检索结果-内蒙古大学图书馆

Multi-view aggregation and multi-relation alignment for few-shot fine-grained recognition

Expert Systems with Applications 2025年 283卷

作者： Chen, Jiale Xu, Feng Lyu, Xin Zeng, Tao Li, Xin Chen, Shangjing College of Computer Science and Software Engineering Hohai University Nanjing210024 China School of Computer Engineering Jiangsu Ocean University Lianyungang222005 China Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University Nanjing211106 China

Few-shot fine-grained recognition (FS-FGR) aims to recognize nuanced categories with a limited number of labeled samples that were not encountered during training. Previous work has made significant progress by enhancing the learning of foreground refined regions and the alignment of consistent semantics. However, the detrimental impact of insufficient background diversity on constructing representative category prototypes has been overlooked. Meanwhile, the alignment of semantically consistent features has been hampered by the reliance on singular metrics, resulting in suboptimal feature extraction. To address the limitations above, a novel framework with multi-view aggregation and multi-relation alignment (MVRA) is proposed. In this framework, we strive to refine category prototypes by generating and consolidating multiple views from limited learnable samples. Specifically, we generate foreground-refined views, pinpointing discriminative regions, and background-obfuscated views, broadening the landscape of background diversity. Further, without relying on the entire prior, a global label assignment module is designed to automatically assign reliable labels to the query set samples. Finally, armed with these credible labels, the multi-relation alignment module harnesses the enriched views and their semantic congruencies, facilitating robust feature extraction. The effectiveness and outstanding performance of MVRA are evaluated through extensive experiments conducted on three fine-grained benchmark datasets. © 2025

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Knowledge-driven prototype refinement for few-shot fine-grained recognition

引用

Knowledge-Based Systems 2025年 318卷

Advancements in deep learning have made image classification rival human performance with sufficient data and supervision. However, in domains with limited visual samples and high labeling costs, enabling AI systems to learn efficiently from few examples is challenging. This challenge is compounded in fine-grained categories, where subtle differences and scarce samples hinder robust representation extraction. To address this, we propose the Knowledge-Driven Prototype Refinement (KDPR) framework, which enhances few-shot fine-grained recognition by integrating prior knowledge from text. KDPR simulates human focus on discriminative foreground regions to extract refined views, forming a dual-branch learning framework alongside original images. It also constructs an unsupervised adjacency graph among visual instances and uses graph neural networks to improve category representation robustness. Additionally, a knowledge transfer-based image recognizer integrates prior text embeddings with global semantics directly into visual recognition, providing extra semantic guidance. To optimize knowledge-to-vision mapping, an auxiliary spatial prototype calibration aligns prototype representations across multiple spaces. Extensive experiments on three fine-grained datasets and two popular backbones demonstrate the effectiveness and state-of-the-art performance of our approach, especially in 1-shot learning. The source code is available at: https://***/HHU-JialeChen/KDPRNet. © 2025

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

SGAN-RL: Fusion classification method for network intrusion detection based on data augmentation

引用

Journal of Intelligent and Fuzzy Systems 2025年第4期48卷 569-583页

作者： Li, Lining Liu, Shuai Ren, Rong Wu, Lianhai Wang, Qian Zhang, Bing College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China School of Information Science and Engineering Yanshan University P.R. Qinhuangdao China The Key Laboratory of Software Engineering Yanshan University Qinhuangdao China

Although traditional research methods for intrusion detection can effectively prevent and mitigate issues such as data leaks to avoid severe consequences, existing intrusion detection technologies encounter limitations, including low classification accuracy and high false positive rates, particularly when dealing with high-dimensional, complex network anomaly traffic data. Additionally, the common problem of class imbalance in intrusion detection datasets exacerbates these challenges. This paper introduces a novel approach to network intrusion detection classification, termed SGAN-RL, which integrates ResNet and LSTM models based on the semi-supervised generative adversarial network (SGAN) framework. This method utilizes SGAN to generate synthetic data resembling real intrusion detection data and continually trains the discriminator to produce high-quality data, thereby enhancing data distribution balance and quality. Moreover, a fusion intrusion detection classification model is presented, leveraging the strengths of ResNet and LSTM architectures to capture spatial and temporal features, respectively. This synergistic fusion enhances the model’s capacity for comprehensive data representation, resulting in improved performance in intrusion detection data classification tasks. Experiments conducted on intrusion detection datasets NSL-KDD, UNSW-NB15, and CIC-IDS2017 demonstrate that the proposed model enhances accuracy, precision, recall, F1-score, ROC-AUC, PR-AUC, respectively, showcasing its robust performance and reliability in network intrusion detection classification. © 2025 – IOS Press. All rights reserved.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

