检索结果-内蒙古大学图书馆

Control, Robotics and Informatics (ICCRI), International Conference on

作者： Hadi Salloum Mohammad Reza Bahrami Artem Matevosian Sofia Gamershmidt Ali Jnadi Manuel Mazzara Faculty of Computer Science and Engineering Innopolis University Innopolis Russia Cyber-physical systems lab Innopolis University Innopolis Russia Institute of Robotics and Computer Vision Innopolis University Innopolis Russia

ISBN: (数字)9798350380309

ISBN: (纸本)9798350380316

This paper explores the integration of quantum computing, specifically quantum annealing, into robotics for inspecting electrical transmission lines. By using quantum annealing's computational power, we address the dynamics of robot inspectors on transmission line conductors, enhancing the computational efficiency of managing the movements of robot inspectors on transmission line conductors. The use of these robots is crucial for performing efficient and safe inspections. We discuss the mathematical foundations of quantum annealing, transforming differential equations governing robot dynamics into Ising model Hamiltonians suitable for quantum annealing devices. Through experiments using D-Wave's ‘Advantage’ quantum annealer, we demonstrate the viability of quantum annealing in solving complex robotics problems, paving the way for advanced applications in the field.

关键词： Annealing Power transmission lines Computational modeling Quantum mechanics Differential equations Inspection Quantum annealing Conductors Mathematical models Robots

来源：评论

学校读者我要写书评

暂无评论

Stochastic Recursive Gradient Descent Optimization-based on Foreground Features of Fisher Vector 14

Stochastic Recursive Gradient Descent Optimization-based on ...

引用

14th International Conference on Digital Image Processing, ICDIP 2022

作者： Kamaleldin, Mohamed Gamal M. Abu-Bakar, Syed A.R. Sheikh, Usman Ullah Electronics and Communications Engineering Department Arab Academy for Science and Technology Cairo11736 Egypt Computer Vision Video and Image Processing Research Lab School of Electrical Engineering Universiti Teknologi Malaysia Johor Skudai81300 Malaysia

ISBN: (纸本)9781510657564

Human action recognition has been one of the hot topics in computer vision both from the handcrafted and deep learning approaches. In the handcrafted approach, the extracted features are encoded for reducing the size of these features. Amonsgt the state-of-the-art approaches is to encode these visual features using the Gaussian mixture model. However, the size of the codebook is an issue in terms of the computation complexity, especially for large-scale data as it requires encoding using a large codebook. In this paper, we introduced the use of different optimizers to reduce the codebook size while boosting its accuracy. To illustrate the performance, first we use the improved dense trajectories (IDT) to extract the handcrafted features. This is followed with encoding the descriptor using Fisher kernel-based codebook using the Gaussian mixture model. Next, the support vector machine is used to classify the categories. We then use and compare five different Stochastic gradient descent optimization techniques to modify the number of Gaussian components. In this manner we are able to select the discriminative foreground features (as represented by the final number of Gaussian components), and omit the background features. Finally, to show the performance improvement of the proposed method, we implement this technique to two datasets UCF101 and HMDB51. © 2022 SPIE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Recurrence sorting method for improved accuracy of unconstrained fast-moving vehicle license plate recognition system

Recurrence sorting method for improved accuracy of unconstra...

引用

Artificial Intelligence for Industries (AI4I)

作者： Abu Anas Ibn Samad Towneda Akhter Prema Computer Vision Engineering Lab Sigmind.ai Limited Dhaka Bangladesh Computer Vision Researcher Bangladesh University of Professionals Dhaka Bangladesh

Automatic Real-Time Vehicle License Plate recognition systemsface a wide variety of challenges to accurately reading the number sequences present in license plates when deployed in the real world. The uncertainty of the real-world license plate recognition system is addressed in this research and proposes a novel method of filtering out inaccurate results based on recurrence-based sorting of the best readable character sequences. The problems of unconstrained real-world real-time license plate recognition have been discussed thoroughly throughout the paper and redefined the problem statement towards attaining the best readability instead of best visibility. An end-to-end cascade neural network architecture has been developed to capture license plate readings in real time. Then the novel recurrence-based iteration method was introduced to sort the Top 1 of the best reading of a unique license plate tracked across the frame where character sequence reading accuracy has been improved by up to 54% when combined with the introduced garbage factor filtering method. The experimental evidence indicated that the traditional confidence-based sorting is prone to failure due to unconstrained real-world uncertainties and accuracy is thoroughly compared with our novel method to illustrate novelty. The system has been deployed in the real world on an embedded system with a substantial amount of vehicle traffic for testing and validation.

关键词： Industries Uncertainty Embedded systems Filtering Face recognition Neural networks Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Deep fake Detection using deep learning techniques: A Literature Review

Deep fake Detection using deep learning techniques: A Litera...

