检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Zhou, Xinyu Li, Jinglun Hong, Lingyi Jiang, Kaixun Guo, Pinxue Ge, Weifeng Zhang, Wenqiang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China Shanghai Engineering Research Center of AI & Robotics Academy for Engineering and Technology Fudan University Shanghai China

Previous visual object tracking methods employ image-feature regression models or coordinate autoregression models for bounding box prediction. Image-feature regression methods heavily depend on matching results and do not utilize positional prior, while the autoregressive approach can only be trained using bounding boxes available in the training set, potentially resulting in suboptimal performance during testing with unseen data. Inspired by the diffusion model, denoising learning enhances the model's robustness to unseen data. Therefore, We introduce noise to bounding boxes, generating noisy boxes for training, thus enhancing model robustness on testing data. We propose a new paradigm to formulate the visual object tracking problem as a denoising learning process. However, tracking algorithms are usually asked to run in real-time, directly applying the diffusion model to object tracking would severely impair tracking speed. Therefore, we decompose the denoising learning process into every denoising block within a model, not by running the model multiple times, and thus we summarize the proposed paradigm as an in-model latent denoising learning process. Specifically, we propose a denoising Vision Transformer (ViT), which is composed of multiple denoising blocks. In the denoising block, template and search embeddings are projected into every denoising block as conditions. A denoising block is responsible for removing the noise in a predicted bounding box, and multiple stacked denoising blocks cooperate to accomplish the whole denoising process. Subsequently, we utilize image features and trajectory information to refine the denoised bounding box. Besides, we also utilize trajectory memory and visual memory to improve tracking stability. Experimental results validate the effectiveness of our approach, achieving competitive performance on several challenging datasets. The proposed in-model latent denoising tracker achieve real-time speed, rendering denoising learning

关键词： Regression analysis

来源：评论

学校读者我要写书评

暂无评论

Novel method for robust bilateral filtering point cloud denoising

引用

Alexandria engineering Journal 2025年 127卷 573-585页

作者： Yang, Huan Wang, Wei Wang, Yue Wang, Peng College of Computer Science and Technology Chongqing University of Posts and Telecommunications No. 2 Chongwen Road Chongqing Nan'an400065 China School of Advanced Manufacturing Engineering Chongqing University of Posts and Telecommunications No. 2 Chongwen Road Chongqing Nan'an400065 China Sevnce Robotics Co. Ltd Building 7 Phase II Internet Industrial Park Chongqing Liangjiang401123 China Big Data Institute BaoShan University No. 16 Yuanzheng Road Longyang District Yunnan Baoshan678000 China

Bilateral filtering for point cloud denoising relies on the normal of the points. However, normals are not inherent attributes of point clouds but are estimated using algorithms such as principal component analysis (PCA). Due to inaccuracies in the normals, bilateral filtering may lead to unexpected results, such as smoothing in sharp regions. This study addressed this issue by improving the accuracy of normals. Initially, PCA was employed to estimate the initial normals of the point cloud. The points were then categorized into edge and planar points by fitting a three-dimensional sphere. Subsequently, iterative weighted PCA was applied to refine the normals of the edge points. Finally, the improved normals were integrated into bilateral filtering to achieve point cloud denoising. Additionally, a robust estimator was used instead of a Gaussian function to compute the weights in the bilateral filtering. To assess and compare the performance of this algorithm with related ones, the mean square angular error (MSAE) and angular error distribution (AE) were employed to evaluate the accuracy of normal estimation, while the mean square error (MSE) and signal-to-noise ratio (SNR) were employed to assess the denoising performance. Results indicate that the proposed method yielded the most accurate normals compared to PCA, Jet, and VCM normal estimation algorithms. Moreover, when compared to algebraic point set surfaces (APSS), robust implicit moving least squares (RIMLS), anisotropic weighted locally optimal projection (AWLOP), bilateral filtering, and guided filtering point cloud denoising algorithms, the proposed method consistently achieved the smallest MSE and the highest SNR in most cases on the dataset used in this study. © 2025 The Authors

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

VideoPure: Diffusion-based Adversarial Purification for Video Recognition

arXiv

引用

arXiv 2025年

作者： Jiang, Kaixun Chen, Zhaoyu Fu, Jiyuan Hong, Lingyi Li, Jinglun Zhang, Wenqiang Shanghai Engineering Research Center of AI Robotics Academy for Engineering & Technology Fudan University Shanghai China Engineering Research Center of AI & Robotics Ministry of Education Academy for Engineering & Technology Fudan University Shanghai China Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China

