检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Dang, Zhuohang Luo, Minnan Wang, Jihong Jia, Chengyou Han, Haochen Wan, Herun Dai, Guang Chang, Xiaojun Wang, Jingdong The School of Computer Science and Technology The Ministry of Education Key Laboratory of Intelligent Networks and Network Security The Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University Shaanxi Xi'An710049 China SGIT AI Lab State Grid Shaanxi Electric Power Company Limited State Grid Corporation of China Shaanxi China The School of Information Science and Technology University of Science and Technology China United Arab Emirates The Baidu Inc China

Cross-modal retrieval is crucial in understanding latent correspondences across modalities. However, existing methods implicitly assume well-matched training data, which is impractical as real-world data inevitably involves imperfect alignments, i.e., noisy correspondences. Although some works explore similarity-based strategies to address such noise, they suffer from sub-optimal similarity predictions influenced by modality-exclusive information (MEI), e.g., background noise in images and abstract definitions in texts. This issue arises as MEI is not shared across modalities, thus aligning it in training can markedly mislead similarity predictions. Moreover, although intuitive, directly applying previous cross-modal disentanglement methods suffers from limited noise tolerance and disentanglement efficacy. Inspired by the robustness of information bottlenecks against noise, we introduce DisNCL, a novel information-theoretic framework for feature Disentanglement in Noisy Correspondence Learning, to adaptively balance the extraction of MII and MEI with certifiable optimal cross-modal disentanglement efficacy. DisNCL then enhances similarity predictions in modality-invariant subspace, thereby greatly boosting similarity-based alleviation strategy for noisy correspondences. Furthermore, DisNCL introduces soft matching targets to model noisy many-to-many relationships inherent in multi-modal input for noise-robust and accurate cross-modal alignment. Extensive experiments confirm DisNCL's efficacy by 2% average recall improvement. Mutual information estimation and visualization results show that DisNCL learns meaningful MII/MEI subspaces, validating our theoretical analyses. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A Real-Time Demonstration of Bidirectional Multi-Format/Rate-Adjustable Integrated Laser Communication/Ranging for Satellite Communication

A Real-Time Demonstration of Bidirectional Multi-Format/Rate...

引用

Conference on Lasers and Electro-Optics (CLEO)

作者： Yizhou Wang Yuanxiang Wang Zhen Luo Linsheng Zhong Yang Zou Xueyuan Ao Jiale Liu Feng Fan Xiaoliang Li Xiaoxiao Dai Qi Yang Deming Liu Wuhan National Lab for Optoelectronics (WNLO) & National Engineering Laboratory for Next Generation Internet Access System School of Optical and Electronic Information Huazhong University of Science and Technology Wuhan China Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China Beijing Research Institute of Telemetry Beijing China Jinyinhu Laboratory Wuhan China

A multi-format/rate-adjustable integrated laser communication/ranging system is proposed, achieving adjustable rates between 0.625-10Gbit/s. Real-time experiment shows that at 1e-4 BER the ranging error is only 0.29% ... 详细信息

ISBN: (纸本)9798350369311

关键词： Laser theory Codes Sensitivity Lasers Measurement uncertainty Measurement by laser beam Electro-optic effects Real-time systems Distance measurement Satellite communications

来源：评论

学校读者我要写书评

暂无评论

Logiformer: A Two-Branch Graph Transformer Network for Interpretable Logical Reasoning

arXiv

引用

arXiv 2022年

作者： Xu, Fangzhi Liu, Jun Lin, Qika Pan, Yudai Zhang, Lingling School of Computer Science and Technology Xi'an Jiaotong University Xi'an China Shaanxi Province Key Laboratory of Satellite and Terrestrial Network Tech. R&d National Engineering Lab for Big Data Analytics Xi'an China

Machine reading comprehension has aroused wide concerns, since it explores the potential of model for text understanding. To further equip the machine with the reasoning capability, the challenging task of logical reasoning is proposed. Previous works on logical reasoning have proposed some strategies to extract the logical units from different aspects. However, there still remains a challenge to model the long distance dependency among the logical units. Also, it is demanding to uncover the logical structures of the text and further fuse the discrete logic to the continuous text embedding. To tackle the above issues, we propose an end-to-end model Logiformer which utilizes a two-branch graph transformer network for logical reasoning of text. Firstly, we introduce different extraction strategies to split the text into two sets of logical units, and construct the logical graph and the syntax graph respectively. The logical graph models the causal relations for the logical branch while the syntax graph captures the co-occurrence relations for the syntax branch. Secondly, to model the long distance dependency, the node sequence from each graph is fed into the fully connected graph transformer structures. The two adjacent matrices are viewed as the attention biases for the graph transformer layers, which map the discrete logical structures to the continuous text embedding space. Thirdly, a dynamic gate mechanism and a question-aware self-attention module are introduced before the answer prediction to update the features. The reasoning process provides the interpretability by employing the logical units, which are consistent with human cognition. The experimental results show the superiority of our model, which outperforms the state-of-the-art single model on two logical reasoning benchmarks. © 2022, CC BY.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

