检索结果-内蒙古大学图书馆

UformPose: A U-Shaped Hierarchical Multi-Scale Keypoint-Aware Framework for Human Pose Estimation

IEEE Transactions on Circuits and Systems for Video Technology 2023年第4期33卷 1697-1709页

作者： Wang, You-Jie Luo, Yan-Min Bai, Gui-Hu Guo, Jing-Ming Huaqiao University Key Laboratory for Computer Vision and Pattern Recognition The College of Computer Science and Technology Xiamen361021 China National Taiwan University of Science and Technology Department of Electrical Engineering Taipei10607 Taiwan

Human pose estimation is a fundamental yet challenging task in computer vision. However, difficult scenarios such as invisible keypoints, occlusions and small-scale persons are still not well-handed. In this paper, we present a novel pose estimation framework named UformPose which targets to relieve these issues. UformPose has two core designs: Shared Feature Pyramid Stem (SFPS) and U-shaped hierarchical Multi-scale Keypoint-aware Attention Module (U-MKAM). SFPS is a feature pyramid stem with shared mechanism to learn stronger low-level features at the initial stage, and the shared mechanism can facilitate cross-resolution commonality learning. Our U-MKAM attempts to generate high-quality high-resolution representations by integrating all levels of feature representation of the backbone layer by layer. More importantly, we utilize the flexibility of attention operations for keypoint-aware modeling, which explicitly captures and trades-offs the dependencies between keypoints. We empirically demonstrate the effectiveness of our framework through the competitive pose estimation results on the COCO dataset. Extensive experiments and visual analysis on CrowdPose demonstrate the robustness of our model in crowd scenes. © 1991-2012 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Specificity-preserving RGB-D saliency detection

引用

Computational Visual Media 2023年第2期9卷 297-317页

作者： Tao Zhou Deng-Ping Fan Geng Chen Yi Zhou Huazhu Fu School of Computer Science and Engineering Nanjing University of Science and TechnologyNanjing 210094China Key Laboratory of System Control and Information Processing Ministry of EducationShanghaiChina Computer Vision Lab ETH Z¨urichZ¨urichSwitzerland School of Computer Science and Engineering Northwestern Polytechnical UniversityXi’anChina School of Computer Science and Engineering Southeast UniversityNanjingChina Inception Institute of Artificial Intelligence Abu DhabiUnited Arab Emirates

Salient object detection(SOD)in RGB and depth images has attracted increasing research *** RGB-D SOD models usually adopt fusion strategies to learn a shared representation from RGB and depth modalities,while few methods explicitly consider how to preserve modality-specific *** this study,we propose a novel framework,the specificity-preserving network(SPNet),which improves SOD performance by exploring both the shared information and modality-specific ***,we use two modality-specific networks and a shared learning network to generate individual and shared saliency prediction *** effectively fuse cross-modal features in the shared learning network,we propose a cross-enhanced integration module(CIM)and propagate the fused feature to the next layer to integrate cross-level ***,to capture rich complementary multi-modal information to boost SOD performance,we use a multi-modal feature aggregation(MFA)module to integrate the modalityspecific features from each individual decoder into the shared *** using skip connections between encoder and decoder layers,hierarchical features can be fully *** experiments demonstrate that our SPNet outperforms cutting-edge approaches on six popular RGB-D SOD and three camouflaged object detection *** project is publicly available at https://***/taozh2017/SPNet.

关键词： salient object detection(SOD) RGB-D cross-enhanced integration module(CIM) multi-modal feature aggregation(MFA)

来源：评论

学校读者我要写书评

暂无评论

AN EMPIRICAL ANALYSIS OF FORGETTING IN PRE-TRAINED MODELS WITH INCREMENTAL LOW-RANK UPDATES 3

AN EMPIRICAL ANALYSIS OF FORGETTING IN PRE-TRAINED MODELS WI...