—Recent work indicates that video recognition models are vulnerable to adversarial examples, posing a serious security risk to downstream applications. However, current research has primarily focused on adversarial attacks, with limited work exploring defense mechanisms. Furthermore, due to the spatial-temporal complexity of videos, existing video defense methods face issues of high cost, overfitting, and limited defense performance. Recently, diffusion-based adversarial purification methods have achieved robust defense performance in the image domain. However, due to the additional temporal dimension in videos, directly applying these diffusion-based adversarial purification methods to the video domain suffers performance and efficiency degradation. To achieve an efficient and effective video adversarial defense method, we propose the first diffusion-based video purification framework to improve video recognition models’ adversarial robustness: VideoPure. Given an adversarial example, we first employ temporal DDIM inversion to transform the input distribution into a temporally consistent and trajectory-defined distribution, covering adversarial noise while preserving more video structure. Then, during DDIM denoising, we leverage intermediate results at each denoising step and conduct guided spatial-temporal optimization, removing adversarial noise while maintaining temporal consistency. Finally, we input the list of optimized intermediate results into the video recognition model for multi-step voting to obtain the predicted class. We investigate the defense performance of our method against state-of-the-art black-box, gray-box, and adaptive attacks on benchmark datasets and models. Compared with other adversarial purification methods, our method overall demonstrates better defense performance against different attacks. Moreover, our method can be applied as a flexible defense plugin for video recognition models. Our code is available at https://***/deep-kaix

关键词： HTTP

来源：评论

学校读者我要写书评

暂无评论

Design and testing of Hybrid Slime Mold Algorithm for Real-Time Adaptive Mobile Robot Path Planning in Dynamic Environments

Design and testing of Hybrid Slime Mold Algorithm for Real-T...

引用

Advancement in Computation & computer Technologies (InCACCT), International Conference on

作者： Sachin Gupta Shivali Gupta Shaik Mohammed Raith Anand Kumar Salil Bharany Vishnu Kant Ch.Sandeep Department of Robotics and Control Engineering School of Electronics and Control Engineering Lovely Professional University Phagwara India Department of Chemistry School of Chemical Engineering and Physical Sciences Lovely Professional University Phagwara India Department of Computer Science and Engineering Lovely Professional University Phagwara Punjab India Chitkara University Institute of Engineering and Technology Chitkara University Rajpura India School of Computer Science and Artificial Intelligence SR University Warangal Telangana

ISBN: (数字)9798331543891

ISBN: (纸本)9798331543907

Dynamic path planning and collision prevention is one of the key tasks for autonomous vehicles in relation to dynamic movement of obstacles. In this paper, a novel hybrid approach based on integration of Slime Mold Algorithm (SMA), Triangle Inequality Principle (TIP), and Partition Method Strategy (PMS) for solution of this problem statement. The SMA algorithm is very flexible and adaptive by nature due to its biological working mechanism which is associated with TIP and PMS strategies in relation to their optimization and efficient path planning capabilities and robust solutions. This integrated module is tested in virtual environment and the results are compared with other updated algorithms such as A*, Genetic Algorithm (GA), and Particle Swarm Optimization (PSO) for the same static and dynamic environment. It has been observed from the results that this hybrid strategy significantly improves the path planning task several times than other algorithms in terms of multiple aspects. Under testing conditions, the path length was reduced to 25% than other algorithms in a dynamic environment. During this calculation, the computational efficiency of the system has been improved to 60% than conventional methods. The chances of collision have been improved to 34.23% especially in environment where the obstacles are moving. The capability of SMA has been improved due to the synergy between TIP and PMS. The dynamic and adaptive nature of this algorithm is suitable for various applications such as search-and-rescue operations, manufacturing units’ automation and other hazardous environment exploration.

关键词： Navigation Heuristic algorithms Virtual environments Path planning Partitioning algorithms Safety Mobile robots Vehicle dynamics Testing Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

RAINER: A Robust Ensemble Learning Grid Search-Tuned Framework for Rainfall Patterns Prediction

arXiv

引用

arXiv 2025年

作者： Li, Zhenqi Zhong, Junhao Wang, Hewei Xu, Jinfeng Li, Yijie You, Jinjiang Zhang, Jiayi Wu, Runzhi Dev, Soumyabrata The Fu Foundation School of Engineering and Applied Science Columbia University United States Biomedical Engineering Department Pratt School of Engineering Duke University United States School of Computer Science University College Dublin Ireland Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong Robotics Institute School of Computer Science Carnegie Mellon University United States Faculty of Science and Engineering University of Nottingham Ningbo China China College of Intelligence and Computing Tianjin University China The ADAPT SFI Research Centre

