检索结果-内蒙古大学图书馆

POSR: Pose-Aligned Outlier Sample Relabeling for Unsupervised Person Reidentification

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Yu, Hang Fan, Huijie Chen, Xiai Wang, Qiang Han, Zhi Shenyang Univ Chem Technol Sch Informat Engn Shenyang 110142 Peoples R China Chinese Acad Sci Shenyang Inst Automat State Key Lab Robot Shenyang 110016 Peoples R China Shenyang Univ Key Lab Mfg Ind Integrated Automat Shenyang 110003 Peoples R China

Unsupervised person reidentification (Re-ID) is crucial since it enables the matching of individuals without labeled data. Existing clustering-based methods directly discard outlier samples. However, these discarded outliers are not noise samples. In contrast, they are some high-quality samples that are especially meaningful for implementing Re-ID cross-camera retrieval. To capitalize on the diversity of data, we propose a pose-aligned outlier sample relabeling (POSR) model to relabel these outliers to mine diverse data representations for accurate cross-camera retrieval. POSR consists of a pose-aligned feature learning (PFL) module and a biclustering outlier relabeling (BOR) module. The PFL module learns pose features with fine-grained information about human joint points by dynamically matching tokens and obtains the pose-aligned feature via average pooling. The pose-aligned features can compensate for the limitations of global features obtained through the transformer encoder for alignment processing. Therefore, the BOR module is proposed to relabel outlier samples through the complementarity of pose-aligned features and global features, which can learn ID-consistent representations and achieve more robust performance for cross-camera retrieval of unsupervised Re-ID by training meaningful outlier samples. Extensive experiments on three datasets demonstrate the effectiveness of our method and significantly improve Re-ID accuracy.

关键词： Training Accuracy Pedestrians Identification of persons clustering algorithms Cameras Transformers Representation learning Pose estimation Data mining Outlier sample person reidentification (Re-ID) pose-aligned feature relabeling unsupervised learning (USL)

来源：评论

学校读者我要写书评

暂无评论

A Noise-Adaptive Machine Learning Framework for Optimizing User Grouping in Dynamic IM-OFDMA Systems

引用

IEEE TRANSACTIONS ON COMMUNICATIONS 2025年第3期73卷 1862-1878页

作者： Ay, Fahrettin Althunibat, Saud Qaraqe, Khalid A. Kurban, Hasan Texas A&M Univ Dept Elect & Comp Engn College Stn TX 77840 USA Al Hussein Bin Talal Univ Dept Commun Engn Maan 71111 Jordan Texas A&M Univ Qatar Dept Elect & Comp Engn Doha Qatar Hamad Bin Khalifa Univ Coll Sci & Engn Doha Qatar

This paper addresses the challenge of optimizing user grouping in Index Modulation-based Orthogonal Frequency-Division Multiple Access (IM-OFDMA) systems within dynamic and stochastic noise environments. Utilizing the eXtreme Gradient Boosting (XGBoost) machine learning algorithm, we devised a framework capable of accurately predicting the optimality of user groupings across varying Signal-to-Noise Ratio (SNR) levels. Six models corresponding to different noise conditions were created, showcasing adaptability to adjacent noise levels via distribution shift handling, thereby ensuring robust performance across a wide noise spectrum. To accurately identify the most appropriate optimality prediction model for dynamic environments, we introduced a specialized model for precisely estimating the system's internal noise power. The accuracy of this model is crucial for the selection process and was significantly enhanced by implementing sequential Bayesian updating, facilitating a more precise estimation of internal noise power. Following this, we introduced a provisional optimization algorithm designed to refine user groupings within dynamic IM-OFDMA systems. Simulation results highlight the algorithm's effectiveness in markedly improving system performance, evidenced by a significant decrease in bitrate errors. These findings illuminate the significant potential of applying machine learning strategies to wireless communication systems, providing insightful contributions to the enhancement of IM-OFDMA systems in practical settings.

关键词： Heuristic algorithms Predictive models NOMA Table lookup Signal to noise ratio clustering algorithms Adaptation models Index modulation IM-OFDMA user grouping machine learning noisy data extreme gradient boosting XGBoost

来源：评论

学校读者我要写书评

暂无评论

Optimizing Athlete Training and Injury Mitigation Using Fuzzy Information-Based Skeletal Motion Analysis

引用

IEEE ACCESS 2025年 13卷 460-470页

作者： Shou, Zaiyong Hou, Ying Chongqing Normal Univ Coll Phys Educ & Hlth Sci Chongqing 401331 Peoples R China Sichuan Int Studies Univ Dept Phys Educ Chongqing 400031 Peoples R China

