检索结果-内蒙古大学图书馆

4th International Conference on Robotics and Computer Vision, ICRCV 2022

作者： Matzinger, Heinrich Allgeier, Allegra Georgia Institute of Technology School of Mathematics Machine Learning Center AtlantaGA United States

ISBN: (数字)9781665481700

ISBN: (纸本)9781665481700

We show that image classification with Convolutional Neural Networks (CNNs) follows a different strategy than how humans recognize objects: while a human may consider the global shape or a 3D picture of the object, a CNN's decision is based mainly on recognizing local-patterns without taking into account their relative positions. We show this by feeding a CNN an image that has been cut into many squares and randomly reassembled. We observe that the original object is still recognized in the scrambled image with high probability up to a certain point. This allows us to estimate the size of the patterns used for recognizing objects by the CNN. We also show that for this analysis to make sense, we need to introduce an alternative class, "other"which contains a very vast amount of different motives, too vast for the CNN to learn. © 2022 IEEE.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

Track-before-detect algorithm based optimized interactive multiple model particle filtering for tracking maneuvering weak target

Track-before-detect algorithm based optimized interactive mu...

引用

2024 International Conference on Image Processing and Artificial Intelligence, ICIPAl 2024

作者： Wu, Xiaojia Yang, Jinlong School of Artificial Intelligence and Computer Science Jiangnan University Wuxi214122 China Engineering Research Center of Integration and Application of Digital Learning Technology Ministry of Education Beijing100039 China

ISBN: (纸本)9781510681514

This paper proposes an optimized algorithm for tracking maneuvering weak radar targets in complex sea environments. In the proposal, we first preprocesses radar echo images using the fractional Fourier transform (FrFT) to reduce clutter interference. Then, Feedback factor and residual resampling are introduced to optimize the interactive multiple model particle filtering (IMMPF) algorithm to achieve effective tracking of maneuvering targets. Additionally, the optimized IMMPF is combined with track before detect algorithm (TBD) to suppress clutter and accumulate target trajectory. Simulation experiment results demonstrate that the proposed algorithm can effectively track targets compared to other TBD algorithms. © 2024 SPIE.

关键词： Monte Carlo methods

来源：评论

学校读者我要写书评

暂无评论

Enhancing Skeleton-Based Action Recognition in Real-World Scenarios Through Realistic Data Augmentation

Enhancing Skeleton-Based Action Recognition in Real-World Sc...

引用

IEEE Winter Applications and Computer Vision Workshops (WACVW)

作者： Mickael Cormier Yannik Schmid Jürgen Beyerer Fraunhofer IOSB Karlsruhe Institute of Technology Fraunhofer Center for Machine Learning

Skeleton-based action recognition is a prominent research area that provides a concise representation of human motion. However, real-world scenarios pose challenges to the reliability of human pose estimation, which is fundamental to such recognition. The existing literature mainly focuses on laboratory experiments with near-perfect skeletons, and fails to address the complexities of the real world. To address this, we propose simple yet highly effective data augmentation techniques based on the observation of erroneous human pose estimation, which enhance state-of-the-art methods for real-world skeleton-based action recognition. These techniques yield significant improvements (up to +4.63 accuracy) on the widely used UAV Human Dataset, a benchmark for evaluating real-world action recognition. Experimental results demonstrate the effectiveness of our augmentation techniques in compensating for erroneous and noisy pose estimation, leading to significant improvements in action recognition accuracy. By bridging the gap between laboratory experiments and real-world scenarios, our work paves the way for more reliable and practical skeleton-based action recognition systems. To facilitate reproducibility and further development, the Skelbumentations library is released at https://***/MickaelCormier/Skelbumentations. This library provides the code implementation of our augmentation techniques, enabling researchers and practitioners to easily augment skeleton sequences and improve the performance of skeleton-based action recognition models in real-world applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