Rainfall prediction remains a persistent challenge due to the highly nonlinear and complex nature of meteorological data. Existing approaches lack systematic utilization of grid search for optimal hyperparameter tuning, relying instead on heuristic or manual selection, frequently resulting in sub-optimal results. Additionally, these methods rarely incorporate newly constructed meteorological features such as differences between temperature and humidity, to capture critical weather dynamics. Furthermore, there is a lack of systematic evaluation of ensemble learning techniques and limited exploration of diverse advanced models introduced in the past one or two years. To address these limitations, we propose a Robust ensemble LeArning grId search-tuNed framEwoRk (RAINER) for rainfall prediction. RAINER incorporates a comprehensive feature engineering pipeline, including outlier removal, imputation of missing values, feature reconstruction, and dimensionality reduction via Principal Component Analysis (PCA). The framework integrates novel meteorological features to capture dynamic weather patterns and systematically evaluates non-learning mathematical-based methods and a variety of machine learning models, from weak classifiers (e.g., KNN, LASSO, and Random Forest) to advanced neural networks such as Kolmogorov-Arnold Networks (KAN). By leveraging grid search for hyperparameter tuning and ensemble voting techniques, RAINER achieves state-of-the-art results within real-world dataset. Extensive experiments demonstrate the framework’s superior performance across diverse metrics, such as Accuracy, Precision, Recall, F1-score, and AUC, highlighting the pivotal role of feature engineering, grid search, and ensemble learning in rainfall prediction tasks. © 2025, CC BY.

关键词： Dimensionality reduction

来源：评论

学校读者我要写书评

暂无评论

Robust Semi-Supervised Deep Nonnegative Matrix Factorization with Constraint Propagation for Data Representation

引用

IEEE Transactions on Big Data 2025年

作者： Peng, Siyuan Yin, Jingxing Yang, Zhijing Nie, Feiping Chen, Badong Guangdong University of Technology School of Information Engineering 510006 China Northwestern Polytechnical University School of Computer Science Center for OPTical IMagery Analysis and Learning Xi'an710072 China Xi'an Jiaotong University Institute of Artificial Intelligence and Robotics Xi'an710049 China

Deep nonnegative matrix factorization (DNMF) technique has attached much great attention in recent year, since it can effectively discover the underlying hierarchical structure of complex data. However, most existing unsupervised and semi-supervised DNMF approaches not only suffer from the noisy data seriously, but also fail to enhance the decomposition quality of DNMF obviously by using the obtained supervisory information. To overcome these drawbacks, a robust semi-supervised DNMF method, called the correntropy based semi-supervised DNMF with constraint propagation (CSDCP), is proposed in this paper for learning a compact and meaningful data representation from the original data. Particularly, instead of adopting the traditional Frobenius norm, CSDCP employs the nonlinear and local similarity measure (e.g., correntropy) as the loss function in DNMF to enhance the robustness of DNMF for the noisy data. In addition, the hypergraph based constraint propagation (HCP) algorithm is adopted in CSDCP to exploit the limited supervisory information fully for capturing good data representation. Moreover, algorithm analysis of CSDCP is presented in this paper, including convergence analysis, robustness analysis supervised information analysis, and computational complexity. Extensive experimental results have illustrated that, in comparison to the most related DNMF approaches, CSDCP usually has better clustering results on six nonnegative datasets in clustering tasks. © 2015 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Analysis of IoT and IoT Security Attacks: Understanding the Threat Landscape

A Comprehensive Analysis of IoT and IoT Security Attacks: Un...

引用

Computational Intelligence, Communication Technology and Networking (CICTN), International Conference on

作者： Himanshi Dhayal Vikas Siwach Harkesh Sehrawat Renu Dalai Department of Computer Science and Engineering UIET Maharshi Dayanand University Rohtak Haryana India University School of Automation and Robotics (USAR) GGSIPU Guru Gobind Singh Indraprastha University Delhi India

ISBN: (数字)9798331530389

ISBN: (纸本)9798331530396

IoT has remarkably changed the internet landscape since its introduction. Today, even an isolated physical device is provided with the internet, which allows it to exchange information with other devices. As much flexibility as these devices offer, they also have numerous security issues, causing threats to its users. Adversaries increasingly exploit the vulnerabilities in Internet of Things devices to execute attacks that can inflict significant harm on individuals, communities, and organizations. Consequently, prioritizing the detection, prevention and mitigation of the attacks is imperative to ensure safety and security. The paper provides an in-depth examination of internet of things (IoT) taxonomy, highlighting the associated challenges and security attacks within the IoT ecosystem, which subsequently gives insights into the vulnerabilities of the IoT ecosystem. Additionally, it includes a comparative analysis of various security attacks along with their impacts.

关键词： Prevention and mitigation Ecosystems Taxonomy Organizations Communications technology Safety Security Internet of Things Computational intelligence

来源：评论

学校读者我要写书评

暂无评论

A Multi-UAV Charging Station Enabling Free Landing by Grid Pattern Transmitter

A Multi-UAV Charging Station Enabling Free Landing by Grid P...