A deep learning-based embedding framework for object detection and recognition in underwater marine organisms

Research Square

引用

Research Square 2021年

作者： Zhu, Jinde Fujian Provincial Key Lab of Big Data Mining and Applications School of Computer Science and Mathematics Fujian University of Technology Fuzhou350118 China

The detection of marine organisms is an important part of the intelligent strategy in marine ranch, which requires an underwater robot to detect the marine organism quickly and accurately in the complex ocean environment. Based on the latest deep learning arithmetic, this paper put forward to find the marine organism in a picture or video to construct a real-time objective invention system for marine organisms. The neural network arithmetic： YOLOv4 was employed to extract the deep features of marine organisms, implementing the accurate detection and size detection of different fish can use arithmetic for evaluation in fisheries. Furthermore, improving the architecture of the backbone and the neck connection is called YOLOv4-embedding. As a result, compared with other object detection arithmetic, YOLOv4-embedding object detection arithmetic was better at detection accuracy-higher detection confidence and higher detection ratio than other one-stage object detection arithmetic, EfficientDet-D3 example. The consequence demonstrates that the suggested instrument could implement the rapid invention of different varieties in marine organisms. Compared to the YOLOv4, the mAP75 of the YOLOv4-embedding achieves an improvement of 2.92% for the marine organism dataset at a rapid rate of ~51 FPS on RTX 3090, 60.8% AP50 for the MS COCO dataset. © 2021, CC BY.

关键词： Fish

来源：评论

学校读者我要写书评

暂无评论

A Large-scale Multiple-objective Method for Black-box Attack against Object Detection

arXiv

引用

arXiv 2022年

作者： Liang, Siyuan Li, Longkang Fan, Yanbo Jia, Xiaojun Li, Jingzhi Wu, Baoyuan Cao, Xiaochun State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China School of Data Science Secure Computing Lab of Big Data The Chinese University of Hong Kong Shenzhen China Tencent AI Lab Shenzhen China School of Cyber Science and Technology Shenzhen Campus Sun Yat-sen University Shenzhen China

Recent studies have shown that detectors based on deep models are vulnerable to adversarial examples, even in the black-box scenario where the attacker cannot access the model information. Most existing attack methods aim to minimize the true positive rate, which often shows poor attack performance, as another sub-optimal bounding box may be detected around the attacked bounding box to be the new true positive one. To settle this challenge, we propose to minimize the true positive rate and maximize the false positive rate, which can encourage more false positive objects to block the generation of new true positive bounding boxes. It is modeled as a multi-objective optimization (MOP) problem, of which the generic algorithm can search the Pareto-optimal. However, our task has more than two million decision variables, leading to low searching efficiency. Thus, we extend the standard Genetic Algorithm with Random Subset selection and Divide-and-Conquer, called GARSDC, which significantly improves the efficiency. Moreover, to alleviate the sensitivity to population quality in generic algorithms, we generate a gradient-prior initial population, utilizing the transferability between different detectors with similar backbones. Compared with the state-of-art attack methods, GARSDC decreases by an average 12.0 in the mAP and queries by about 1000 times in extensive experiments. Our codes can be found at https://***/LiangSiyuan21/ GARSDC. © 2022, CC BY.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

A Knowledge-Enhanced Medical Named Entity Recognition Method that Integrates Pre-Trained Language Models

A Knowledge-Enhanced Medical Named Entity Recognition Method...

引用

Medical Artificial Intelligence (MedAI), IEEE International Conference on

作者： Zhiyuan Wang Qiang Zhou Zhao Junfeng Yasha Wang Hongxin Ding Jiahe Song Key Lab of HCST (PKU) MOE SCS Peking University Beijing China School of Software & Microelectronics Peking University Beijing China Shenzhen Emergency Medical Center Shenzhen China Research Center of Big Data Technology Nanhu Laboratory Jiaxing China School of Computer Science Peking University Beijing China

