检索结果-内蒙古大学图书馆

Dual Branch PnP Based Network for Monocular 6D Pose Estimation

Intelligent Automation & Soft Computing 2023年第6期36卷 3243-3256页

作者： Jia-Yu Liang Hong-Bo Zhang Qing Lei Ji-Xiang Du Tian-Liang Lin Department of Computer Science and Technology Huaqiao UniversityXiamen361000China Xiamen Key Laboratory of Computer Vision and Pattern Recognition Huaqiao UniversityXiamen361000China Fujian Key Laboratory of Big Data Intelligence and Security Huaqiao UniversityXiamen361000China College of Mechanical Engineering and Automation Xiamen361000China

Monocular 6D pose estimation is a functional task in the field of com-puter vision and *** recent years,2D-3D correspondence-based methods have achieved improved performance in multiview and depth data-based ***,for monocular 6D pose estimation,these methods are affected by the prediction results of the 2D-3D correspondences and the robustness of the per-spective-n-point(PnP)*** is still a difference in the distance from the expected estimation *** obtain a more effective feature representation result,edge enhancement is proposed to increase the shape information of the object by analyzing the influence of inaccurate 2D-3D matching on 6D pose regression and comparing the effectiveness of the intermediate ***,although the transformation matrix is composed of rotation and translation matrices from 3D model points to 2D pixel points,the two variables are essentially different and the same network cannot be used for both variables in the regression ***,to improve the effectiveness of the PnP algo-rithm,this paper designs a dual-branch PnP network to predict rotation and trans-lation ***,the proposed method is verified on the public LM,LM-O and YCB-Video *** ADD(S)values of the proposed method are 94.2 and 62.84 on the LM and LM-O datasets,*** AUC of ADD(-S)value on YCB-Video is *** experimental results show that the performance of the proposed method is superior to that of similar methods.

关键词： 6D pose monocular RGB edge enhancement dual-branch PnP 2D-3D correspondence

来源：评论

学校读者我要写书评

暂无评论

Smart Phone for Measurement of Reflectivity of Road Pavement Markings 8

Smart Phone for Measurement of Reflectivity of Road Pavement...

引用

8th IEEE International Conference on Computational System and Information Technology for Sustainable Solutions, CSITSS 2024

作者： Anjaneyappa, V. Varuna, M. Archana, M.R. Sunil, S. Holla, Ravishankar Vaidya, Shrish Shrinath Mahendra, B.M. Department of Civil Engineering R V College of Engineering India Department of Ece R V College of Engineering India Vidyashilp University Department of Computer vision Bengaluru India

ISBN: (纸本)9798331505462

Thermoplastic road pavement markings guide, warn, and inform road users, contributing significantly to road safety. Pavement markings play an important role in enhancing road safety by providing visual guidance and information to drivers. Pavement markings help to improve lane discipline, delineate traffic flow and communicate important messages to road users. Portable reflectometers are used for measurement of reflectivity. Reflectivity measurements are generally carried out during the laying operations of pavement markings. The reflectometer is costly and often not available regularly with engineers of road authorities and contractors. Hence quality of reflectivity is assessed through visual means during maintenance period. Smart phones which are handy and are with all, if made used for measuring quality of reflectivity during maintenance will be more useful for quick and relatively fair assessment of quality for any intervention required will be useful to all stake holders in enhancing the road safety. An attempt is made in the study to study the feasibility of using smart phone for measuring reflectivity. The study indicate use of smart phones for assessing the maintenance interventions of pavement marking. © 2024 IEEE.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

Improved Belief Propagation Decoder for LDPC-CRC-Polar Codes with Bit-Freezing

引用

China Communications 2024年第7期21卷 135-148页

作者： Qasim Jan Yin Chao Pan Zhiwen Muhammad Furqan Zakir Ali You Xiaohu National Mobile Communications Research Laboratory Southeast UniversityNanjing 210096China Purple Mountain Laboratories Nanjing 211100China Department of Computer Science National University of Computer and Emerging Sciences Peshawar Campus 25100Pakistan Department of Software Engineering Capital University of Science and Technology(CUST)Islamabad 44000Pakistan Department of Computer Sciences Bahria University Lahore CampusPakistan