引用

3rd Conference on Lifelong Learning Agents, CoLLAs 2024

作者： Soutif-Cormerais, Albin Magistri, Simone van de Weijer, Joost Bagdanov, Andrew D. Computer Vision Center Spain Department of Computer Science Universitat Autònoma de Barcelona Spain Department of Information Engineering University of Florence Italy

Broad, open source availability of large pretrained foundation models on the internet through platforms such as HuggingFace has taken the world of practical deep learning by storm. A classical pipeline for neural network training now typically consists of finetuning these pretrained network on a small target dataset instead of training from scratch. In the case of large models this can be done even on modest hardware using a low rank training technique known as Low-Rank Adaptation (LoRA). While Low Rank training has already been studied in the continual learning setting, existing works often consider storing the learned adapter along with the existing model but rarely attempt to modify the weights of the pretrained model by merging the LoRA with the existing weights after finishing the training of each task. In this article we investigate this setting and study the impact of LoRA rank on the forgetting of the pretraining foundation task and on the plasticity and forgetting of subsequent ones. We observe that this rank has an important impact on forgetting of both the pretraining and downstream tasks. We also observe that vision transformers finetuned in that way exhibit a sort of "contextual" forgetting, a behaviour that we do not observe for residual networks and that we believe has not been observed yet in previous continual learning works. © 2024 CoLLAs. All Rights Reserved.

关键词： Open systems

来源：评论

学校读者我要写书评

暂无评论

BEDiff: denoising diffusion probabilistic models for building extraction

引用

Optoelectronics Letters 2025年第5期21卷 298-305页

作者： LEI Yanjing WANG Yuan CHAN Sixian HU Jie ZHOU Xiaolong ZHANG Hongkai College of Computer Science and Technology Zhejiang University of Technology Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering College of Computer and Information China Three Gorges University Key Laboratory of Intelligent Informatics for Safety & Emergency of Zhejiang Province Wenzhou University College of Electrical and Information Engineering Quzhou University School of Electronic and Information Engineering Anhui Jianzhu University

Accurately identifying building distribution from remote sensing images with complex background information is challenging. The emergence of diffusion models has prompted the innovative idea of employing the reverse denoising process to distill building distribution from these complex backgrounds. Building on this concept, we propose a novel framework, building extraction diffusion model(BEDiff), which meticulously refines the extraction of building footprints from remote sensing images in a stepwise fashion. Our approach begins with the design of booster guidance, a mechanism that extracts structural and semantic features from remote sensing images to serve as priors, thereby providing targeted guidance for the diffusion process. Additionally, we introduce a cross-feature fusion module(CFM) that bridges the semantic gap between different types of features, facilitating the integration of the attributes extracted by booster guidance into the diffusion process more effectively. Our proposed BEDiff marks the first application of diffusion models to the task of building extraction. Empirical evidence from extensive experiments on the Beijing building dataset demonstrates the superior performance of BEDiff, affirming its effectiveness and potential for enhancing the accuracy of building extraction in complex urban landscapes.

关键词： A

来源：评论

学校读者我要写书评

暂无评论

Solar Radiation Estimation Based on a New Combined Approach of Artificial Neural Networks (ANN) and Genetic Algorithms (GA) in South Algeria

引用

computers, Materials & Continua 2024年第6期79卷 4725-4740页

作者： Djeldjli Halima Benatiallah Djelloul Ghasri Mehdi Tanougast Camel Benatiallah Ali Benabdelkrim Bouchra Material Sciences Department Faculty of Material SciencesMathematics and Computer ScienceLaboratory of Sustainable Development and Computer Science(LSDCS)University of AdrarAdrar01000Algeria Department of Civil Engineering University of Sistan and BaluchestanZahedan98167-45845Iran Laboratory of Computer Production and Maintenance Engineering(LGIPM)University of LorraineChieulles57070France Laboratory of Energy Environment and Information System(LEEIS) University of AdrarAdrar01000Algeria

