检索结果-内蒙古大学图书馆

Diffusion-based framework for weakly-supervised temporal action localization

Pattern Recognition 2025年 160卷

作者： Zou, Yuanbing Zhao, Qingjie Sarker, Prodip Kumar Li, Shanshan Wang, Lei Liu, Wangwang School of Computer Science and Technology Beijing Institute of Technology Beijing100081 China Beijing Institute of Control Engineering Beijing100190 China

Weakly supervised temporal action localization aims to localize action instances with only video-level supervision. Due to the absence of frame-level annotation supervision, how effectively separate action snippets and backgrounds from semantically ambiguous features becomes an arduous challenge for this task. To address this issue from a generative modeling perspective, we propose a novel diffusion-based network with two stages. Firstly, we design a local masking mechanism module to learn the local semantic information and generate binary masks at the early stage, which (1) are used to perform action-background separation and (2) serve as pseudo-ground truth required by the diffusion module. Then, we propose a diffusion module to generate high-quality action predictions under the pseudo-ground truth supervision in the second stage. In addition, we further optimize the new-refining operation in the local masking module to improve the operation efficiency. The experimental results demonstrate that the proposed method achieves a promising performance on the publicly available mainstream datasets THUMOS14 and ActivityNet. The code is available at https://***/Rlab123/action_diff. © 2024

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Real-time Safety Helmet-wearing Detection Based on Improved YOLOv5

引用

computer Systems science & engineering 2022年第12期43卷 1219-1230页

作者： Yanman Li Jun Zhang Yang Hu Yingnan Zhao Yi Cao NARI Nanjing Control System Ltd. Nanjing210032China School of Computer Nanjing University of Information Science&TechnologyNanjing210044China Department of Electrical and computer Engineering University of WindsorWindsorN9B 3P4Canada

Safety helmet-wearing detection is an essential part of the intelligentmonitoring system. To improve the speed and accuracy of detection, especiallysmall targets and occluded objects, it presents a novel and efficient detectormodel. The underlying core algorithm of this model adopts the YOLOv5 (YouOnly Look Once version 5) network with the best comprehensive detection performance. It is improved by adding an attention mechanism, a CIoU (CompleteIntersection Over Union) Loss function, and the Mish activation function. First,it applies the attention mechanism in the feature extraction. The network can learnthe weight of each channel independently and enhance the information dissemination between features. Second, it adopts CIoU loss function to achieve accuratebounding box regression. Third, it utilizes Mish activation function to improvedetection accuracy and generalization ability. It builds a safety helmet-wearingdetection data set containing more than 10,000 images collected from the Internetfor preprocessing. On the self-made helmet wearing test data set, the averageaccuracy of the helmet detection of the proposed algorithm is 96.7%, which is1.9% higher than that of the YOLOv5 algorithm. It meets the accuracy requirements of the helmet-wearing detection under construction scenarios.

关键词： Safety helmet wearing detection object detection deep learning YOLOv5 Attention Mechanism

来源：评论

学校读者我要写书评

暂无评论

Retinal disorder diagnosis based on hybrid deep learning models

引用

Multimedia Tools and Applications 2025年 1-25页

作者： Sedik, Ahmed El-Shafai, Walid El-Hag, Noha A. El-Banby, Ghada M. Abd El-Samie, Fathi E. Smart Systems Engineering Laboratory College of Engineering Prince Sultan University Riyadh11586 Saudi Arabia Department of the Robotics and Intelligent Machines Faculty of Artificial Intelligence Kafrelsheikh University Kafr el-Sheikh Egypt Computer Science Department Prince Sultan University Riyadh11586 Saudi Arabia Department of Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt The Higher Institute of Commercial Sciences Algarbia Al Mahalla Al Kubra31951 Egypt Department of Industrial Electronics and Control Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Department of Information Technology College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia

