic *** is very important in applications,such as magnetic resonance imaging,nuclear magnetic resonance spectroscopy and atomic absorption *** measurement was used in Di Li's recent Nature paper to reveal a coherent magnetic field from the atomic cold neutral medium to the molecular *** paper proposes a novel data observation based on neural network for Zeeman detection,which provides a different way to learn data feature *** results show that our method can fit the data in Li's paper well.

关键词： Data Observation Neural Network Zeeman Detection

来源：评论

学校读者我要写书评

暂无评论

ERNCLS: A Cross-Lingual Text Summarization Model Integrating Entity Relation Extraction Task 3

ERNCLS: A Cross-Lingual Text Summarization Model Integrating...

引用

3rd IEEE International Conference on Information technology, Big Data and Artificial Intelligence, ICIBA 2023

作者： Liu, Zhaohong Cao, Juan Yu, Jia Chen, Guowei He, Qiang Communication University of China State Key Laboratory of Media Convergence and Communication Beijing China State Key Laboratory of Media Convergence Production Technology and Systems Beijing China

ISBN: (纸本)9781665490788

The current research on generative cross-lingual summarization models mainly adopts the framework of seq2seq, where entity relation errors are inevitable. How to reduce the occurrence of errors and improve the accuracy of summary generation needs to be addressed urgently. In this regard, we try to add the task of extracting entity relations as an auxiliary task in the Chinese-to-English cross-lingual text summarization model to reduce the entity relation errors in the summaries, and propose two fusion strategies for merging the auxiliary task. In addition, we also adjust the dataset for this task. The experiment proves that it is effective to reduce errors as well as improve the performance of cross-lingual text summarization model by merging the auxiliary task of extracting entity relations in the way of splicing summaries and entity relation triples as real labels of training sets. © 2023 IEEE.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

Intelligent Mobile Body Temperature Monitoring Management System for Nursing Home 6

Intelligent Mobile Body Temperature Monitoring Management Sy...

引用

6th IEEE International Conference on Computer and Communication systems, ICCCS 2021

作者： Cui, Chengkun Wang, Chen Dong, Xu An, Ziji State Key Laboratory of Media Convergence Production Technology and Systems Xinhua News Agency Future Media Convergence Institute Xinhuanet Beijing China

ISBN: (纸本)9780738126043

Public health security is a common challenge facing all mankind and requires efforts from worldwide countries. Since the beginning of 2020, the sudden outbreak of the COVID-19 has affected everyone around the world. Thermometers have played a crucial role in the fight against the pandemic. For example, public places like airports and stations are all equipped with necessary temperature-measuring devices such as medical thermometers, infrared ear thermometers, and thermal imagers. Traditional mercury thermometers not only easily break, but also take a long time to measure body temperature and are difficult to read. As staffers need to be assigned to measure people's temperature, infrared ear thermometers and thermal imagers increase the chances of cross infection and are unable to provide real-time and continuous data, making temperature monitoring and management during the pandemic much more difficult. This paper will introduce an intelligent mobile body temperature monitoring and management system (IMBTMMS) particularly designed for nursing homes. Besides monitoring body temperature on a real-time and continuous basis, the system also provides heart rate and blood oxygen data and intelligently recommends relaxing music solutions. The sensor pad is connected to the mobile app via Bluetooth, with the server on the cloud integrated with an advanced artificial intelligence (AI) algorithm. By regularly processing body temperature, heart rate, and blood oxygen data, the system offers real-time and continuous monitoring, forecasting, warning, and management services. Targeting at use in nursing home, the system enables large-scale monitoring and management, which greatly eases the shortage of manpower during the pandemic and reduces the risk of cross infection. Finally, the system is highly extendable as it can be connected with offline and online medical services, which can be customized as per different demands. © 2021 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Image Matters: A New Dataset and Empirical Study for Multimodal Hyperbole Detection 30

Image Matters: A New Dataset and Empirical Study for Multimo...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Zhang, Huixuan Wan, Xiaojun Wangxuan Institute of Computer Technology Peking University State Key Laboratory of Media Convergence Production Technology and Systems China