Though belief propagation bit-flip(BPBF)decoding improves the error correction performance of polar codes,it uses the exhaustive flips method to achieve the error correction performance of CA-SCL decoding,thus resulting in high decoding complexity and *** alleviate this issue,we incorporate the LDPC-CRC-Polar coding scheme with BPBF and propose an improved belief propagation decoder for LDPC-CRC-Polar codes with bit-freezing(LDPCCRC-Polar codes BPBFz).The proposed LDPCCRC-Polar codes BPBFz employs the LDPC code to ensure the reliability of the flipping set,i.e.,critical set(CS),and dynamically update *** modified CS is further utilized for the identification of error-prone *** proposed LDPC-CRC-Polar codes BPBFz obtains remarkable error correction performance and is comparable to that of the CA-SCL(L=16)decoder under medium-to-high signal-to-noise ratio(SNR)*** gains up to 1.2dB and 0.9dB at a fixed BLER=10-4compared with BP and BPBF(CS-1),*** addition,the proposed LDPC-CRC-Polar codes BPBFz has lower decoding latency compared with CA-SCL and BPBF,i.e.,it is 15 times faster than CA-SCL(L=16)at high SNR regions.

关键词： belief propagation bit-flipping concatenated codes LDPC-CRC-Polar codes polar codes

来源：评论

学校读者我要写书评

暂无评论

Text-Guided Portrait Image Matting

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第8期5卷 4149-4162页

作者： Xu, Yong Yao, Xin Liu, Baoling Quan, Yuhui Ji, Hui South China University of Technology School of Computer Science and Engineering Guangzhou510000 China Communication and Computer Network Laboratory of Guangdong Guangzhou510641 China Peng Cheng Laboratory Shenzhen518000 China National University of Singapore Department of Mathematics 119076 Singapore

Image matting is a technique used to separate the foreground of an image from the background, which estimates an alpha matte that indicates pixel-wise degree of transparency. To precisely extract target objects and address the ambiguity of solutions in image matting, many existing approaches employ a trimap or background image provided by the user as additional input to guide the matting process. This article introduces a novel matting paradigm termed text-guided image matting, utilizing a textual description of the foreground object as a guiding element. In contrast to trimap or background-based methods, text-guided matting offers a user-friendly interface, providing semantic clues for the objects of interest. Moreover, it facilitates batch processing across multiple frames featuring the same objects of interest. The proposed text-guided matting approach is implemented through a deep neural network (NN) comprising three-stage cross-modal feature fusion and two-step alpha matte prediction. Experimental results on portrait matting demonstrate the competitive performance of our text-guided approach compared to existing trimap-based and background-based methods. © 2020 IEEE.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Analysis and Classification of Fake News Using Sequential Pattern Mining

引用

Big Data Mining and Analytics 2024年第3期7卷 942-963页

作者： M.Zohaib Nawaz M.Saqib Nawaz Philippe Fournier-Viger Yulin He College of Computer Science and Software Engineering Shenzhen UniversityShenzhen 518060 Guangdong Laboratory of Artificial Intelligence and Digital Economy(SZ) Shenzhen 518107China Department of Computer Science Faculty of Computing and Information TechnologyUnivesity of SargodhaSargodha 40100Pakistan

Disinformation,often known as fake news,is a major issue that has received a lot of attention *** researchers have proposed effective means of detecting and addressing *** machine and deep learning based methodologies for classification/detection of fake news are content-based,network(propagation)based,or multimodal methods that combine both textual and visual *** introduce here a framework,called FNACSPM,based on sequential pattern mining(SPM),for fake news analysis and *** this framework,six publicly available datasets,containing a diverse range of fake and real news,and their combination,are first transformed into a proper ***,algorithms for SPM are applied to the transformed datasets to extract frequent patterns(and rules)of words,phrases,or linguistic *** obtained patterns capture distinctive characteristics associated with fake or real news content,providing valuable insights into the underlying structures and commonalities of ***,the discovered frequent patterns are used as features for fake news *** framework is evaluated with eight classifiers,and their performance is assessed with various *** experiments were performed and obtained results show that FNACSPM outperformed other state-of-the-art approaches for fake news classification,and that it expedites the classification task with high accuracy.