引用

International Conference on Control Communication & Computing India (ICCC)

作者： Amala Mary Anitha Edison Computer Vision Lab College of Engineering Trivandrum Kerala Affiliated to APJ Abdul Kalam Technological University Trivandrum Kerala India

Deep learning is a sophisticated and adaptable technique that has found widespread use in fields such as natural language processing, machine learning, and computer vision. It is one of the most recent deep learning-powered applications to emerge. Deep fakes are altered, high-quality, realistic videos/images that have lately gained popularity. Many incredible uses of this technology are being investigated. Malicious uses of fake videos, such as fake news, celebrity pornographic videos, financial scams, and revenge porn are currently on the rise in the digital world. As a result, celebrities, politicians, and other well-known persons are particularly vulnerable to the Deep fake detection challenge. Numerous research has been undertaken in recent years to understand how deep fakes function and many deep learning-based algorithms to detect deep fake videos or pictures have been *** study comprehensively evaluates deep fake production and detection technologies based on several deep learning algorithms. In addition, the limits of current approaches and the availability of databases in society will be discussed. A deep fake detection system that is both precise and automatic. Given the ease with which deep fake videos/images may be generated and shared, the lack of an effective deep fake detection system creates a serious problem for the world. However, there have been various attempts to address this issue, and deep learning-related solutions outperform traditional approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive autonomy in human-on-the-loop vision-based robotics systems 1

Adaptive autonomy in human-on-the-loop vision-based robotics...

引用

1st IEEE/ACM Workshop on AI engineering - Software engineering for AI, WAIN 2021

作者： Abraham, Sophia Carmichael, Zachariah Banerjee, Sreya Vidalmata, Rosaura Agrawal, Ankit Al Islam, Md Nafee Scheirer, Walter Cleland-Huang, Jane University of Notre Dame Computer Vision Research Lab Department of Computer Science and Engineering South Bend United States University of Notre Dame DroneResponse Lab Department of Computer Science and Engineering South Bend United States

ISBN: (纸本)9781665444705

computer vision approaches are widely used by autonomous robotic systems to sense the world around them and to guide their decision making as they perform diverse tasks such as collision avoidance, search and rescue, and object manipulation. High accuracy is critical, particularly for Human-on-the-loop (HoTL) systems where decisions are made autonomously by the system, and humans play only a supervisory role. Failures of the vision model can lead to erroneous decisions with potentially life or death consequences. In this paper, we propose a solution based upon adaptive autonomy levels, whereby the system detects loss of reliability of these models and responds by temporarily lowering its own autonomy levels and increasing engagement of the human in the decision-making process. Our solution is applicable for vision-based tasks in which humans have time to react and provide guidance. When implemented, our approach would estimate the reliability of the vision task by considering uncertainty in its model, and by performing covariate analysis to determine when the current operating environment is illmatched to the model's training data. We provide examples from DroneResponse, in which small Unmanned Aerial Systems are deployed for Emergency Response missions, and show how the vision model's reliability would be used in addition to confidence scores to drive and specify the behavior and adaptation of the system's autonomy. This workshop paper outlines our proposed approach and describes open challenges at the intersection of computer vision and Software engineering for the safe and reliable deployment of vision models in the decision making of autonomous systems. © 2021 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

CERTAINTY IN, CERTAINTY OUT REVQCS FOR QUANTUM MACHINE LEARNING

arXiv

引用

arXiv 2023年

作者： Helgesen, Hannah D. Felsberg, Michael Larsson, Jan-Åke Department of Electrical Engineering Linköpings University Linköping58183 Sweden The Computer Vision Lab Division of Information Coding

The field of Quantum Machine Learning (QML) has emerged recently in the hopes of finding new machine learning protocols or exponential speedups for classical ones. Apart from problems with vanishing gradients and efficient encoding methods, these speedups are hard to find because the sampling nature of quantum computers promotes either simulating computations classically or running them many times on quantum computers in order to use approximate expectation values in gradient calculations. In this paper, we make a case for setting high single-sample accuracy as a primary goal. We discuss the statistical theory which enables highly accurate and precise sample inference, and propose a method of reversed training towards this end. We show the effectiveness of this training method by assessing several effective variational quantum circuits (VQCs), trained in both the standard and reversed directions, on random binary subsets of the MNIST and MNIST Fashion datasets, on which our method provides an increase of 10-15% in single-sample inference accuracy. © 2023, CC BY.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Entropy: A New Parameter for Image Deciphering

Entropy: A New Parameter for Image Deciphering

引用

International Conference on Recent Trends in Machine Learning, IOT, Smart Cities and Applications, ICMISC 2020

作者： Cheggoju, Naveen Nawandar, Neha K. Satpute, Vishal R. Image Processing and Computer Vision Lab Department of Electronics and Communication Engineering Visvesvaraya National Institute of Technology Nagpur India

ISBN: (纸本)9789811572333

Data and information, these two terms may look quite similar and also sometimes used with the same meaning. But in-depth, these terms are completely different from each other. This paper mainly focuses on this difference to extract the encrypted information from the data (importantly image data). Here, every aspect of the study and the way of formulation are explained using "Einstein’s theory of relativity" and "Arrow of time" for better understanding. Einstein’s theory is used to explain "how similar things can be seen in different ways?" (here data and information) and arrow of time is used to explain "how the correct information can be extracted from the data?". To explain this concept, an image encrypted using a chaotic logistic map is used. The edge information present in this data is taken as the parameter to differentiate the unorganized data and organized data (correct information). Here, a new parameter called "Randomness parameter (Rp)" is introduced, which gives the entropy (randomness) of the data. The outcome of this parameter is used to differentiate the data and correct information. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning based Bangladeshi Vehicle Classification using Fine-Tuned Multi-class Vehicle Image Network (MVINet) Model

A Deep Learning based Bangladeshi Vehicle Classification usi...