Medical Named Entity Recognition (NER) is a critical task in medical text processing. But medical documents exhibit high variability in terms of language usage, abbreviations, synonyms, misspellings, and typographical errors, so the precise extraction of named entities is challenging. Although large language models (LLMs) have shown good performance in medical knowledge extraction tasks in few-shot settings, their performance is difficult to fully leverage in supervised medical named entity recognition (NER) tasks. This is because NER is a sequence labeling task, while LLMs are more suitable for tasks such as text generation. Furthermore, the structured output of NER tasks leads to a performance loss when LLMs convert it into generative text. Therefore, it is a challenging problem to utilize LLMs to improve the accuracy of medical named entity recognition tasks. On this paper, we propose a method that integrates LLM knowledge to enhance the performance of medical NER models. Firstly, we improve the structure of the LLM model to make it more adaptable to NER tasks. Secondly, we adopt the LoRA method and incorporate Chinese vocabulary information into the model training. Finally, to fully utilize the fine-tuned LLM to enhance the medical NER model, we convert the output of the LLM into a knowledge concentration matrix and inject it into the NER model. We have verify the effectiveness of our new method on the CMeEE dataset. The results demonstrate that our method can efficiently fine-tune the LLM and improve its performance. Moreover, our method can also leverage the prior knowledge of the fine-tuned LLM to enhance the BERT-based medical NER model. In addition, our method demonstrates good generalization and can tackle entity recognition tasks in other domains. We validated the superiority of our approach on the resume-zh dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A comprehensive survey on shadow removal from document images: datasets, methods, and opportunities

引用

Vicinagearth 2025年第1期2卷 1-18页

作者： Wang, Bingshu Li, Changping Zou, Wenbin Zhang, Yongjun Chen, Xuhang Chen, C.L. Philip School of Software Northwestern Polytechnical University Xi’an China Guangdong Provincial Key Laboratory of Intelligent Information Processing & Shenzhen Key Laboratory of Media Security Shenzhen University Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing College of Electronics and Information Engineering Shenzhen University Shenzhen China Yongjun Zhang is with the State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang China School of Computer Science and Engineering Huizhou University Huizhou China School of Computer Science and Engineering South China University of Technology and Pazhou Lab Guangzhou China

With the rapid development of document digitization, people have become accustomed to capturing and processing documents using electronic devices such as smartphones. However, the captured document images often suffer from issues like shadows and noise due to environmental factors, which can affect their readability. To improve the quality of captured document images, researchers have proposed a series of models or frameworks and applied them in distinct scenarios such as image enhancement, and document information extraction. In this paper, we primarily focus on shadow removal methods and open-source datasets. We concentrate on recent advancements in this area, first organizing and analyzing nine available datasets. Then, the methods are categorized into conventional methods and neural network-based methods. Conventional methods use manually designed features and include shadow map-based approaches and illumination-based approaches. Neural network-based methods automatically generate features from data and are divided into single-stage approaches and multi-stage approaches. We detail representative algorithms and briefly describe some typical techniques. Finally, we analyze and discuss experimental results, identifying the limitations of datasets and methods. Future research directions are discussed, and nine suggestions for shadow removal from document images are proposed. To our knowledge, this is the first survey of shadow removal methods and related datasets from document images.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Anticipation of Parking Vacancy during Peak/Non-peak Hours using Convolutional Neural Network-YOLOv3 in University Campus

Anticipation of Parking Vacancy during Peak/Non-peak Hours u...

引用

2021 International Conference on Green Energy, Computing and Sustainable Technology, GECOST 2021

作者： Davan, Jasvina Mae A.P. Ealn Koh, Tieng Wei Tong, Dong Ling Tseu, Kwan Lee First City University College Artificial Intelligence Lab Faculty of Computing and Engineering Petaling Jaya Malaysia University of Putra Malaysia Faculty of Computer Science and Information Technology Selangor Malaysia Universiti Tunku Abdul Rahman Centre of IoT Big Data Faculty of Information and Communication Technology Perak Malaysia

ISBN: (纸本)9781665438650

Searching for a publicly available parking space has become a nightmare to many drivers. With the constant development of global urbanization, human population has increased drastically in the past decades. Searching for a publicly available parking space in a highly populated area can be daunting and time consuming. No matter how much time is spent to find a vacant parking space, it always causes traffic congestion in the area. To alleviate these problems, it is of utmost importance to have a system that can detect and display the vacant parking spaces in real-time. This paper has conducted a study of anticipation of parking vacancy using convolutional neural network called YOLOv3 in a university campus. Image data is gathered from the video capture of the university's campus open space parking lot. The YOLOv3 algorithm is used to train and predict whether the space is vacant or occupied. Results showed that YOLOv3 has been able to correctly predict the vacant space. The result of the rendering video will then be transformed into an image and is sent to the students via a Telegram group. © 2021 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Vehicle location algorithm based on federated learning and smart phone in GNSS low sampling rate scene

Vehicle location algorithm based on federated learning and s...