关键词： disinformation fake news sequential pattern mining(SPM) frequent patterns classification

来源：评论

学校读者我要写书评

暂无评论

Frequency disentangled residual network

引用

Multimedia Systems 2024年第1期30卷 1-13页

作者： Singh, Satya Rajendra Yedla, Roshan Reddy Dubey, Shiv Ram Sanodiya, Rakesh Kumar Chu, Wei-Ta Computer Science and Engineering Group Indian Institute of Information Technology Andhra Pradesh Sri India Stony Brook University Stony BrookNY United States Computer Vision and Biometrics Lab Indian Institute of Information Technology Uttar Pradesh Allahabad India Department of Computer Science and Information Engineering National Cheng Kung University Tainan Taiwan

Residual networks (ResNets) have been utilized for various computer vision and image processing applications. The residual connection improves the training of the network with better gradient flow. A residual block consists of a few convolutional layers having trainable parameters, which leads to overfitting. Moreover, the present residual networks are not able to utilize the high- and low-frequency information suitably, which also challenges the generalization capability of the network. In this paper, a frequency-disentangled residual network (FDResNet) is proposed to tackle these issues. Specifically, FDResNet includes separate connections in the residual block for low- and high-frequency components, respectively. Basically, the proposed model disentangles the low- and high-frequency components to increase the generalization ability. Moreover, the computation of low- and high-frequency components using fixed filters further avoids the overfitting. The proposed model is tested on benchmark CIFAR-10/100, Caltech, and TinyImageNet datasets for image classification. The performance of the proposed model is also tested in the image retrieval framework. It is noticed that the proposed model outperforms its counterpart residual model. The effect of kernel size and standard deviation is also evaluated. The impact of the frequency disentangling is also analyzed using a saliency map. © 2024, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Optimization of Residential Net Load using Demand Response and Battery Storage 3

Optimization of Residential Net Load using Demand Response a...

引用

3rd International Conference on Energy Transition in the Mediterranean Area, SyNERGY MED 2024

作者： Bracho, Jorge Ilia, Neofytos Makrides, George Tseng, Alex R. Herodotou, Panagiotis Georgiou, George E. PV Technology Laboratory Department of Electrical and Computer Engineering Cyprus for Intelligent Nicosia Cyprus Princeton University Electrical and Computer Engineering NJ United States

ISBN: (纸本)9798350375923

Demand side management (DSM) and solar-plus-storage systems are enabling technologies that facilitate consumers to increase self-consumption (SC), while reducing electricity costs through efficient and intelligent electricity usage. Even though many demand response (DR) strategies have been presented for the residential sector, a major challenge remains the joint optimal utilization and synergies of DR and the battery systems flexibility scheduling. This paper explores how the optimization of DR and battery energy storage systems (BESS) scheduling can notably improve the net load profile of residential users. The obtained results indicate that the optimized DR model and battery storage effectively support load shifting and peak energy utilization. Specifically, the analysis suggests that the combination of DR and an 8kWh battery storage system increased the SC from 55.04% to 95.84% and the SS from 37.50% to 66.88%, compared to a baseline scenario (without battery storage and DR actions). Ultimately, the proposed optimization achieved a higher degree of energy autonomy for the yearly profile of a median household by minimizing the sum of absolute values of the net load with load shifting and BESS charging/discharging. Finally, the optimization model can be used by aggregators and system operators for scheduling and optimizing flexibility actions. © 2024 IEEE.

关键词： Demand response

来源：评论

学校读者我要写书评

暂无评论

Energy Efficient Hardware Acceleration of Neural Networks with Power-of-Two Quantisation

Energy Efficient Hardware Acceleration of Neural Networks wi...