In modern sports, enhancing athletic performance and minimizing the risk of injuries is crucial to optimize athlete training and injury mitigation. An athlete's efficiency, endurance, and recovery times can be improved using targeted training programs. This study aims to develop a new strategy to study different training programs for injury mitigation based on an intuitionistic fuzzy rough set (IFRS). An IFRS is vital to reduce uncertainty during data collection and analysis. IFRS bridges two significant frameworks used to reduce uncertainty in information, i.e., the intuitionistic fuzzy set (IFS) and the rough set (RS). First, we develop new similarity measures based on IFRS to enhance accuracy. Then, we use the developed similarity measures to choose the most suitable training program for injury mitigation of athletes according to the demands of modern sports. To do so, different training programs are assessed based on several crucial factors using the proposed measures. The developed measures enhance the accuracy of data collection concerning various uncertain factors crucial in injury mitigation. An example is solved to show the application of the developed measures in injury mitigation. The main contribution of the proposed study is to enhance accuracy when human opinion is modelled.

关键词： Injuries Training Prevention and mitigation Uncertainty clustering algorithms Fuzzy sets Decision making Sports Rough sets Data collection Injury mitigation fuzzy information aggregation fuzzy information handling multi-attribute group decision-making

来源：评论

学校读者我要写书评

暂无评论

Individual Tree Segmentation Based on Region-Growing and Density-Guided Canopy 3-D Morphology Detection Using UAV LiDAR Data

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2025年 18卷 8897-8909页

作者： Li, Shihua Zhao, Shunda Tian, Zhilin Tang, Hao Su, Zhonghua Univ Elect Sci & Technol China Sch Resources & Environm Chengdu 611731 Peoples R China Minist Nat Resources Technol Innovat Ctr Southwest Land Space Ecol Rest Chengdu 610045 Peoples R China Xihua Univ Sch Comp & Software Engn Chengdu 610039 Peoples R China

Forest tree information is crucial for monitoring forest resources and developing forestry management strategies. Airborne laser scanning is an efficient and rapid method for acquiring 3-D point cloud data of forests, making up for the shortcomings of optical remote sensing. Especially for unmanned aircraft vehicle laser scanning, the high-density point cloud provides the possibility of a detailed depiction of forest structures. Extracting individual trees from point cloud data is a prerequisite for fine forestry research. Currently, existing methods fail to fully utilize the height information, density information, and vertical structure details of tree crowns within point cloud data, resulting in complex algorithmic processes and reduced reliability. This study proposes a novel method that combines the canopy height model (CHM) and point cloud data for segmenting individual trees and employs height and density information for morphological detection of tree canopies. First, based on CHM-based segmentation, the point cloud density feature is introduced to identify the wrong segmented trees. Next, the height and density information are combined to guide the selection of vertical profiles. Finally, a 3-D morphological detection is conducted on the profiles to extract the potential trees. We validate the accuracy of the method on German forests. The results indicated that the average F1-scores of six study plots were 0.95, which improved by 5% after the introduction of density information. The primary source of errors was the irregularity of tree morphology. Our method produced reasonable results across different parameter settings, demonstrating its insensitivity to parameter configurations.

关键词： Vegetation Forestry Point cloud compression Accuracy Surveys Three-dimensional displays Morphology Laser radar Autonomous aerial vehicles clustering algorithms Density individual tree segmentation morphology region growing unmanned aerial vehicle (UAV) light detection and ranging (LiDAR)

来源：评论

学校读者我要写书评

暂无评论

Visualizing Temporal Topic Embeddings with a Compass

引用

IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS 2025年第1期31卷 272-282页

作者： Palamarchuk, Daniel Williams, Lemara Mayer, Brian Danielson, Thomas Faust, Rebecca Deschaine, Larry North, Chris Virginia Polytech Inst & State Univ Blacksburg VA 24060 USA Savannah River Natl Lab Savannah GA USA Tulane Univ Tulane LA USA

Dynamic topic modeling is useful at discovering the development and change in latent topics over time. However, present methodology relies on algorithms that separate document and word representations. This prevents the creation of a meaningful embedding space where changes in word usage and documents can be directly analyzed in a temporal context. This paper proposes an expansion of the compass-aligned temporal Word2Vec methodology into dynamic topic modeling. Such a method allows for the direct comparison of word and document embeddings across time in dynamic topics. This enables the creation of visualizations that incorporate temporal word embeddings within the context of documents into topic visualizations. In experiments against the current state-of-the-art, our proposed method demonstrates overall competitive performance in topic relevancy and diversity across temporal datasets of varying size. Simultaneously, it provides insightful visualizations focused on temporal word embeddings while maintaining the insights provided by global topic evolution, advancing our understanding of how topics evolve over time.