引用

2021 International Conference on Information Technology and Mechanical Engineering, ITME 2021

作者： Guo, Wenbiao Li, Hang Yin, Feng Ai, Bo School of Electronic and Information Engineering Beijing Jiaotong University Beijing China State Key Lab of Rail Traffic Control and Safety Beijing Jiaotong University Beijing China Shenzhen Research Institute of Big Data Shenzhen China School of Science and Engineering the Chinese University of Hong Kong Shenzhen China

In the existing vehicle positioning system based on Global Navigation Satellite System/Inertial Navigation System (GNSS/INS), when the GNSS signal is lost, the error accumulated by using only the INS will damage the positioning accuracy. In order to improve the accuracy, this paper proposed a positioning method based on data-driven and learning models, which utilized distributed data sets to collaboratively construct accurate positioning models through federated fusion algorithms without sacrificing user privacy. In the field scenarios of IID and Non-IID types, this paper compared the performance of INS and the existing two typical methods, DeepSense and PVAUA, it is verified that the two federated learning algorithm models constructed had higher positioning accuracy in different scenarios and different GNSS signal loss durations. The results were analyzed. © 2021 Institute of Physics Publishing. All rights reserved.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Projected near-surface wind speed and wind energy over Central Asia using dynamical downscaling with bias-corrected global climate models

引用

Advances in Climate Change Research 2024年第4期15卷 669-679页

作者： Jin-Lin ZHA Ting CHUAN Yuan QIU Jian WU De-Ming ZHAO Wen-Xuan FAN Yan-Jun LYU Hui-Ping JIANG Kai-Qiang DENG Miguel ANDRES-MARTIN Cesar AZORIN-MOLINA Deliang CHEN Key Laboratory of Atmospheric Environment and Processes in the Boundary Layer over the Low-Latitude Plateau Region Department of Atmospheric ScienceYunnan UniversityKunming 650091China Key Laboratory of Regional Climate and Environment for Temperate East Asia Institute of Atmospheric Physics Chinese Academy of SciencesBeijing 100029China Center for Energy&Environmental Policy Research Beijing Institute of Technology Beijing 100081China Key Laboratory of Regional Sustainable Development Modeling Institute of Geographic Sciences and Natural Resources ResearchChinese Academy of SciencesBeijing 100101China International Research Center of Big Data for Sustainable Development Goals Beijing 100094China School of Atmospheric Sciences Sun Yat-sen Universityand Southern Marine Science and Engineering Guangdong Laboratory(Zhuhai)Zhuhai 519082China Centro de Investigaciones Sobre Desertificacion Consejo Superior de Investigaciones Cientificas(CIDECSIC-UV-Generalitat Valenciana)ClimateAtmosphere and Ocean Laboratory(Climatoc-Lab)Moncada 46113Spain Regional Climate Group.Deparment of Earth Sciences University of GothenburgGothenburg 40530Sweden

Wind energy development in Central Asia can help alleviate drought and fragile ***,current studies mainly used the global climate models(GCMs)to project wind speed and *** simulated biases in GCMs remain prominent,which induce a large uncertainty in the projected *** reduce the uncertainties of projected near-surface wind speed(NSW)and better serve the wind energy development in Central Asia,the Weather Research and Forecasting(WRF)model with bias-corrected GCMs was *** with the outputs of GCMs,dynamical downscaling acquired using the WRF model can better capture the high-and low-value centres of NSWS,especially those of Central Asia's ***,the simulated NSWS bias was also *** future changes in wind speed and wind energy,under the Representative Concentration Pathway 4.5(RCP4.5)scenario,NSWS during 2031-2050 is projected to decrease compared with that in *** magnitude of NSwS reduction during 2031-2050 willreach 0.1 m s^(-1).and the maximum reduction is projected to occur over the central and western regions(>0.2 m s^(-1)).Furthermore,future wind power density(WPD)can reveal nonstationarity and strong volatility,although a downward trend is expected during *** addition,the higher frequency of wind speeds at the turbine hub height exceeding 3.0 m s^(-1)can render the plain regions more suitable for wind energy development than the mountains from 2031 to *** study can serve as a guide in gaining insights into future changes in wind energy across Central Asia and provide a scientific basis for decision makers in the formulation of policies for addressing climate change.

关键词： Near-surface wind speed Wind power density Dynamical downscaling Central Asia WRF

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：