检索结果-内蒙古大学图书馆

FASTEN: Video Event Localization Based on Audio-Visual Feature Alignment and Multi-Scale Temporal Enhancement

IEEE Signal Processing Letters 2025年 32卷 2010-2014页

作者： Liu, Yin Wu, Qin Zeng, Mingyong Liu, Yahan Pan, Yuying Jiangnan University School of Artificial Intelligence and Computer Science Wuxi214122 China State Key Laboratory of Mathematical Engineering and Advanced Computing Wuxi214083 China Jiangnan University School of Internet of Things Engineering Wuxi214122 China

The audio-visual event localization task investigates how audio and visual modalities can mutually enhance video event localization. Current methods often rely on single-modality features or lack effective initial alignment between modalities. Although feature pyramids with multiple resolutions are commonly used, the effective and efficient mining of cross-modal and cross-level semantics remains a challenge. In this letter, we propose FASTEN, which stands for audio-visual Feature Alignment and multi-Scale Temporal ENhancement. Novel features derived from an initially aligned multimodal model are introduced and have been shown to be remarkably beneficial. We design an efficient encoder by sharing weights across all pyramid levels and propose a weighted cross-modal attention module to facilitate interaction between modalities. Additionally, global and local pyramids are fused to jointly capture multi-scale temporal dependencies. Evaluated on UnAV-100 and AVE, our method significantly outperforms competing solutions while reducing parameters and computational FLOPs greatly. © 1994-2012 IEEE.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

Deniable Identity-Based Matchmaking Encryption for Anonymous Messaging

引用

IEEE Transactions on Dependable and Secure computing 2025年第3期22卷 2197-2210页

作者： Cao, Yanmei Wei, Jianghong Huang, Xinyi Chen, Xiaofeng Xiang, Yang Xi'an710071 China State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou450001 China Artifcial Intelligence Thrust Information Hub Guangzhou511400 China Swinburne University of Technology School of Software and Electrical Engineering MelbourneVIC3122 Australia

Anonymous messaging system allows users to deliver messages without revealing the sending content and their identifiers, which has attracted ongoing concerns. However, to the best of our knowledge, all the existing solutions still fail to protect users' privacy under coercion. That is, the user's communication transcripts might be tracked and cached, and later coerced to reveal the underlying messages associated with the ciphertexts due to law enforcement reasons or for evil purposes. In addition, anonymity alone is not enough for some practical scenarios. For instance, a journalist just wants to communicate with those intended informants, and thereby gather information from anonymous but authenticated sources. In this paper, to address the above-mentioned issues, we introduce an authenticated and deniable anonymous messaging framework. Its core component is a new cryptographic primitive dubbed deniable identity-based matchmaking encryption (DIB-ME), which captures plausible deniability under coercion and mutual authentication without interactions simultaneously. We further present a concrete DIB-ME construction and prove its security in the random oracle model. The performance analysis indicates merits of the proposed DIB-ME scheme. We also implement the proposed DIB-ME construction and present extensive experiment results, as a proof of concept to demonstrate its soundness and practicability. © 2024 IEEE.

关键词： Anonymity

来源：评论

学校读者我要写书评

暂无评论

Multi-scale Re-weighted Attention Feature Fusion for Non-Intrusive Load Monitoring

Multi-scale Re-weighted Attention Feature Fusion for Non-Int...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Yang, Lingxi Sun, Meijun Ran, Haowei Liu, Yipu Zhou, Yan Wang, Zheng College of Intelligence and Computing Tianjin University Tianjin China Tianjin Key Laboratory of Machine Learning Tianjin University Tianjin China School of Disaster and Emergency Medicine Tianjin University Tianjin China

ISBN: (纸本)9798350368741

Non-Intrusive Load Monitoring (NILM) addresses the challenge of disaggregating total energy consumption into individual appliance usage, which is essential for enhancing energy efficiency and managing smart grids. Existing methods often overlook the impact of window sizes on the separation of appliance-level power signals, leading to appliance power aliasing (APA), where a single total power curve corresponds to multiple operating conditions and appliance couplings. A larger window captures global features noise, but it also exacerbates APA, thereby enlarging the solution space. In contrast, a smaller window mitigates APA but it introduces noise and increases complexity. To address these limitations, we propose the MultiScale Re-weighted Attention Feature Fusion (MRAFF) model, which employs a multi-scale framework to manage temporal variations and incorporates a re-weighted attention module to enhance multi-scale interactions, thereby improving feature representation. Experimental results demonstrate that our MRAFF model significantly outperforms baseline models on the REDD and UK-DALE datasets, achieving improvements ranging from 2.27% to 10.5% in MAE and from 33.74% to 58.34% in SAE. © 2025 IEEE.

关键词： appliance power aliasing deep learning MRAFF modle muti-scale time series NILM

来源：评论

学校读者我要写书评

暂无评论

PPGF: Probability Pattern-Guided Time Series Forecasting

引用

IEEE Transactions on Neural Networks and Learning Systems 2025年 PP卷 PP页

作者： Sun, Yanru Xie, Zongxia Xing, Haoyu Yu, Hualong Hu, Qinghua Tianjin University College of Intelligence and Computing Tianjin Key Laboratory of Machine Learning Tianjin300350 China