END-TO-END learning OF GAUSSIAN MIXTURE PRIORS FOR DIFFUSION SAMPLER

arXiv

引用

arXiv 2025年

作者： Blessing, Denis Jia, Xiaogang Neumann, Gerhard Autonomous Learning Robots Karlsruhe Institute of Technology Germany FZI Research Center for Information Technology Germany

Diffusion models optimized via variational inference (VI) have emerged as a promising tool for generating samples from unnormalized target densities. These models create samples by simulating a stochastic differential equation, starting from a simple, tractable prior, typically a Gaussian distribution. However, when the support of this prior differs greatly from that of the target distribution, diffusion models often struggle to explore effectively or suffer from large discretization errors. Moreover, learning the prior distribution can lead to mode-collapse, exacerbated by the mode-seeking nature of reverse Kullback-Leibler divergence commonly used in VI. To address these challenges, we propose end-to-end learnable Gaussian mixture priors (GMPs). GMPs offer improved control over exploration, adaptability to target support, and increased expressiveness to counteract mode collapse. We further leverage the structure of mixture models by proposing a strategy to iteratively refine the model by adding mixture components during training. Our experimental results demonstrate significant performance improvements across a diverse range of real-world and synthetic benchmark problems when using GMPs without requiring additional target evaluations. © 2025, CC BY.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Predicting Stock Market Trends Using Deep learning: A Case Study of Pakistan Stock Exchange

Predicting Stock Market Trends Using Deep Learning: A Case S...

引用

International Conference on Open Source Systems and Technologies (ICOSST)

作者： Maaz Balouch Faizan Hamayat Humza Fazal Abbasi Muhammad Qasim Javed Ali Mehrban Rana Fayyaz Ahmad Department of Business Studies Namal University Mianwali Pakistan Machine Learning and Deep Learning Lab Artificial Intelligence Technology Center National Center for Physics Islamabad Pakistan Machine Learning and Deep Learning Lab Artificial Intelligence Technology Center National Center for Physics Pakistan School of Electrical and Electronics Engineering Newcastle University Newcastle United Kingdom

ISBN: (数字)9798331508692

ISBN: (纸本)9798331508708

This research investigates the short-term stock price prediction in the Pakistan Stock Exchange (PSX) using Deep learning (DL) techniques. By integrating historical stock data, economic indicators, and market news, the research aims to address the limitations of traditional stock analysis methods. Data was collected and pre-processed from various sources, including the PSX, economic indicators, and market news. Four techniques were implemented: ARIMA, LSTM, BI-LSTM, and a hybrid CNN-BI-LSTM. Their performance was evaluated using RMSE, MAE, and MAPE metrics. Comparative analysis revealed that BILSTM outperformed the other techniques, with RMSE, MAE, and MAPE scores of 0.9298, 0.6099, and 13.9443, respectively. Despite ARIMA's lower accuracy, it had the fastest inference time, followed by LSTM, CNN-BI-LSTM, and BI-LSTM. Results indicate that using comprehensive data with DL models significantly improves stock price forecast accuracy, highlighting the potential of technological innovation in enhancing financial market decision-making. These DL algorithms can provide valuable insights for investors and analysts in the PSX, leading to better decision-making and more accurate economic predictions.

关键词： Deep learning Measurement Accuracy Economic indicators Biological system modeling Decision making Predictive models Prediction algorithms Data models Stock markets

来源：评论

学校读者我要写书评

暂无评论

Spreading Awareness Cybersecurity via Storytelling: A Systematic Literature Review 14th

Spreading Awareness Cybersecurity via Storytelling: A Syst...

