检索结果-内蒙古大学图书馆

25th International Conference on Parallel and Distributed Computing, Applications and Technologies, PDCAT 2024

作者： Zhang, Feng Wang, Jia-Xin Hua, Qiang Dong, Chun-Ru Zhu, Jie Hebei Key Laboratory of Machine Learning and Computational Intelligence College of Mathematics and Information Science Hebei University Baoding China

ISBN: (纸本)9789819642069

To handle model bias from long-tailed image datasets, most existing studies have proposed to strengthen the focus on tail classes. However, they usually overlook the intricacies of sample learning hardness and feature norms’ impact on accuracy, as well as the non-target class contribution. We designed a new loss using logit adjustment. It considers the distribution of the number of class samples, sample learning hardness, and feature norms. Moreover, it combines a complementary entropy regularization term designed for long-tailed data. Extensive experiments on long-tailed datasets confirm the proposed loss’s superiority in enhancing classification accuracy. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

Discriminative Score Suppression for Weakly Supervised Video Anomaly Detection

Discriminative Score Suppression for Weakly Supervised Video...

引用

2025 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2025

作者： Xu, Chen Li, Chunguo Xing, Hongjie College of Mathematics and Information Science Hebei University Hebei Key Laboratory of Machine Learning and Computational Intelligence Baoding071002 China School of Cyber Security and Computer Hebei University Baoding071000 China

ISBN: (纸本)9798331510831

Weakly supervised video anomaly detection (WSVAD) often relies on Multiple Instance learning (MIL). However, selecting only the most discriminative segments for training limits the model's ability to comprehensively detect anomalous events, particularly hard anomalies. To overcome this limitation, we propose the Discriminative Score Suppression (DSS) module. This module suppresses the discriminative scores of the most prominent anomalies, shifting the model's attention to less obvious but important hard anomalies. This approach guides the model to learn the critical features of hard anomalies, enabling a more comprehensive detection of anomalous events. Additionally, the Anomaly Score Refinement (ASR) module constructs a dissimilarity-based classifier by storing normal patterns as prototypes, and integrates this with a neural network classifier. By combining the anomaly scores from both classifiers, more accurate detection of true hard anomalies is achieved. A score-sensitive inner-bag loss function not only adjusts penalties based on anomaly scores but also ensures that the model avoids erroneous selections. Our method accurately detects various anomalies, including challenging and multi-segment anomalies, while minimizing false positives for normal events. Extensive experiments show that the proposed framework outperforms state-of-the-art methods on the UCF-Crime and XD-Violence datasets. © 2025 IEEE.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Text semantic structure-guided correlation learning for cross-modal retrieval

引用

Multimedia Systems 2025年第3期31卷 1-17页

作者： Zhu, Jie Fan, Jingjing Zhao, Jianguang Wu, Shufang Liu, Jianan Hebei Key Laboratory of Machine Learning and Computational Intelligence College of Mathematics and Information Science Hebei University Baoding071002 China Information Engineering College Hebei University of Architecture Zhangjiakou075000 China College of Management Hebei University Baoding071002 China

To effectively integrate the structural relationships between data into the generated cross-modal features, numerous cross-modal retrieval methods have employed Graph Convolutional Networks (GCNs) for cross-modal feature learning. However, most studies independently learn features for different modalities, ultimately limiting structural consistency across cross-modal features. As text features encompass semantic structural information, we introduce a Text Semantic Structure-Guided Correlation learning (TSSCL) method. This method leverages text features as supervision information to guide the learning of both image and label correlations. As a result, we can align the structural relationships within the common representations and label embeddings with those inherent in the texts. Furthermore, we introduce a novel Structure Transfer Graph Convolutional Network (STGCN) to maintain the global structural relationships across images. Additionally, we propose a series of semantic consistency losses and structural InfoNCE losses, which are beneficial for maintaining both the semantic consistency and structural consistency of the common representations and label embeddings. We perform experiments on the NUS-WIDE, MIRFlickr-25K, and MS-COCO datasets, and the results demonstrate that our TSSCL outperforms the current state-of-the-art cross-modal retrieval methods. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Modal analysis

来源：评论

学校读者我要写书评

暂无评论

A Multiscale Global-Local Transformer for Long-Sequence PV Power Generation Forecasting 25th

A Multiscale Global-Local Transformer for Long-Sequence PV ...