引用

Annual IEEE Conference on Applied Power Electronics Conference and Exposition (APEC)

作者： Jungho Kim Hyunkyeong Jo Seoktae Seo Bonyoung Lee Hyungki Min Franklin Bien School of Electrical and Computer Engineering Ulsan National Institute of Science and Technology Ulsan Korea Program in Information & Communication Technology Convergence Ulsan National Institute of Science and Technology Ulsan Korea

ISBN: (数字)9798331516116

ISBN: (纸本)9798331516123

This paper proposed a novel landing platform with wireless power transfer (WPT) to charge multiple unmanned aerial vehicles (UAVs) without restrictions on landing locations or alignment. A transmitter is designed using wires to charge a wide area. To overcome the disadvantages of system made by wires, a grid pattern transmitter and double power line are proposed. These structures provide multiple charging with free positioning of receivers and excite the transmitter lines in wide area properly. The optimized system is composed of 0.15m square cells, providing a 0.9 m by 0.9 m charging area. By experiment, it can efficiently charge four 0.1 m square receivers located anywhere in transmitter. The overall efficiency of four receivers is 37.5%. Also, the experimental results verify that it is unnecessary to align the receiver within the cell, as it has a 2.62% error due to rotation and a 2.94 % error due to position within the cell.

关键词： Coils Magnetic flux leakage Transmitters Wires Windings Receivers Wireless power transfer Autonomous aerial vehicles Current distribution Power electronics

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Cuffless Blood Pressure Estimation Accuracy at Each Heartbeat During Exercise 6th

Evaluation of Cuffless Blood Pressure Estimation Accuracy a...

引用

6th International Conference on Biomedical and Health Informatics, ICBHI 2024

作者： Ono, Kouki Maeda, Yuka Yoshimura, Takumi Huang, Ming Tamura, Toshiyo Master’s Program in Intelligent and Mechanical Interaction Systems University of Tsukuba Tsukuba305-8577 Japan Institute of Systems and Information Engineering University of Tsukuba Tsukuba305-8577 Japan Medical and Welfare Engineering Tokyo Metropolitan College of Industrial Technology Tokyo116-8523 Japan School of Data Science Nagoya City University Nagoya467-8501 Japan Future Robotics Organization Waseda University Tokyo169-8050 Japan

ISBN: (纸本)9783031863226

Continuous blood pressure monitoring is crucial because of its dynamic nature, influenced by factors such as physical activity and mental stress. Although cuffless blood pressure estimation is a promising technique for continuous monitoring, its accuracy during drastic fluctuations, especially during exercise, remains insufficiently validated. In this study, we evaluated a simple Pulse Arrival Time based blood pressure estimation method and several improved methods for sharp fluctuations induced by exercise. Sixteen subjects in the experiment, with data from 13 valid for analysis. The proposed method achieved an average correlation of 0.527 in systolic blood pressure, suggesting that cuffless blood pressure estimation could be applied to estimate continuous blood pressure variability during exercise. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Blood pressure

来源：评论

学校读者我要写书评

暂无评论

Visual Sensor-Based Trajectory Multimodality Prediction via Anchor-Free Query Attention Network

引用

IEEE Transactions on Instrumentation and Measurement 2025年 74卷

作者： Wang, Ruiping Cheng, Jun Yu, Junzhi Nanyang Technological University School of Computer Science and Engineering Jurong West Singapore639798 Singapore Peking University College of Engineering Beijing100871 China Peking University State Key Laboratory for Turbulence and Complex Systems Department of Advanced Manufacturing and Robotics College of Engineering Beijing100871 China

As a core component of intelligent surveillance and autonomous driving systems, visual sensor-based trajectory multimodality prediction can significantly improve their perception and decision-making capabilities. Numerous existing trajectory prediction methods are dedicated to enhance prediction performance. However, they still fail to effectively model the complex spatiotemporal interactions among pedestrians and trajectory multimodality. To address the above challenges, this article presents one new trajectory multimodality prediction method via anchor-free query-based attention network, which can more effectively capture spatiotemporal interactions and model trajectory multimodality. First, the initial trajectory proposal module employs target-centered query-based attention to capture complex spatiotemporal interactions and generate multiple trajectory proposals corresponding to the multiple modes of the future trajectory, which allows the model to use different interaction information when decoding trajectory points at different time steps. Second, the novel trajectory refinement module utilizes the learnable trajectory proposals to construct proposal-level interaction mechanisms to refine future trajectories. Experimental results conducted on ETH and UCY datasets demonstrate that the proposed model can provide the state-of-the-art prediction performance. © 1963-2012 IEEE.

关键词： Prediction models

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：