引用

14th International Conference on Methodologies and Intelligent Systems for technology Enhanced learning, mis4TEL 2024

作者： Andriessen, Jerry Citro, Tiziano Palmieri, Giuseppina Pardijs, Mirjam Wise and Munro Learning Research The Hague Netherlands Department of Computer Science Università degli Studi di Salerno Salerno Italy Regional Center Information Communication Technology CeRICT scrl Naples Italy

ISBN: (纸本)9783031855603

Contribution: This Systematic Literature Review (SLR) aims to investigate how storytelling can effectively convey cybersecurity awareness for specific target groups in education, from different age groups. Background: Cybersecurity is increasingly pervasive, impacting nearly everyone globally. Therefore, there’s a critical need for widespread education on the risks and consequences of daily technology use. Research Questions:RQ1:Are there any methods to approach the topic of cybersecurity without age constraints?RQ2:What type of technology used emerges from our review?RQ3:Which are the major outcomes of the proposed initiatives? Methodology: We use PRISMA guidelines [22] with n=53 papers published until December 2023 identified and n=18 final relevant papers. Findings: This review identified delivery methods [8], within the research field of technology-enhanced learning, that address, by the introduction of storytelling approach, the spread of cybersecurity education, leading to increased awareness and engagement on cybersecurity issues. It confirms that traditional forms of education focusing solely on knowledge transmission are not well suited for developing learning and understanding in a highly dynamic area such as cybersecurity. These delivery methods aim at developing cybersecurity awareness through the storytelling approach, expanding the notion of "being secure" to that of "acting securely". © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Awareness Cybersecurity Digital Storytelling Engagement learning Replication Package

来源：评论

学校读者我要写书评

暂无评论

PATH INTEGRAL SAMPLER: A STOCHASTIC CONTROL APPROACH FOR SAMPLING 10

PATH INTEGRAL SAMPLER: A STOCHASTIC CONTROL APPROACH FOR SAM...

引用

10th International Conference on learning Representations, ICLR 2022

作者： Zhang, Qinsheng Chen, Yongxin Center for Machine Learning Georgia Institute of Technology United States School of Aerospace Engineering Georgia Institute of Technology United States

We present Path Integral Sampler (PIS), a novel algorithm to draw samples from unnormalized probability density functions. The PIS is built on the Schrödinger bridge problem which aims to recover the most likely evolution of a diffusion process given its initial distribution and terminal distribution. The PIS draws samples from the initial distribution and then propagates the samples through the Schrödinger bridge to reach the terminal distribution. Applying the Girsanov theorem, with a simple prior diffusion, we formulate the PIS as a stochastic optimal control problem whose running cost is the control energy and terminal cost is chosen according to the target distribution. By modeling the control as a neural network, we establish a sampling algorithm that can be trained end-to-end. We provide theoretical justification of the sampling quality of PIS in terms of Wasserstein distance when sub-optimal control is used. Moreover, the path integrals theory is used to compute importance weights of the samples to compensate for the bias induced by the sub-optimality of the controller and time-discretization. We experimentally demonstrate the advantages of PIS compared with other start-of-the-art sampling methods on a variety of tasks. © 2022 ICLR 2022 - 10th International Conference on learning Representationss. All rights reserved.

关键词： Probability density function

来源：评论

学校读者我要写书评

暂无评论

A Bitcoin Address Multi-Classification Mechanism Based on Bipartite Graph-Based Maximization Consensus

引用

Computer Modeling in Engineering & Sciences 2024年第4期139卷 783-800页

作者： Lejun Zhang Junjie Zhang Kentaroh Toyoda Yuan Liu Jing Qiu Zhihong Tian Ran Guo College of Information Engineering Yangzhou UniversityYangzhou225127China Cyberspace Institute Advanced Technology Guangzhou UniversityGuangzhou510006China Research and Development Center for E-Learning Ministry of EducationBeijing100039China Institute of High Performance Computing(IHPC) Agency for ScienceTechnology and Research(A∗STAR)Singapore138632Singapore School of Physics and Materials Science Guangzhou UniversityGuangzhou510006China