引用

Next-Generation Computing, IoT and Machine Learning (NCIM), International Conference on

作者： Tanvir Ahmed Farzana Sharmin Mou Abu Anas Ibn. Samad Dept. of Computer Science and Engineering Dhaka University of Engineering & Technology Dhaka Gazipur Bangladesh Dept. of Computer Science University of Birmingham Birmingham UK Computer Vision Engineering Lab Sigmind.ai Limited Dhaka Bangladesh

The classification of vehicles is an important task in many applications, including traffic management, surveillance, and law enforcement. In Bangladesh, vehicle classification has become increasingly challenging due to the rapid growth in the number of vehicles on the roads. In this study, a novel deep learning-based Bangladeshi vehicle classification model using fine-tuned Multi-class Vehicle Image Network (MVINet) based on DenseNet201 with four added layers has been proposed. Our approach uses convolutional neural networks (CNNs) to extract features from images of vehicles. To make our dataset, we employ a YOLO (You Only Look Once) model for initial vehicle detection, followed by manual filtering and augmentation of the dataset to improve classification accuracy. The proposed method demonstrates superior performance compared to manual data collection methods. We evaluated our approach using standard metrics such as accuracy, precision, recall, and F1 score. Our model achieved an accuracy of 97.06%, precision of 97.17%, recall of 97.24%, and F1-score of 97.12% indicating high performance in classifying vehicles. We also compared our approach with state-of-the-art techniques and found that the proposed deep learning-based approach outperformed them significantly. The proposed approach has the potential to improve traffic management and law enforcement in Bangladesh. It can be used to monitor traffic flow, detect traffic violations, and identify stolen vehicles. Overall, this study demonstrates the effectiveness of deep learning in Bangladeshi vehicle detection and classification and highlights the importance of using advanced technologies to address the challenges of a rapidly changing transportation landscape.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Relative-Interior Solution for the (Incomplete) Linear Assignment Problem with Applications to the Quadratic Assignment Problem

arXiv

引用

arXiv 2023年

作者： Dlask, Tomáš Savchynskyy, Bogdan Faculty of Electrical Engineering Czech Technical University Prague Czech Republic Computer Vision and Learning Lab IWR University of Heidelberg Germany

We study the set of optimal solutions of the dual linear programming formulation of the linear assignment problem (LAP) to propose a method for computing a solution from the relative interior of this set. Assuming that an arbitrary dual-optimal solution and an optimal assignment are available (for which many efficient algorithms already exist), our method computes a relative-interior solution in linear time. Since the LAP occurs as a subproblem in the linear programming (LP) relaxation of the quadratic assignment problem (QAP), we employ our method as a new component in the family of dual-ascent algorithms that provide bounds on the optimal value of the QAP. To make our results applicable to the incomplete QAP, which is of interest in practical use-cases, we also provide a linear-time reduction from the incomplete LAP to the complete LAP along with a mapping that preserves optimality and membership in the relative interior. Our experiments on publicly available benchmarks indicate that our approach with relative-interior solution can frequently provide bounds near the optimum of the LP relaxation and its runtime is much lower when compared to a commercial LP solver. Copyright © 2023, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Disentangling Hierarchical Features for Anomalous Sound Detection Under Domain Shift

Disentangling Hierarchical Features for Anomalous Sound Dete...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Guan, Jian Tian, Jiantong Zhu, Qiaoxi Xiao, Feiyang Zhang, Hejing Liu, Xubo Group of Intelligent Signal Processing College of Computer Science and Technology Harbin Engineering University Harbin150001 China Acoustics Lab University of Technology Sydney UltimoNSW2007 Australia Centre for Vision Speech and Signal Processing University of Surrey GuildfordGU2 7XH United Kingdom

ISBN: (纸本)9798350368741

Anomalous sound detection (ASD) encounters difficulties with domain shift, where the sounds of machines in target domains differ significantly from those in source domains due to varying operating conditions. Existing methods typically employ domain classifiers to enhance detection performance, but they often overlook the influence of domain-unrelated information. This oversight can hinder the model's ability to clearly distinguish between domains, thereby weakening its capacity to differentiate normal from abnormal sounds. In this paper, we propose a Gradient Reversal-based Hierarchical feature Disentanglement (GRHD) method to address the above challenge. GRHD uses gradient reversal to separate domain-related features from domain-unrelated ones, resulting in more robust feature representations. Additionally, the method employs a hierarchical structure to guide the learning of fine-grained, domain-specific features by leveraging available metadata, such as section IDs and machine sound attributes. Experimental results on the DCASE 2022 Challenge Task 2 dataset demonstrate that the proposed method significantly improves ASD performance under domain shift. © 2025 IEEE.

关键词： Anomalous sound detection domain shift feature learning gradient reversal

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：