When designing solar systems and assessing the effectiveness of their many uses,estimating sun irradiance is a crucial first *** study examined three approaches(ANN,GA-ANN,and ANFIS)for estimating daily global solar radiation(GSR)in the south of Algeria:Adrar,Ouargla,and *** proposed hybrid GA-ANN model,based on genetic algorithm-based optimization,was developed to improve the ANN *** GA-ANN and ANFIS models performed better than the standalone ANN-based model,with GA-ANN being better suited for forecasting in all sites,and it performed the best with the best values in the testing phase of Coefficient of Determination(R=0.9005),Mean Absolute Percentage Error(MAPE=8.40%),and Relative Root Mean Square Error(rRMSE=12.56%).Nevertheless,the ANFIS model outperformed the GA-ANN model in forecasting daily GSR,with the best values of indicators when testing the model being R=0.9374,MAPE=7.78%,and rRMSE=10.54%.Generally,we may conclude that the initial ANN stand-alone model performance when forecasting solar radiation has been improved,and the results obtained after injecting the genetic algorithm into the ANN to optimize its weights were *** model can be used to forecast daily GSR in dry climates and other climates and may also be helpful in selecting solar energy system installations and sizes.

关键词： Solar energy systems genetic algorithm neural networks hybrid adaptive neuro fuzzy inference system solar radiation

来源：评论

学校读者我要写书评

暂无评论

Part of Speech Tagging Using Part of Speech Sequence Graph

引用

Annals of Data Science 2023年第5期10卷 1301-1328页

作者： Gholami-Dastgerdi, Pejman Feizi-Derakhshi, Mohammad-Reza Computerized Intelligence Systems Laboratory Department of Computer Engineering University of Tabriz Tabriz Iran

Part of speech tagging is one of the most fundamental needs of intelligent text processing, which is assigning the most appropriate grammatical category to each word on the text. Hence, provision of a tagger with high accuracy for the Persian language is the major priority of this article. Numerous other methods of POS tagging have already been presented in a way that each one has been applied in taggers to achieve high performance and accuracy. Statistical methods known as a primary technique and one of the most important issues in POS tagging systems is identifying unknown words. This paper investigates all tags that the Maximum Likelihood Estimation method assigns the words existing in the text (including known and unknown) by proposing a graph-based method and correcting them. To do so, a graph is created from the training corpus including the part of speech sequence in the sentences. Then, sentences tagged with Maximum Likelihood Estimation will be corrected by traversing the graph. It should be noted that different methods have been proposed, implemented, and evaluated for tagging using graphs. Next, by investigating pros and cons, a method is proposed which tags the unknown words with the accuracy of 86.84% and the known words with the accuracy of 97.54%. In conclusion, the overall accuracy of the method is calculated as 96.78%, which is an improvement in comparison to the Maximum Likelihood Estimation method and consequently, the graph method shows an acceptable performance in part of speech tagging and is more reliable. © 2021, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Part of speech tagging Natural language processing MLE tagger Data science Text processing

来源：评论

学校读者我要写书评

暂无评论

SEOE:an option graph based semantically embedding method for prenatal depression detection

引用

Frontiers of computer Science 2024年第6期18卷 245-258页

作者： Xiaosong HAN Mengchen CAO Dong XU Xiaoyue FENG Yanchun LIANG Xiaoduo LANG Renchu GUAN College of Computer Science and Technology Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of EducationJilin UniversityChangchun 130012China Department of Electrical Engineering and Computer Science and Christopher S.Bond Life Sciences Center University of MissouriColumbiaMO 65211USA Department of Computer Science and Technology Zhuhai Laboratory of Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of EducationZhuhai College of Science and TechnologyZhuhai 519041China Jilin Provincial Institute of Population Science and Technology Changchun 130000China

Prenatal depression,which can affect pregnant women’s physical and psychological health and cause postpartum depression,is increasing ***,it is essential to detect prenatal depression early and conduct an attribution *** studies have used questionnaires to screen for prenatal depression,but the existing methods lack *** diagnose the early signs of prenatal depression and identify the key factors that may lead to prenatal depression from questionnaires,we present the semantically enhanced option embedding(SEOE)model to represent questionnaire *** can quantitatively determine the relationship and patterns between options and *** first quantifies options and resorts them,gathering options with little difference,since Word2Vec is highly dependent on *** resort task is transformed into an optimization problem involving the traveling salesman ***,all questionnaire samples are used to train the options’vector using ***,an LSTM and GRU fused model incorporating the cycle learning rate is constructed to detect whether a pregnant woman is suffering from *** verify the model,we compare it with other deep learning and traditional machine learning *** experiment results show that our proposed model can accurately identify pregnant women with depression and reach an F1 score of *** most relevant factors of depression found by SEOE are also verified in the *** addition,our model is of low computational complexity and strong generalization,which can be widely applied to other questionnaire analyses of psychiatric disorders.