FedCGAT: A federated demand prediction method for shared bicycles based on contrastive graph attention mechanism

引用

Journal of Intelligent & Fuzzy Systems 2025年第3期48卷 329-344页

作者： Zhu, Yichang Chen, Leiming Zhang, Weishan Zhang, Baoyu Dong, Cihao Qiu, Jiakang Qingdao Institute of Software College of Computer Science and Technology China University of Petroleum (East China) China Shandong Data Open Innovative Application Laboratory Qingdao China School of Computing and Data Science Nanyang Technological University Singapore

Demand prediction for shared bicycles based on historical trip data helps bicycle management organizations plan the scheduling of bicycles. However, the current prediction methods have the following problems: (1) the bicycle trip station data hides the temporal and spatial information, which is crucial for demand prediction, and the traditional methods cannot effectively use that information. (2) each bicycle organization manages its region, and local region data cannot accurately predict the demand of the whole region. Due to the privacy trip data, organizations cannot share raw data directly, which makes it a challenge to achieve federated multi-participant analyses. To address these issues, we propose a federated learning framework for demand prediction of shared bicycles (FedCGAT). Firstly, we propose a spatio-temporal graph neural network based on an attention mechanism for feature modeling of data. Meanwhile, we propose a graph data augmentation method to eliminate noisy data and capture spatial correlations. Then, we construct an auxiliary task based on contrastive learning to assist model training, which can learn the data features fully. Finally, we conducted experiments on two real-world bicycle datasets. The experiments demonstrate that FedCCAT achieves high prediction accuracy while preserving data privacy. Compared to the best-performing baseline model on both datasets, our model achieves reductions in MAPE values of 1.67% and 1.94%, respectively. © 2025 – IOS Press. All rights reserved.

关键词： Federated learning demand prediction shared bicycles graph attention mechanism contrastive learning

来源：评论

学校读者我要写书评

暂无评论

A Self-Evolving Framework for Multi-Agent Medical Consultation Based on Large Language Models

A Self-Evolving Framework for Multi-Agent Medical Consultati...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Kai Chen Ji Qi Jing Huo Pinzhuo Tian Fanyu Meng Xi Yang Yang Gao State Key Laboratory for Novel Software Technology Nanjing University Nanjing China China Mobile (Suzhou) Software Technology Co. Ltd. Suzhou China School of Computer Engineering and Science Shanghai University Shanghai China China Mobile Research Institute Beijing China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

We propose a multi-agent approach (SeM-Agents) based on large language models for medical consultations. This framework incorporates various doctor roles and auxiliary roles, with agents communicating through natural language. Using a residual structure, the system conducts multi-round medical consultations based on the patient’s treatment background and symptoms. In the final summary and output stage of the consultation, it utilizes two experience databases—the Correct Consultation Experience Database and the Chain of Thought (CoT) Experience Database—which evolve with accumulated experience during consultations. This evolution drives the framework’s self-improvement, significantly enhancing the rationality and accuracy of the consultations. To ensure that the conclusions are safe, reliable, and aligned with human values, the final decisions undergo a safety review before being provided to the patient. This framework achieved accuracy rates of 89.2% and 83.1% on the MedQA and PubMedQA datasets, respectively.

关键词： Accuracy Pollution Databases Reviews Large language models Natural languages Signal processing Safety Reliability Speech processing

来源：评论

学校读者我要写书评

暂无评论

Generating Targeted Universal Adversarial Perturbation against Automatic Speech Recognition via Phoneme Tailoring

Generating Targeted Universal Adversarial Perturbation again...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Yujun Zhang Yanqu Chen Jiakai Wang Jin Hu Renshuai Tao Xianglong Liu State Key Laboratory of Complex & Critical Software Environment Beihang University China School of Computer Science and Engineering Beihang University China College of Computer Science Beijing University of Technology China Zhongguancun Laboratory China School of Computer and Information Technology Beijing Jiaotong University China Institute of Data Space Hefei Comprehensive National Science Center China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

There is a growing concern about adversarial attacks against automatic speech recognition (ASR) systems. Although research into targeted universal adversarial examples (AEs) has progressed, current methods are constrained by inefficient exploitation of audio features, demonstrating insufficient attack ability and robustness in the physical world. To solve this problem, we propose a phoneme-tailored attack (PTA) to improve the quality of the generated AEs. Specifically, to improve attack ability, we propose a Diverse Audio Composition Enrichment method, which enhances the utilization of audio features through phoneme-level slicing and recombination. To adapt AEs to complex environments, we propose a Natural Noise Pattern Guidance method to align AEs with natural noise patterns to improve their robustness. Experiments show that our method achieves an average accuracy of more than 72.34% and 98% with and without a norm constraint, and also demonstrates excellent performance in terms of generalization across datasets and resilience to MP3 compression.