Anomaly detection from medical images is badly needed for automated diagnosis. For example, medical images obtained with several modalities, such as magnetic resonance (MR) and confocal microscopy, need to be classified for anomaly detection. The MR images may contain tumors that need to be detected with anomaly detection techniques. In MR imaging, brain tumors are represented as areas composed of abnormal cells that need to be detected. On the other hand, confocal microscopy can be used for retinal imaging. Hence, there is a need to apply classification techniques for diagnosing diseases of the eye, such as Diabetic Retinopathy (DR), which leads to exudates in different regions of the retina. The detection of exudates is necessary for the diagnosis of DR. In this paper, two models are presented for the classification of MR and retinal images. Much research has been done in this area, but it did not achieve high accuracy of classification in an acceptable time. In addition, the previous models did not consider both types of image modalities considered in this paper. The suggested models are Convolutional Neural Network (CNN) and Convolutional Long Short-Term Memory (Conv-LSTM). They are used to classify normal and abnormal cases of both brain tumor and DR diseases. The CNN model is composed of six convolutional layers and six max-pooling layers. A soft-max activation function takes the classification decision. The proposed Conv-LSTM model is composed of three stages: pre-processing, feature extraction, and classification. The deep learning model performance is better than those of traditional networks. The CNN gives an accuracy of 94.26% for DR classification and 95.8% for brain tumor classification, while the Conv-LSTM gives the maximum accuracy of 96.41% for DR classification and 97.4% for brain tumor classification. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Confocal microscopy

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised Learning with Nearest-Neighbor Label and Consistency Regularization 1

引用

4th International Conference on Machine Learning for Cyber Security, ML4CS 2022

作者： Zheng, Guolin Li, Zuoyong Hu, Wenkai Fan, Haoyi Ching, Fum Yew Yu, Zhaochai Chen, Kaizhi College of Computer and Data Science Fuzhou University Fuzhou350108 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Control Engineering Minjiang University Fuzhou350121 China School of Computer and Artificial Intelligence Zhengzhou University Zhengzhou450001 China School of Computer Sciences Universiti Sains Malaysia Penang11800 Malaysia Minjiang University Fuzhou350121 China

ISBN: (数字)9783031200991

ISBN: (纸本)9783031200984

Semi-supervised learning, a system dedicated to making networks less dependent on labeled data, has become a popular paradigm due to its strong performance. A common approach is to use pseudo-labels with unlabeled data for training, however, pseudo-labels cannot correct their own errors. In this paper, we propose a semi-supervised method that uses nearest neighbor samples to obtain pseudo-labels and combines consistency regularization for image classification. Our method obtains pseudo-labels by computing the similarity of the data distribution between the weakly-augmented version of the unlabeled data and the labeled data stored in the support set and combines the consistency of the strongly-augmented version and the weakly-augmented version of the unlabeled data. We compared with several standard semi-supervised learning benchmarks and achieved a competitive performance. For example, we achieved an accuracy of 94.02 % on CIFAR-10 with 250 labels and 97.50 % on SVNH with 250 labels. It even achieved 91.59 % accuracy with only 40 labels data in the CIFAR-10. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Leveraging Large Language Models for Automatic Smart Contract Generation

Leveraging Large Language Models for Automatic Smart Contrac...

引用

IEEE Annual International computer Software and Applications Conference (COMPSAC)

作者： Emanuele Antonio Napoli Fadi Barbàra Valentina Gatteschi Claudio Schifanella Department of Control and Computer Engineering Politecnico di Torino Turin ITALY Department of Computer Science University of Turin Turin ITALY

ISBN: (数字)9798350376968

ISBN: (纸本)9798350376975

In the rapidly evolving landscape of blockchain technology, smart contracts stand as pivotal instrument for automating and enforcing digital agreements. However, their creation often necessitates specialized programming skills, hindering broader adoption and accessibility. This paper proposes a pipeline that leverages the capabilities of Large Language Models (LLMs) to automate the generation of smart contracts. By harnessing the natural language understanding and generation capabilities of LLMs, our approach aims to make accessible smart contract development to people that are not familiar with this task. The proposed pipeline employs the CO-STAR methodology to optimize prompt creation for high-quality outputs. Moreover, in order to assess the correctness and reliability of the generated smart contracts, we leverage on Slither, one of the most cutting-edge vulnerability detection tools. Furthermore, we propose a benchmarking suite based on metrics such as compilability, vulnerabilities, and presence of comments, among the others, in order to evaluate the effectiveness of the pipeline in terms of consistency of generated smart contracts, LLM's temperature effect, and prompt selection. The results show that our pipeline is able to produce 98.1% of compilable smart contracts, the temperature value has negligible effect on the generated smart contracts, and the CO-STAR methodology produces valuable and consistent outputs with low-impact vulnerabilities.