关键词： Visualization Compass Vectors Streams Electronic mail clustering algorithms Training High dimensional data Dynamic topic modeling Cluster analysis

来源：评论

学校读者我要写书评

暂无评论

Colorful Star Motif Counting: Concepts, algorithms and Applications

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2025年第3期37卷 1105-1125页

作者： Qin, Hongchao Sen, Gao Li, Rong-Hua Chen, Hongzhi Yuan, Ye Wang, Guoren Beijing Inst Technol Dept Comp Sci Beijing 100811 Peoples R China Natl Univ Singapore Sch Comp Comp Sci Singapore 119077 Singapore ByteDanceInfrastruct Team Beijing 100098 Peoples R China

A colorful star motif is a star-shaped graph where any two nodes have different colors. Counting the colorful star motif can help to analyze the structural properties of real-life colorful graphs, model higher-order clustering, and accelerate the mining of the densest subgraph exhibiting h-clique characteristics in graphs. In this manuscript, we introduce the concept of colorful h-star in a colored graph and proposes two higher-order cohesive subgraph models, namely colorful h-star core and colorful h-star truss. We show that the colorful h-stars can be counted and updated very efficiently using a novel dynamic programming (DP) algorithm. Based on the proposed DP algorithm, we develop a colorful h-star core decomposition algorithm which takes O(hm) time, O(hn+m) space;and a colorful h-star truss decomposition algorithm which takes O(hm(1.5)) time, O(hm) space, where mm and n denote the number of edges and nodes of the graph respectively. Moreover, we also propose a graph reduction technique based on our colorful h-star core model to accelerate the computation of the approximation algorithm for h-clique densest subgraph mining. The results of comprehensive experiments on 11 large real-world datasets demonstrate the efficiency, scalability and effectiveness of the proposed algorithms.

关键词： Stars Approximation algorithms Image color analysis Color Heuristic algorithms clustering algorithms Computational modeling Wireless communication Dynamic programming Analytical models Colorful star K-core K-truss H-clique densest subgraph

来源：评论

学校读者我要写书评

暂无评论

Brain-inspired multimodal motion and fine-grained action recognition

引用

FRONTIERS IN NEUROROBOTICS 2025年 18卷 1502071页

作者： Li, Yuening Yang, Xiuhua Chen, Changkui Wuhan Sports Univ Wuhan Peoples R China Shandong Adm Inst Communist Party China Sch Phys Educ & Training Party Sch Shandong Prov Comm Jinan Shandong Peoples R China

Introduction Traditional action recognition methods predominantly rely on a single modality, such as vision or motion, which presents significant limitations when dealing with fine-grained action recognition. These methods struggle particularly with video data containing complex combinations of actions and subtle motion *** Typically, they depend on handcrafted feature extractors or simple convolutional neural network (CNN) architectures, which makes effective multimodal fusion challenging. This study introduces a novel architecture called FGM-CLIP (Fine-Grained Motion CLIP) to enhance fine-grained action recognition. FGM-CLIP leverages the powerful capabilities of Contrastive Language-Image Pretraining (CLIP), integrating a fine-grained motion encoder and a multimodal fusion layer to achieve precise end-to-end action recognition. By jointly optimizing visual and motion features, the model captures subtle action variations, resulting in higher classification accuracy in complex video *** and discussion Experimental results demonstrate that FGM-CLIP significantly outperforms existing methods on multiple fine-grained action recognition datasets. Its multimodal fusion strategy notably improves the model's robustness and accuracy, particularly for videos with intricate action patterns.

关键词： brain-inspired multimodal action recognition CLIP clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

4D-CS: Exploiting Cluster Prior for 4D Spatio-Temporal LiDAR Semantic Segmentation

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2025年第1期10卷 468-475页

作者： Zhong, Jiexi Li, Zhiheng Cui, Yubo Fang, Zheng Northeastern Univ Fac Robot Sci & Engn Shenyang 110819 Peoples R China Northeastern Univ Natl Frontiers Sci Ctr Ind Intelligence & Syst Opt Shenyang 110819 Peoples R China Northeastern Univ Key Lab Data Analyt & Optimizat Smart Ind Minist Educ Shenyang 110819 Peoples R China Northeastern Univ Fac Robot Sci & Engn Shenyang 110819 Peoples R China

Semantic segmentation of LiDAR points has significant value for autonomous driving and mobile robot systems. Most approaches explore spatio-temporal information of multi-scan to identify the semantic classes and motion states for each point. However, these methods often overlook the segmentation consistency in space and time, which may result in point clouds within the same object being predicted as different categories. To handle this issue, our core idea is to generate cluster labels across multiple frames that can reflect the complete spatial structure and temporal information of objects. These labels serve as explicit guidance for our dual-branch network, 4D-CS, which integrates point-based and cluster-based branches to enable more consistent segmentation. Specifically, in the point-based branch, we leverage historical knowledge to enrich the current feature through temporal fusion on multiple views. In the cluster-based branch, we propose a new strategy to produce cluster labels of foreground objects and apply them to gather point-wise information to derive cluster features. We then merge neighboring clusters across multiple scans to restore missing features due to occlusion. Finally, in the point-cluster fusion stage, we adaptively fuse the information from the two branches to optimize segmentation results. Extensive experiments confirm the effectiveness of the proposed method, and we achieve state-of-the-art results on the multi-scan semantic and moving object segmentation on SemanticKITTI and nuScenes datasets.