引用

International Conference on computer vision and Graphics, ICCVG 2022

作者： Przewlocka-Rus, Dominika Kryjak, Tomasz Embedded Vision Systems Group Computer Vision Laboratory Department of Automatic Control and Robotics AGH University of Science and Technology Krakow Poland

ISBN: (纸本)9783031220241

Deep neural networks virtually dominate the domain of most modern vision systems, providing high performance at a cost of increased computational complexity. Since for those systems it is often required to operate both in real-time and with minimal energy consumption (e.g., for wearable devices or autonomous vehicles, edge Internet of Things (IoT), sensor networks), various network optimisation techniques are used, e.g., quantisation, pruning, or dedicated lightweight architectures. Due to the logarithmic distribution of weights in neural network layers, a method providing high performance with significant reduction in computational precision (for 4-bit weights and less) is the Power-of-Two (PoT) quantisation (and therefore also with a logarithmic distribution). This method introduces additional possibilities of replacing the typical for neural networks Multiply and ACcumulate (MAC—performing, e.g., convolution operations) units, with more energy-efficient Bitshift and ACcumulate (BAC). In this paper, we show that a hardware neural network accelerator with PoT weights implemented on the Zynq UltraScale + MPSoC ZCU104 SoC FPGA can be at least 1.4x more energy efficient than the uniform quantisation version. To further reduce the actual power requirement by omitting part of the computation for zero weights, we also propose a new pruning method adapted to logarithmic quantisation. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： System-on-chip

来源：评论

学校读者我要写书评

暂无评论

rafPS:A shapley-based visual analytics approach to interpret traffic

引用

Computational Visual Media 2024年第6期10卷 1101-1119页

作者： Zezheng Feng Yifan Jiang Hongjun Wang Zipei Fan Yuxin Ma Shuang-Hua Yang Huamin Qu Xuan Song Department of Computer Science and Engineering Southern University of Science and TechnologyShenzhen 18055China Department of Computer Science and Engineering Hong Kong University of Science and TechnologyHong KongChina Department of Computer Science University of ReadingBerkshire RG66AHUK Center for Spatial Information Science the University of TokyoTokyo 113-00331Japan Shenzhen Key Laboratory of Safety and Security for Next Generation of Industrial Internet Southern University of Science and TechnologyShenzhen 518055China

Recent achievements in deep learning(DL)have demonstrated its potential in predicting traffic *** predictions are beneficial for understanding the situation and making traffic control ***,most state-of-the-art DL models are consi-dered“black boxes”with little to no transparency of the underlying mechanisms for end *** previous studies attempted to“open the black box”and increase the interpretability of generated ***,handling complex models on large-scale spatiotemporal data and discovering salient spatial and temporal patterns that significantly influence traffic flow remain *** overcome these challenges,we present TrafPS,a visual analytics approach for interpreting traffic prediction outcomes to support decision-making in traffic management and urban *** measurements region SHAP and trajectory SHAP are proposed to quantify the impact of flow patterns on urban traffic at different *** on the task requirements from domain experts,we employed an interactive visual interface for the multi-aspect exploration and analysis of significant flow *** real-world case studies demonstrate the effectiveness of TrafPS in identifying key routes and providing decision-making support for urban planning.

关键词： data visualization model interpretation urban planning urban visual analytics

来源：评论

学校读者我要写书评

暂无评论

Multi-label Textual Data Augmentation Using BERT Based on Transformer Model 1

引用

13th International Conference on Information Systems and Advanced Technologies, ICISAT 2023

作者： Rouabhi, Roumaissa Hammami, Nacer Eddine Azizi, Nabiha Benzebouchi, Nacer Eddine Chaib, Rim LabGed Laboratory Badji Mokhtar University Annaba Algeria Computer Engineering Department College of Engineering and Computer Science Mustaqbal University Buraydah Saudi Arabia

ISBN: (数字)9783031605918

ISBN: (纸本)9783031605901

In recent years, the healthcare field has taken a turn towards the AI domain, with applications such as image segmentation and medical report classification leading researchers to delve deeper into this area. On the other hand, the natural language processing has taken another turn with the arrival of the transformer models, the deep learning pre-trained models on a large corpus of documents, permitting an optimal use of medical text documents. However, the lack of diversification in text data more specifically multilabel data can be a constraint to get performant results. In this study, we are utilizing BioBERT for multilabel text classification, with the aim of achieving more refined results by implementing a data augmentation approach using a BERT-based transformer model. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Deep learning

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：