关键词： Measurement Large language models Instruments Smart contracts Pipelines Programming Software

来源：评论

学校读者我要写书评

暂无评论

LoBee: Bidirectional Communication between LoRa and ZigBee based on Physical-Layer CTC

引用

IEEE Transactions on Wireless Communications 2025年

作者： Gao, Demin Wang, Haoyu Chen, YongRui Ye, Qiaolin Wang, Weizheng Guo, Xiuzhen Wang, Shuai Liu, Yunhuai He, Tian Nanjing Forestry University College of Information Science and Technology Artificial Intelligence Nanjing210037 China University of Minnesota The Department of Computer Science and Engineering 55414 United States University of Chinese Academy of Sciences School of Electronic Electrical and Communication Engineering Beijing100049 China Southeast University The School of Computer Science and Engineering Nanjing211189 China City University of Hong Kong Department of Computer Science 999077 Hong Kong College of Control Science and Engineering Zhejiang 310027 China Peking University The Department of Computer Science and Engineering Beijing100871 China University of Minnesota The Department of Computer Science and Engineering Minneapolis55414 United States

LoRa networks operating in a star topology, this configuration creates a single point of failure and may limit scalability and reliability in areas that are large and geographically dispersed. In order to improve the overall transmission capabilities of the network, recent studies show that adding LoRa to the ZigBee devices effectively disseminates network management. By doing so, the strengths of both technologies can be leveraged, with LoRa serving as the long-range transmitter and ZigBee functioning as the mesh network. In this study, we present LoBee, a novel bidirectional communication method between LoRa and ZigBee that relies on Physical-Layer Cross-Technology Communication. Despite the fact that LoRa and ZigBee utilize different modulation techniques, ZigBee devices can detect and recognize LoRa chirps through the process of sampling the received signal strength. For the transmissions from ZigBee to LoRa devices, we carefully select the input chips to generate specific waveforms, where LoBee detects the preamble of a ZigBee frame based on the locations of the repeated peaks. Our evaluation, which was conducted using USRP and commodity devices, demonstrates that LoBee is capable of achieving concurrent bidirectional wireless communications, with a data rate of approximately 639.38 bits per second from LoRa to ZigBee and from ZigBee to LoRa with more than 90% frame reception rate in the 2.4 GHz frequency band. © 2002-2012 IEEE.

关键词： Zigbee

来源：评论

学校读者我要写书评

暂无评论

Insulator Defect Detection Based on YOLOv4-tiny with Improved Feature Fusion 12

Insulator Defect Detection Based on YOLOv4-tiny with Improve...

引用

12th International Conference on Information Technology in Medicine and Education, ITME 2022

作者： Zhong, Yuning Hu, Rong Li, Zuoyong Cai, Yuanzheng Fujian University of Technology College of Computer Science and Mathematics Fuzhou350118 China Minjiang University Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Control Engineering Fuzhou350121 China

ISBN: (纸本)9798350310153

Insulator exposed to a wild environment for long-term running usually suffers from the damage of natural calamities that makes them become one of the most fragile components in the whole power system. In this case, even a slight fault will seriously affect the power supply safety of the power grid. Therefore, it is critical to find and identify the faulty insulator efficiently and accurately. However, an insulator is quite a small component in comparison with a huge power system which makes it hard to visible with naked eyes. This characteristic leads to poor recognition accuracy for existing detection methods. In order to solve the above problems, we propose an insulator defect detection algorithm based on an improved YOLOv4-tiny model. It differs from existing insulator detection models, our algorithm applies the effective channel attention network to the feature extraction network of YOLOv4-tiny, which significantly enhances the feature extraction ability of the backbone network. These two-way features of the pyramid can be fully fused in the two-way feature fusion stages seamlessly. Experimental results show that compared with, our proposed algorithm outperforms Faster RCNN and YOLOv3 in average classification accuracy, missed detection, and false detection. © 2022 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

PI-funnel and inverse hysteresis compensation cascade control of smart soft dielectric elastomer actuator

引用

control Theory and Technology 2024年第4期22卷 552-567页

作者： Peng Huang Yawu Wang Yue Zhang Jundong Wu Chun-Yi Su School of Automation China University of GeosciencesWuhan430074HubeiChina Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074HubeiChina Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of EducationWuhan430074HubeiChina Gina Cody School of Engineering and Computer Science Concordia UniversityMontrealQCH3G 1M8Canada