ISBN: (纸本)9782493814104

Hyperbole, or exaggeration, is a common linguistic phenomenon. The detection of hyperbole is an important part of understanding human expression. There have been several studies on hyperbole detection, but most of which focus on text modality only. However, with the development of social media, people can create hyperbolic expressions with various modalities, including text, images, videos, etc. In this paper, we focus on multimodal hyperbole detection. We create a multimodal detection dataset from Weibo (a Chinese social media) and carry out some studies on it. We treat the text and image from a piece of weibo as two modalities and explore the role of text and image for hyperbole detection. Different pre-trained multimodal encoders are also evaluated on this downstream task to show their performance. Besides, since this dataset is constructed from five different keywords, we also evaluate the cross-domain performance of different models. These studies can serve as a benchmark and point out the direction of further study on multimodal hyperbole detection. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Is Summary Useful or Not? An Extrinsic Human Evaluation of Text Summaries on Downstream Tasks 30

Is Summary Useful or Not? An Extrinsic Human Evaluation of T...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Pu, Xiao Gao, Mingqi Wan, Xiaojun Wangxuan Institute of Computer Technology Peking University State Key Laboratory of Media Convergence Production Technology and Systems China

ISBN: (纸本)9782493814104

Research on automated text summarization typically uses human and automatic evaluation methods. While most recent studies focus on intrinsic evaluation, which assesses the general quality of summaries, e.g. coherence and informativeness, we concentrate on task-based extrinsic evaluation to determine the usefulness of summaries. We incorporate three downstream tasks, namely question answering, text classification, and text similarity assessment, and measure the usefulness of summaries for these tasks by several metrics. Our findings reveal that summaries are generally useful in tasks that require a comprehensive grasp of the text but are less useful in tasks requiring a more specific understanding of the text. We also analyze the usefulness and inherent properties of summaries from different models, and find that fine-tuned models consistently produce more useful summaries across all three tasks. In contrast, zero-shot models tend to lean towards text classification and similarity assessment, providing more general and less detailed summaries. Additionally, we assess the correlation between 14 intrinsic automatic metrics and human judgments. Intrinsic metrics perform well in evaluating summaries for question answering but are less effective in the other two tasks. This highlights the limitations of relying solely on intrinsic metrics for assessing summary performance and usefulness. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Quality control

来源：评论

学校读者我要写书评

暂无评论

Visual and Textual Information Fusion Method for Chart Recognition 25th

Visual and Textual Information Fusion Method for Chart Recog...

引用

25th International Conference on Pattern Recognition Workshops, ICPR 2020

作者： Wang, Chen Cui, Kaixu Zhang, Suya Xu, Changliang XinHua ZhiYun Inc. Hangzhou China State Key Laboratory of Media Convergence Production Technology and Systems Beijing China State Key Laboratory of Media Convergence and Communication Communication University of China Beijing China

ISBN: (纸本)9783030687922

In this report, we present our method in the ICPR 2020 Competition on Harvesting Raw Tables from Infographics, which is composed of Chart Classification, Text Detection/Recognition, Text Role Classification, Axis Analysis, Legend Analysis, Plot Element Detection/Classification and CSV Extraction. The image classification models of ResNet are adopt in Chart Classification. We adopted a two-stage based pipeline for end-to-end recognition, considering detection and recognition as two modules in Text Detection/Recognition. An ensemble model with LayoutLM and object detection model is adopted in Text Role Classification. A two-stage pipeline with two detection model is adopt in Legend Analysis. The final results are discussed. © 2021, Springer Nature Switzerland AG.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

Intelligent News Recommendation System for Automobile Based on Bio-Sensing and Physiological Computing 2021

Intelligent News Recommendation System for Automobile Based ...