引用

25th International Conference on Parallel and Distributed Computing, Applications and Technologies, PDCAT 2024

作者： Deng, Tian-Yang Li, Wen-Li Zhang, Feng Hua, Qiang Dong, Chun-Ru Lim, Boon Han Hebei Key Laboratory of Machine Learning and Computational Intelligence Baoding China College of Mathematics and Information Science Hebei University Baoding China Lee Kong Chian Faculty of Engineering and Science Universiti Tunku Abdul Rahman Kajang Malaysia

ISBN: (纸本)9789819642069

The intermittent and fluctuating solar irradiance makes photovoltaic (PV) power generation unstable, which brings great challenges to the power grid system. Existing deep learning-based PV power generation prediction models usually employ Long Short-Term Memory (LSTM) or Convolutional Neural Networks (CNNs) to predict the future PV power generation. However, the recurrent structure-based methods usually failed to model the long-term dependence due to the accumulated error caused by backpropagation through time. To overcome these issues, an improved Transformer-based prediction model, which is called GLformer, is proposed in this work. Specifically, the proposed GLformer decomposes an input series into global pattern subsequences and local pattern subsequences, where the global pattern subsequences represent the trends and seasonality and the local pattern subsequences are used to describe the fluctuations. The global and local features are extracted and fused using a Transformer-based global-local feature extraction module, which enhances the model’s capability of modeling long-term dependence, and obtaining complete time features for prediction. Extensive experimental results show that the proposed method is superior to most SOTA forecasting models. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Deep learning PV power forecasting Solar energy Transformer

来源：评论

学校读者我要写书评

暂无评论

Discriminative Score Suppression for Weakly Supervised Video Anomaly Detection

Discriminative Score Suppression for Weakly Supervised Video...

引用

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Chen Xu Chunguo Li Hongjie Xing Hebei Key Laboratory of Machine Learning and Computational Intelligence College of Mathematics and Information Science Hebei University Baoding China School of Cyber Security and Computer Hebei University Baoding China

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

关键词： Training Computer vision Accuracy Neural networks Prototypes Benchmark testing Feature extraction Robustness Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

A novel deep high-level concept-mining jointing hashing model for unsupervised cross-modal retrieval

High-Confidence Computing

引用

High-Confidence Computing 2025年第2期5卷

作者： Dong, Chun-Ru Zhang, Jun-Yan Zhang, Feng Hua, Qiang Xu, Dachuan Hebei Key Laboratory of Machine Learning and Computational Intelligence College of Mathematics and Information Science Hebei University Baoding071002 China Beijing Institute for Scientific and Engineering Computing Beijing University of Technology Beijing100124 China

Unsupervised cross-modal hashing has achieved great success in various information retrieval applications owing to its efficient storage usage and fast retrieval speed. Recent studies have primarily focused on training the hash-encoded networks by calculating a sample-based similarity matrix to improve the retrieval performance. However, there are two issues remain to solve: (1) The current sample-based similarity matrix only considers the similarity between image-text pairs, ignoring the different information densities of each modality, which may introduce additional noise and fail to mine key information for retrieval;(2) Most existing unsupervised cross-modal hashing methods only consider alignment between different modalities, while ignoring consistency between each modality, resulting in semantic conflicts. To tackle these challenges, a novel Deep High-level Concept-mining Jointing Hashing (DHCJH) model for unsupervised cross-modal retrieval is proposed in this study. DHCJH is able to capture the essential high-level semantic information from image modalities and integrate into the text modalities to improve the accuracy of guidance information. Additionally, a new hashing loss with a regularization term is introduced to avoid the cross-modal semantic collision and false positive pairs problems. To validate the proposed method, extensive comparison experiments on benchmark datasets are conducted. Experimental findings reveal that DHCJH achieves superior performance in both accuracy and efficiency. The code of DHCJH is available at Github. © 2024 The Author(s)

关键词： Online searching

来源：评论

学校读者我要写书评

暂无评论

MFF-YOLO: An Improved YOLO Algorithm Based on Multi-Scale Semantic Feature Fusion

引用

Tsinghua Science and Technology 2025年第5期30卷 2097-2113页

作者： Junsan Zhang Chenyang Xu Shigen Shen Jie Zhu Peiying Zhang Qingdao Institute of Software College of Computer Science and Technology China University of Petroleum (East China) Qingdao China School of Information Engineering Huzhou University Huzhou China Hebei Key Laboratory of Machine Learning and Computational Intelligence College of Mathematics and Information Science Hebei University Baoding China National Research Center for Information Science and Technology Tsinghua University Beijing China