Smart soft dielectric elastomer actuators(SSDEAs)possess wide applications in soft robotics due to their properties similar to natural muscles,including large deformation ratio,high energy density,and fast response ***,the complicated asymmetric and rate-dependent hysteresis property,creep property and quadratic input property of the SSDEA pose enormous challenges to its dynamic modeling and motion *** this paper,first,we construct the dynamic model of the SSDEA by connecting a square module,a one-sided Prandtl–Ishlinskii(OSPI)model and a linear system in series to describe the above *** key and innovative aspect of the dynamic modeling lies in cascading the square module in series with the OSPI model to construct the asymmetric hysteresis ***,a PI-funnel and inverse hysteresis compensation(PIFIHC)cascade control method of the SSDEA is proposed to actualize its tracking control *** performing the inversion operation on the asymmetric hysteresis model,the inverse hysteresis compensation controller(IHCC)is designed to compensate the asymmetric hysteresis property and quadratic input property of the *** addition,a PI-funnel controller is designed to cascade with the IHCC to construct the PIFIHC cascade controller to obtain a good tracking ***,the stability analysis of the PIFIHC cascade control system of the SSDEA is performed to theoretically prove that the tracking error can be controlled within the performance funnel and the steady-state error converges to ***,several practical tracking control experiments of the SSDEA are conducted,and RRMSEs are less than 2.30%for all *** experimental results indicate the effectiveness and feasibility of the proposed PIFIHC cascade control method of the SSDEA.

关键词： Smart soft dielectric elastomer actuator Dynamic modeling Inverse hysteresis compensation controller PI-funnel controller Cascade controller

来源：评论

学校读者我要写书评

暂无评论

Low-Rank Rescaled Vision Transformer Fine-Tuning: A Residual Design Approach

arXiv

引用

arXiv 2024年

作者： Dong, Wei Zhang, Xing Chen, Bihui Yan, Dawei Lin, Zhijun Yan, Qingsen Wang, Peng Yang, Yang School of Computer Science and Engineering University of Electronic Science and Technology of China China College of information and control engineering Xi'an University of Architecture and Technology China School of Computer Science Northwestern Polytechnical University China

Parameter-efficient fine-tuning for pre-trained Vision Transformers aims to adeptly tailor a model to downstream tasks by learning a minimal set of new adaptation parameters while preserving the frozen majority of pre-trained parameters. Striking a balance between retaining the generalizable representation capacity of the pre-trained model and acquiring task-specific features poses a key challenge. Currently, there is a lack of focus on guiding this delicate trade-off. In this study, we approach the problem from the perspective of Singular Value Decomposition (SVD) of pretrained parameter matrices, providing insights into the tuning dynamics of existing methods. Building upon this understanding, we propose a Residual-based Low-Rank Rescaling (RLRR) fine-tuning strategy. This strategy not only enhances flexibility in parameter tuning but also ensures that new parameters do not deviate excessively from the pretrained model through a residual design. Extensive experiments demonstrate that our method achieves competitive performance across various downstream image classification tasks, all while maintaining comparable new parameters. We believe this work takes a step forward in offering a unified perspective for interpreting existing methods and serves as motivation for the development of new approaches that move closer to effectively considering the crucial trade-off mentioned above. Our code is available at https://***/zstarN70/***. Copyright © 2024, The Authors. All rights reserved.

关键词： Singular value decomposition

来源：评论

学校读者我要写书评

暂无评论

Remaining Useful Life Prediction of Multi-Component System Clustering with Time-Varying Kernel Density

Remaining Useful Life Prediction of Multi-Component System C...

引用

2023 China Automation Congress, CAC 2023

作者： Li, Ke Fan, Xingle Shi, Hui Zhang, Xiaohong Sun, Chaoli Wang, Jianan Taiyuan University of Science and Technology Shanxi Key Laboratory of Advanced Control and Equipment Intelligence Dept. of Electronic and Information Engineering Taiyuan China Taiyuan University of Science and Technology Shanxi Key Laboratory of Advanced Control and Equipment Intelligence Dept. of Economics and Management Taiyuan China Taiyuan University of Science and Technology Shanxi Key Laboratory of Advanced Control and Equipment Intelligence Dept. of Computer Science and Technology Taiyuan China

ISBN: (纸本)9798350303759

Aiming at the uncertainty of the degradation procedure of a complex multi-component system in a time-varying environment and the influence of the random dependence between different components, a remaining useful life prediction model for time-varying adaptive kernel density estimation based on the dependence between multiple components is established. First, the random dependence between multi-component systems is clustered. Considering that different components in the same cluster are affected by the random dependence, the components between different clusters do not affect each other. Judge the dependence characteristics between components, and use the dependence characteristics of different components to conduct clustering degradation modelling. Secondly, the parameters of the system change with time. Considering that monitoring data near the current time has a greater impact on the remaining useful life prediction compared with historical data, data in the vicinity of the current time is accorded a more significant weight, and a time-varying kernel density estimation prediction method is designed, in which the nearest-neighbour adaptive window-width selection method is used. Finally, give an example to demonstrate the effectiveness by the proposed method. © 2023 IEEE.

关键词： Forecasting

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：