关键词： Feature extraction Semantics Laser radar Semantic segmentation Point cloud compression Motion segmentation clustering algorithms Object segmentation Convolution Aggregates Semantic scene understanding deep learning methods clustering

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Blind Signal Detection for Ambient Backscatter Communication Systems

引用

IEEE TRANSACTIONS ON COGNITIVE COMMUNICATIONS AND NETWORKING 2025年第2期11卷 1172-1183页

作者： Zhu, Han Zhan, Jiamiao Lam, Chan-Tong Chen, Bidong Ng, Benjamin K. Macao Polytech Univ Fac Appl Sci Macau Peoples R China Baosight Software Nanchang Co Ltd Prod Res & Dev Dept Nanchang 330199 Peoples R China

Ambient backscatter communication (AmBC) is emerging as a promising energy-saving and spectrum-efficient passive Internet of Things (IoT) technology that can be used for battery-less communication devices due to its low power consumption and cost constraints. However, in AmBC systems, recovering tag information at the reader is a challenging problem due to the difficulty in obtaining relevant channel state information (CSI). In this paper, we propose a variational Bayesian inference and machine learning (VBI-ML) based blind signal detection method, which can automatically recover tag information in AmBC systems. Firstly, two known labels are transmitted from the tag to the reader before valid data is transmitted, thus eliminating the need for CSI estimation. Secondly, we use the VBI approach with the Gaussian mixture model to obtain the real constellation information, which does not require a priori signal modulation technology to recover the tag information at the reader automatically. Using real constellation information, the signal detection problem is converted into a clustering problem. Finally, we cluster all the received signals using an improved expectation maximization algorithm in ML to learn the parameters in labeled and unlabeled signals and recover the signals. Thorough simulation results demonstrate that our proposed method performs similarly to the optimal detector with perfect CSI and outperforms traditional constellation learning methods. More critically, ML algorithms can mitigate direct link interference and simplify the number of estimated parameters.

关键词： Radio frequency Signal detection Detectors Backscatter clustering algorithms Internet of Things Modulation Ambient backscatter communication blind signal detection expectation maximization algorithm Gaussian mixture model variational Bayesian inference

来源：评论

学校读者我要写书评

暂无评论

Optimizing Clustered Cell-Free Networking for Sum Ergodic Capacity Maximization With Joint Processing Constraint

引用

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS 2025年第1期24卷 571-584页

作者： Xia, Funing Wang, Junyuan Dai, Lin Tongji Univ Coll Elect & Informat Engn Shanghai 201804 Peoples R China Tongji Univ Inst Adv Study Coll Elect & Informat Engn Shanghai 201804 Peoples R China Tongji Univ Shanghai Inst Intelligent Sci & Technol Shanghai 201804 Peoples R China City Univ Hong Kong Dept Elect Engn SAR Hong Kong Peoples R China

Clustered cell-free networking has been considered as an effective scheme to trade off between the low complexity of current cellular networks and the superior performance of fully cooperative networks. With clustered cell-free networking, the wireless network is decomposed into a number of disjoint parallel operating subnetworks with joint processing adopted inside each subnetwork independently for intra-subnetwork interference mitigation. Different from the existing works that aim to maximize the number of subnetworks without considering the limited processing capability of base-stations (BSs), this paper investigates the clustered cell-free networking problem with the objective of maximizing the sum ergodic capacity while imposing a limit on the number of user equipments (UEs) in each subnetwork to constrain the joint processing complexity. By successfully transforming the combinatorial NP-hard clustered cell-free networking problem into an integer convex programming problem, the problem is solved by the branch-and-bound method. To further reduce the computational complexity, a bisection clustered cell-free networking ((BCF)-F-2-Net) algorithm is proposed to decompose the network hierarchically. Simulation results show that compared to the branch-and-bound based scheme, the proposed (BCF)-F-2-Net algorithm significantly reduces the computational complexity yet achieves nearly the same network decomposition result. Moreover, our (BCF)-F-2-Net algorithm achieves near-optimal performance and outperforms the state-of-the-art benchmarks with up to 25% capacity gain.

关键词： clustering algorithms Wireless networks Partitioning algorithms Interference Cellular networks Simulation Signal processing algorithms Uplink Optimization Computer architecture Clustered cell-free networking sum ergodic capacity maximization joint processing constraint bisection algorithm

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：