关键词： Accuracy Target recognition Perturbation methods Noise Robustness Acoustics Speech processing Digital audio players Automatic speech recognition Resilience

来源：评论

学校读者我要写书评

暂无评论

Hyperbolic Variational Graph Auto-Encoder for Next POI Recommendation 34

Hyperbolic Variational Graph Auto-Encoder for Next POI Recom...

引用

34th ACM Web Conference, WWW 2025

作者： Liu, Yuwen Qi, Lianyong Mao, Xingyuan Liu, Weiming Wang, Fan Xu, Xiaolong Zhang, Xuyun Dou, Wanchun Zhou, Xiaokang Beheshti, Amin Shandong Key Laboratory of Intelligent Oil and Gas Industrial Software College of Computer Science and Technology China University of Petroleum (East China) Qingdao China College of Computer Science and Technology Zhejiang University Hangzhou China School of Software Nanjing University of Information Science and Technology Nanjing China School of Computing Macquarie University Sydney Australia Department of Computer Science and Technology Nanjing University Nanjing China Faculty of Business and Data Science Kansai University Osaka Japan

ISBN: (纸本)9798400712746

Next Point-of-Interest (POI) recommendation has become a crucial task in Location-Based Social Networks (LBSNs), which provide personalized recommendations by predicting the user’s next check-in locations. Commonly used models including Recurrent Neural Networks (RNNs) and Graph Convolutional Networks (GCNs) have been widely explored. However, these models face significant challenges, including the difficulty of capturing the hierarchical and tree-like structure of POIs in Euclidean space and the sparsity problem inherent in POI recommendations. To address these challenges, we propose a Hyperbolic Variational Graph Auto-Encoder (HVGAE) for next POI recommendation. Specifically, we utilize a Hyperbolic Graph Convolutional Network (Hyperbolic GCN) to model hierarchical structures and tree-like relationships by converting node embeddings from euclidean space to hyperbolic space. Then we use Variational Graph Auto-Encoder (VGAE) to convert node embeddings to probabilistic distributions, enhancing the capture of deeper latent features and providing a more robust model structure. Furthermore, we combine the Mamba4Rec recommender and Rotary Position Embedding (RoPE) and propose Rotary Position Mamba (RPMamba) to effectively utilize POI embeddings rich in sequential information, which improves the accuracy of the next POI recommendation. Extensive experiments on three public datasets demonstrate the superior performance of the HVGAE model. © 2025 Copyright held by the owner/author(s).

关键词： Graph convolutional network Hyperbolic space Mamba Point-of-interest recommendation Variational graph auto-encoder

来源：评论

学校读者我要写书评

暂无评论

WeakMedSAM: Weakly-Supervised Medical Image Segmentation via SAM with Sub-Class Exploration and Prompt Affinity Mining

arXiv

引用

arXiv 2025年

作者： Wang, Haoran Huai, Lian Li, Wenbin Qi, Lei Jiang, Xingqun Shi, Yinghuan National Key Laboratory for Novel Software Technology The National Institute of Healthcare Data Science Nanjing University Jiangsu Nanjing China National Key Laboratory for Novel Software Technology National Institute of Healthcare Data Science Nanjing University Nanjing Drum Tower Hospital Jiangsu Nanjing China National Key Laboratory for Novel Software Technology Nanjing University Jiangsu Nanjing China Lab School of Computer Science and Engineering Southeast University Jiangsu Nanjing China BOE Technology Group Co. Ltd. Beijing China