引用

4th International Conference on Signal Processing and Machine Learning, SPML 2021

作者： Cui, Chengkun Wang, Chen Wen, Cong Fang, Xiaoyin Deng, Yuanyuan State Key Laboratory of Media Convergence Production Technology and Systems Xinhua News Agency and Future Media Convergence Institute Xinhuanet Beijing China Migu Culture Technology Co. Ltd China

ISBN: (纸本)9781450390170

With the development and application of technologies such as big data and artificial intelligence, the automotive industry is confronted with unprecedented challenges. New technologies are coming into the spotlight while potentials for transformation are growing under the surface, leading to the omnipresence of challenges across various fields. Under such circumstances, media and auto companies are both aware of an imminent change. The smart ring developed by our team can be applied to the driver fatigue detection system in industrial production-which helps media companies to access the vehicle networking system by monitoring the fatigue status of drivers, as well as their physiological changes when listening to the news. The vehicle networking system recommends personalized contents for users based on their portraits, using algorithm not only considers their interests and browsing behaviors, but also takes physiological and psychological responses of vehicle users when listening to the news as a key dimension based on the smart ring;therefore, it enables integration of online behavioral and offline physiological data, as such making up for where traditional algorithms fall short. Through intelligent interaction of media contents and human physiological signals, it changes the existing process of news production, manufacturing, distribution, collection, and feedback, and thus will become a model of the future smart recommendation system for in-vehicle infotainment. At present, research findings have been applied to two vehicle types of an auto company, which will come into the market in the first half of this year. © 2021 ACM.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Error-Robust Retrieval for Chinese Spelling Check 30

Error-Robust Retrieval for Chinese Spelling Check

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Yin, Xunjian Hu, Xinyu Jiang, Jin Wan, Xiaojun Wangxuan Institute of Computer Technology Peking University Center for Data Science State Key Laboratory of Media Convergence Production Technology and Systems China

ISBN: (纸本)9782493814104

Chinese Spelling Check (CSC) aims to detect and correct error tokens in Chinese contexts, which has a wide range of applications. However, it is confronted with the challenges of insufficient annotated data and the issue that previous methods may actually not fully leverage the existing datasets. In this paper, we introduce our plug-and-play retrieval method with error-robust information for Chinese Spelling Check (RERIC), which can be directly applied to existing CSC models. The datastore for retrieval is built completely based on the training data, with elaborate designs according to the characteristics of CSC. Specifically, we employ multimodal representations that fuse phonetic, morphologic, and contextual information in the calculation of query and key during retrieval to enhance robustness against potential errors. Furthermore, in order to better judge the retrieved candidates, the n-gram surrounding the token to be checked is regarded as the value and utilized for specific reranking. The experiment results on the SIGHAN benchmarks demonstrate that our proposed method achieves substantial improvements over existing work. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

Utilizing spatio-temporal feature fusion in videos for detecting the fluidity of coal water slurry

引用

International Journal of Mining Science and technology 2024年第11期34卷 1587-1597页

作者： Meijie Sun Ziqi Lv Zhiqiang Xu Haimei Lv Yanan Tu Weidong Wang School of Chemical&Environmental Engineering China University of Mining&Technology(Beijing)Beijing 100083China Inner Mongolia Research Institute China University of Mining&Technology(Beijing)Ordos 017001China State Key Laboratory of Media Convergence Production Technology and Systems Beijing 100803China

The fluidity of coal-water slurry(CWS)is crucial for various industrial applications such as long-distance transportation,gasification,and ***,there is currently a lack of rapid and accurate detection methods for assessing CWS *** paper proposed a method for analyzing the fluidity using videos of CWS dripping *** integrating the temporal and spatial features of each frame in the video,a multi-cascade classifier for CWS fluidity is *** classifier distinguishes between four levels(A,B,C,and D)based on the quality of *** preliminary classification of A and D is achieved through feature engineering and the XGBoost ***,convolutional neural networks(CNN)and long short-term memory(LSTM)are utilized to further differentiate between the B and C categories which are prone to ***,through detailed comparative experiments,the paper demonstrates the step-by-step design process of the proposed method and the superiority of the final *** proposed method achieves an accuracy rate of over 90%in determining the fluidity of CWS,serving as a technical reference for future industrial applications.

关键词： Coal water slurry Spatio-temporal feature CNN-LSTM Video classification Machine vision

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：