关键词： questionnaire analyses text classification graph representation learning traveling salesman problem prenatal depression

来源：评论

学校读者我要写书评

暂无评论

Lightweight object detection algorithm for automatic driving scenarios

引用

International Journal of Wireless and Mobile Computing 2024年第1期26卷 74-82页

作者： Zhou, Tu Ming, Chen College of Computer and Information Technology China Three Gorges University Yichang Hubei China Hubei Key Laboratory of Intelligent Vision-Based Monitoring for Hydroelectric Engineering Yichang Hubei China

Aiming to solve the problems of large model size, unbalanced detection speed and detection accuracy of traditional target-detection algorithms in autonomous driving scenarios, a lightweight YOLO algorithm is proposed based on YOLOv4. First, the lightweight network Mobilenetv1 was used to replace the original YOLOv4 feature-extraction network and a Depth-Wise Cross-Stage Part module (DW-CSP) was proposed to improve the detection speed. Then, a new Lish activation function was designed and the K-means++ clustering algorithm was used to regenerate prior frames of different scales. Finally, the FocalLoss loss function was introduced instead of the cross-entropy loss function. Experiments show that compared with the YOLOv4 algorithm, the improved YOLO algorithm improves the detection accuracy by 1.72% and the detection speed by 53%, and the model size is reduced by about four times. The algorithm is more in line with the target-detection requirements of autonomous driving scenarios. Copyright © 2024 Inderscience Enterprises Ltd.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Demonstrating the Transient System Impact of Cyber-Physical Events Through Scalable Transmission and Distribution (T&D) Co-Simulation

引用

CSEE Journal of Power and Energy Systems 2025年第1期11卷 329-339页

作者： Mengmeng Cai Wenbo Wang Xin Fang Anthony R.Florita Michael Ingram Dane Christensen National Renewable Energy Laboratory GoldenCO15013USA Department of Electrical and Computer Engineering Mississippi State UniversityUSA

Modern power systems become more vulnerable to cyber threats due to their growing interconnectivity, interdependence, and complexity. Widespread deployment of distributed energy resources (DERs) further expands the threat landscape to the grid edge, where fewer cybersecurity protections exist. In this article, a systematic cyber-physical events demonstration, enabled by an integrated transmission, distribution, and communication co-simulation framework, is performed. It analyzes cyber risks to power grid under DER-enabled automatic generation control from different angles. Unlike existing works, the simulation captures millisecond-to-minutes frequency and voltage transient dynamics at a cross-region system scale.

关键词： Cyber-physical events distributed energy resources T&D dynamic co-simulation

来源：评论

学校读者我要写书评

暂无评论

Gender-Based Analysis of User Reactions to Facebook Posts

引用

Big Data Mining and Analytics 2024年第1期7卷 75-86页

作者： Yassine El Moudene Jaafar Idrais Rida El Abassi Abderrahim Sabour Mathematical Engineering and Computer Science Laboratory Faculty of SciencesIbn Zohr UniversityAgadir 8706Morocco Department of Computer Science Mathematical−High School of Technology Ibn Zohr UniversityAgadir 8706Morocco

Online Social Networks(OSNs)are based on the sharing of different types of information and on various interactions(comments,reactions,and sharing).One of these important actions is the emotional reaction to the *** diversity of reaction types available on Facebook(namely FB)enables users to express their feelings,and its traceability creates and enriches the users’emotional identity in the virtual *** paper is based on the analysis of 119875012 FB reactions(Like,Love,Haha,Wow,Sad,Angry,Thankful,and Pride)made at multiple levels(publications,comments,and sub-comments)to study and classify the users’emotional behavior,visualize the distribution of different types of reactions,and analyze the gender impact on emotion *** of these can be achieved by addressing these research questions:who reacts the most?Which emotion is the most expressed?

关键词： profiling knowledge extraction data mining emotion mining social media data crawling Facebook reactions gender

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：