We have witnessed remarkable progress in foundation models in vision tasks. Currently, several recent works have utilized the segmenting anything model (SAM) to boost the segmentation performance in medical images, where most of them focus on training an adaptor for fine-tuning a large amount of pixel-wise annotated medical images following a fully supervised manner. In this paper, to reduce the labeling cost, we investigate a novel weakly-supervised SAM-based segmentation model, namely WeakMedSAM. Specifically, our proposed WeakMedSAM contains two modules: 1) to mitigate severe co-occurrence in medical images, a sub-class exploration module is introduced to learn accurate feature representations. 2) to improve the quality of the class activation maps, our prompt affinity mining module utilizes the prompt capability of SAM to obtain an affinity map for random-walk refinement. Our method can be applied to any SAM-like backbone, and we conduct experiments with SAMUS and EfficientSAM. The experimental results on three popularly-used benchmark datasets, i.e., BraTS 2019, AbdomenCT-1K, and MSD Cardiac dataset, show the promising results of our proposed WeakMedSAM. Our code is available at https://***/wanghr64/WeakMedSAM. Copyright © 2025, The Authors. All rights reserved.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Distributed Learning for Privacy-Preserving Semi-Supervised Video Anomaly Detection

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年

作者： Xie, Xiao-Dong Zhan, Yu-Wei Ma, Zhen-Xiang Liu, Hong-Mei Chen, Zhen-Duo Luo, Xin Xu, Xin-Shun Shandong University School of Software Jinan250101 China Tsinghua University Department of Computer Science and Technology Beijing100084 China Innovation Institute Jinan250001 China Quan Cheng Laboratory Jinan250103 China

Semi-supervised video anomaly detection (SS-VAD) is essential for intelligent monitoring. However, collecting large-scale surveillance videos from various organizations raises significant privacy concerns regarding sensitive information. Federated learning offers a promising solution by enabling distributed learning among multiple participants while safeguarding privacy. Despite its potential, research on applying federated learning to SS-VAD remains unexplored due to the inherent challenges of this task. In this paper, we solve this task via proposing DLPP, a novel distributed learning framework for privacy-preserving SS-VAD. It addresses the issue of statistical heterogeneity among data from different participants in real-world federated SS-VAD applications, particularly focusing on non-independent and identically distributed (non-IID) data and imbalanced data volumes. In specific, it addresses these challenges in two key innovations: (1) For the non-IID data challenge, it dynamically updates the client model based on the overall gradient at the client of the previous training round and the degree of divergence between the server model and the client model. In this way, it can better adapt the server model to each client and promote convergence. (2) For the imbalanced data volumes challenge, it adaptively allocates client aggregation weights by comprehensively considering the data volumes, model quality, and learning efficiency of clients. This means a more robust server model can be obtained, and model bias reduced. We conduct extensive experiments to evaluate the performance of DLPP on benchmark datasets by partitioning data to simulate various degrees of non-IID environments. The results show that DLPP significantly outperforms both Baseline and SOTA methods, achieving up to a 3.89% improvement, and its communication efficiency is 3x better than FedAvg. © 2025 IEEE. All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Partially Hidden Policy Attribute-Based Multi-Keyword Searchable Encryption with Verification and Revocation

引用

IEEE Transactions on Mobile Computing 2025年

作者： Chen, Liqing Xu, Shiguo Jin, Chunhua Zhang, Hao Weng, Jian Huaiyin Institute of Technology Faculty of Computer and Software Engineering Jiangsu Huai'an223003 China Fujian Provincial Key Laboratory of Network Security and Cryptology Fujian Fuzhou350117 China Jinan University College of Information Science and Technology Guangdong Guangzhou510632 China

Data security is becoming increasingly critical as outsourced data services flourish. An effective solution for ensuring data confidentiality in the cloud is attribute-based searchable encryption (ABSE). However, most extant ABSE solutions have not been able to simultaneously achieve rich expressive queries, result validation, attribute revocation, and policy hiding, and there are problems such as inflexibility in query methods and access control capabilities, insufficient scalability and practicality, and privacy leakage. In particular, it should be noted that most ABSE schemes fail to promise the privacy security of access policies and are susceptible to offline keyword guessing attack. Hidden policy-ABSE (HP-ABSE) has been proposed to tackle the issue of explicit attribute values in access policies potentially compromising privacy. Nevertheless, in most existing HP-ABSE schemes, an adversary may initiate attribute values guessing attack to speculate on the values of attribute within access strategy. To this end, this paper proposes partially hidden policy attribute-based multi-keyword searchable encryption with verification and revocation (PHP-ABMKSE-VR). PHP-ABMKSE-VR scheme is practical, secure, as well as effective, making it appropriate for real-world scenarios like smart healthcare, as demonstrated by the experimental outcomes and safety analysis. © 2002-2012 IEEE.

关键词： Differential privacy

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：