Bitcoin is widely used as the most classic electronic currency for various electronic services such as exchanges,gambling,marketplaces,and also scams such as high-yield investment *** the services operated by a Bitcoin address can help determine the risk level of that address and build an alert model *** engineering can also be used to flesh out labeled addresses and to analyze the current state of Bitcoin in a small *** this paper,we address the problem of identifying multiple classes of Bitcoin services,and for the poor classification of individual addresses that do not have significant features,we propose a Bitcoin address identification scheme based on joint multi-model prediction using the mapping relationship between addresses and *** innovation of the method is to(1)Extract as many valuable features as possible when an address is given to facilitate the multi-class service identification task.(2)Unlike the general supervised model approach,this paper proposes a joint prediction scheme for multiple learners based on address-entity mapping ***,after obtaining the overall features,the address classification and entity clustering tasks are performed separately,and the results are subjected to graph-basedmaximization *** final result ismade to baseline the individual address classification results while satisfying the constraint of having similarly behaving entities as far as *** testing and evaluating over 26,000 Bitcoin addresses,our feature extraction method captures more useful *** addition,the combined multi-learner model obtained results that exceeded the baseline classifier reaching an accuracy of 77.4%.

关键词： Bitcoin multi-service classification graph maximization consensus data security

来源：评论

学校读者我要写书评

暂无评论

MRIN: Fine-grained Feature Interaction based on Multiple Feature Relationships for CTR Prediction 26

MRIN: Fine-grained Feature Interaction based on Multiple Fea...

引用

26th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2023

作者： Ju, Jianbang Xiao, Yingyuan Yang, Peilin Zheng, Wenguang Tianjin University of Technology Enginnering Research Center of Learning-Based Intelligent System Ministry of Education Tianjin China Tianjin University of Technology Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin China

ISBN: (纸本)9798350331684

CTR prediction is an important task in personalized recommendation and online advertising. In recent years, many models have been applied in CTR prediction systems to imporve the predcition accuracy. Although the current work has achieved results, the diversity of relationships between the different features was ignored: 1) most existing models usually use the vector-product to realize the interaction of each feature pairs, which ignore the potential contexts between the different feature interactions and lack the different interactive behaviors between the same pair of features;2) most existing models usually only consider the importance of features of the same order, which ignore the weight relationships between the different feature *** this paper, we propose a novel deep learning model called Multi-Relational Interaction Network (MRIN), which learns fine-grained feature interactions and captures latent relationships between features. On the one hand, we design two interactive modules that take different interactive methods to learn the feature interactions in the potential contexts. On the other hand, we flexibly apply attention network to further automatically learn the weight relationships between different feature representations. Extensive experiments conducted on two public datasets prove the effectiveness of our proposed model, which has better performance than the state-of-the-art models. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Semantics-aware transformer for 3D reconstruction from binocular images

引用

Optoelectronics Letters 2022年第5期18卷 293-299页

作者： JIA Xin YANG Shourui GUAN Diyi the engineering research center of learning-based intelligent system and the key laboratoryof computer vision and system of ministry of education tianjin university of technologytianjin 300384china zhejiang university of technology hangzhou 310014china

Existing multi-view three-dimensional(3 D) reconstruction methods can only capture single type of feature from input view, failing to obtain fine-grained semantics for reconstructing the complex shapes. They rarely explore the semantic association between input views, leading to a rough 3 D shape. To address these challenges, we propose a semantics-aware transformer(SATF) for 3 D reconstruction. It is composed of two parallel view transformer encoders and a point cloud transformer decoder, and takes two red, green and blue(RGB) images as input and outputs a dense point cloud with richer details. Each view transformer encoder can learn a multi-level feature, facilitating characterizing fine-grained semantics from input view. The point cloud transformer decoder explores a semantically-associated feature by aligning the semantics of two input views, which describes the semantic association between views. Furthermore, it can generate a sparse point cloud using the semantically-associated feature. At last, the decoder enriches the sparse point cloud for producing a dense point cloud with richer details. Extensive experiments on the Shape Net dataset show that our SATF outperforms the state-of-the-art methods.

关键词： details semantic decoder

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：