The YOLOv5 algorithm is widely used in edge computing systems for object detection. However, the limited computing resources of embedded devices and the large model size of existing deep learning based methods increase the difficulty of real-time object detection on edge devices. To address this issue, we propose a smaller, less computationally intensive, and more accurate algorithm for object detection. Multi-scale Feature Fusion-YOLO (MFF-YOLO) is built on top of the YOLOv5s framework, but it contains substantial improvements to YOLOv5s. First, we design the MFF module to improve the feature propagation path in the feature pyramid, which further integrates the semantic information from different paths of feature layers. Then, a large convolution-kernel module is used in the bottleneck. The structure enlarges the receptive field and preserves shallow semantic information, which overcomes the performance limitation arising from uneven propagation in Feature Pyramid Networks (FPN). In addition, a multi-branch downsampling method based on depthwise separable convolutions and a bottleneck structure with deformable convolutions are designed to reduce the complexity of the backbone network and minimize the real-time performance loss caused by the increased model complexity. The experimental results on PASCAL VOC and MS COCO datasets show that, compared with YOLOv5s, MFF-YOLO reduces the number of parameters by 7% and the number of FLoating point Operations Per second (FLOPs) by 11.8%. The mAP@0.5 has improved by 3.7% and 5.5%, and the mAP@0.5:0.95 has improved by 6.5% and 6.2%, respetively. Furthermore, compared with YOLOv7-tiny, PP-YOLO-tiny, and other mainstream methods, MFF-YOLO has achieved better results on multiple indicators.

关键词： YOLO Deformable models Accuracy computational modeling Image edge detection Semantics Neural networks Feature extraction Real-time systems Edge computing

来源：评论

学校读者我要写书评

暂无评论

MTTF: a multimodal transformer for temperature forecasting

引用

International Journal of Computers and Applications 2024年第2期46卷 122-135页

作者： Cao, Yang Zhai, Junhai Zhang, Wei Zhou, Xuesong Zhang, Feng Key Laboratory of Machine Learning and Computational Intelligence College of Mathematics and Information Science Hebei University Hebei Province Baoding China

Accurate weather forecasting is crucial for various applications, including agriculture and environmental monitoring. However, existing deep learning based methods typically use only temperature observations as input, which do not consider spatial location (e.g. neighboring regions usually show similar temperature trends) and increase the difficulty in predicting anomalous fluctuations in temperature. To address the issue, a multimodal transformer model for temperature forecasting is proposed. This model not only uses observational data (time series data) as input but also incorporates spatially rich ERA5 reanalysis temperature data (spatio-temporal data). The proposed method has two distinctive features: (1) a sequence merging module to highlight dominating features and reduce the cost of attention calculations. (2) a cross-all-modal attention mechanism to capture dependencies between the current modality and all modalities. The method was evaluated on three temperature datasets from a plain and two challenging high-altitude mountainous regions. Results showed that the proposed method outperforms existing methods in terms of MAE and MSE, offering a promising new solution for temperature prediction. Our code and data are available at https://***/Adam618/MTTF. © 2023 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Weather forecasting

来源：评论

学校读者我要写书评

暂无评论

Nonlinear dynamics of a classical rotating pendulum system with multiple excitations

引用

Chinese Physics B 2020年第11期29卷 230-243页

作者： Ning Han Pei-Pei Lu Key Laboratory of Machine Learning and Computational Intelligence College of Mathematics and Information ScienceHebei UniversityBaoding 071002China

We report an attempt to reveal the nonlinear dynamic behavior of a classical rotating pendulum system subjected to combined excitations of constant force and periodic *** unperturbed system characterized by strong irrational nonlinearity bears significant similarities to the coupling of a simple pendulum and a smooth and discontinuous(SD)oscillator,especially the phase trajectory with coexistence of Duffing-type and pendulum-type homoclinic *** order to learn the effect of constant force on this pendulum system,all types of phase portraits are displayed by means of the Hamiltonian function with large constant excitation especially the transitions of complex singular closed *** sufficiently small perturbations of the viscous damping and constant excitation,the Melnikov method is used to analyze the global structure of the phase space and the feature of *** is shown,both theoretically and numerically,that this system undergoes a homoclinic bifurcation and then bifurcates a unique attracting rotating limit ***,the estimation of the chaotic threshold of the rotating pendulum system with multiple excitations is calculated and the predicted periodic and chaotic motions can be shown by applying numerical simulations.

关键词： rotating pendulum Melnikov method rotating limit cycle chaotic dynamics

来源：评论

学校读者我要写书评

暂无评论

Regularity for minimizing sequences of some variational integrals

引用

Science China Mathematics 2023年第4期66卷 777-798页

作者： Hongya Gao Yanan Shan Wei Ren Hebei Key Laboratory of Machine Learning and Computational Intelligence College of Mathematics and Information ScienceHebei UniversityBaoding 071002China

This paper deals with regularity properties for minimizing sequences of some integral functionals related to the nonlinear elasticity *** some structural conditions,we derive that the minimizing sequence and the deriv... 详细信息

关键词： regularity minimizing sequence variational integral energy Ekeland variational principle

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：