Time series forecasting (TSF) is an essential branch of machine learning with various applications. Most methods for TSF focus on constructing different networks to extract better information and improve performance. However, practical application data contain different internal mechanisms, resulting in a mixture of multiple patterns. That is, the model's ability to fit different patterns is different and generates different errors. In order to solve this problem, we propose an end-to-end framework, namely probability pattern-guided time series forecasting (PPGF). PPGF reformulates the TSF problem as a forecasting task guided by probabilistic pattern classification. First, we propose the grouping strategy to approach forecasting problems as classification and alleviate the impact of data imbalance on classification. Second, we predict the corresponding class interval to guarantee the consistency of classification and forecasting. In addition, true class probability (TCP) is introduced to pay more attention to the difficult samples to improve the classification accuracy. Detailedly, PPGF classifies the different patterns to determine which one the target value may belong to and estimates it accurately in the corresponding interval. To demonstrate the effectiveness of the proposed framework, we conduct extensive experiments on real-world datasets, and PPGF achieves significant performance improvements over several baseline methods. Furthermore, the effectiveness of TCP and the necessity of consistency between classification and forecasting are proved in the experiments. All data and codes are available online: https://***/syrGitHub/PPGF. © 2025 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Complete Gait Phase Recognition Based on Muscle Synergy Using PSO-CNN-LSTM Algorithm

引用

IEEE Sensors Journal 2025年第10期25卷 16775-16786页

作者： Zhang, Kewen Li, Xiaoling Chen, Xin Yu, Longjie Jin, Yinan Fan, Bingfei Du, Mingyu Bao, Guanjun Wu, Xinyu Cai, Shibo Zhejiang University of Technology College of Mechanical Engineering Key Laboratory of Special Purpose Equipment and Advanced Processing Technology Ministry of Education and Zhejiang Province Hangzhou310023 China Zhejiang University of Technology College of Mechanical Engineering Hangzhou310023 China ZJUT Yinhu Research Institute of Innovation and Entrepreneurship Zhejiang University of Technology Fuyang Hangzhou310023 China Shenzhen Institutes of Advanced Technology Guangdong Provincial Key Laboratory of Robotics and Intelligent System Chinese Academy of Sciences Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology Shenzhen518055 China

Accurately recognizing gait phases, by applying proper instrumentation and measurement, is significant in walking rehabilitation training for patients with impaired mobility. In this study, seven phases of complete stand-walk–stand cycle as well as continuous daily walking were recognized based on muscle synergy and particle swarm optimization (PSO)-convolutional neural network (CNN)-long short-term memory (LSTM) model. First, the complete stand-walk–stand walking cycle was divided into starting phase, terminal swing phase, loading response phase, mid-stance phase, terminal stance phase, initial swing phase, and stopping phase, based on the features of surface electromyography (sEMG) collected by portable sEMG acquisition system and measured motion data of lower limb. Second, a muscle weight matrix and an activation sequence matrix were calculated by using nonnegative matrix factorization (NMF). Finally, a PSO-CNN-LSTM network was designed to recognize the complete stand-walk–stand cycle by applying the abovementioned matrices as input. Fourteen subjects volunteered to perform linear walking experiments under procedure to verify the feasibility of the proposed approach by comparing results with other classifiers and features. Experimental results show that the proposed approach was capable of achieving an average recognition accuracy of up to 85.384%. This work will offer a promising gait recognition method for rehabilitation robots to achieve natural and flexible human-robot interaction. © 2001-2012 IEEE.

关键词： Non-negative matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Byzantine-robust distributed support vector machine

引用

Science China Mathematics 2025年第3期68卷 707-728页

作者： Xiaozhou Wang Weidong Liu Xiaojun Mao School of Statistics East China Normal UniversityShanghai 200062China Key Laboratory of Advanced Theory and Application in Statistics and Data Science(Ministry of Education) East China Normal UniversityShanghai 200062China School of Mathematical Sciences Shanghai Jiao Tong UniversityShanghai 200240China Key Laboratory of Artificial Intelligence(Ministry of Education) Shanghai Jiao Tong UniversityShanghai 200240China Key Laboratory of Scientific and Engineering Computing(Ministry of Education) Shanghai Jiao Tong UniversityShanghai 200240China

The development of information technology brings diversification of data sources and large-scale data sets and calls for the exploration of distributed learning algorithms. In distributed systems, some local machines may behave abnormally and send arbitrary information to the central machine(known as Byzantine failures), which can invalidate the distributed algorithms based on the assumption of faultless systems. This paper studies Byzantine-robust distributed algorithms for support vector machines(SVMs) in the context of binary classification. Despite a vast literature on Byzantine problems, much less is known about the theoretical properties of Byzantine-robust SVMs due to their unique challenges. In this paper, we propose two distributed gradient descent algorithms for SVMs. The median and trimmed mean operations in aggregation can effectively defend against Byzantine failures. Theoretically, we show the convergence of the proposed estimators and provide the statistical error rates. After a certain number of iterations, our estimators achieve near-optimal rates. Simulation studies and real data analysis are conducted to demonstrate the performance of the proposed Byzantine-robust distributed algorithms.

关键词： Byzantine robustness convergence distributed learning support vector machine

来源：评论

学校读者我要写书评

暂无评论

A Prompt Learning Framework with Large Language Model Augmentation for Few-shot Multi-label Intent Detection

A Prompt Learning Framework with Large Language Model Augmen...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Zhuang, Ning Wei, Xiao Li, Junlei Wang, Xiaobao Wang, Chenyang Wang, Longbiao Dang, Jianwu Tianjin Key Laboratory of Cognitive Computing and Application College of Intelligence and Computing Tianjin University Tianjin China Shenzhen China Co. Ltd. Tianjin China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China

ISBN: (纸本)9798350368741

Intent detection (ID) is essential in spoken language understanding, especially in multi-label settings where intent labels are interdependent and diverse. Existing methods like SE-MLP and QA-FT struggle in few-shot settings, due to limited data availability and efficiency concerns. To address this, we introduce a Prompt Learning framework with large language Model Augmentation (PLMA) for few-shot multi-label ID. In this study, we make three contributions. First, PLMA integrates large language models (LLMs) with small language models (SLMs), using LLMs to enhance SLMs, with prompt learning as the core framework. Second, it leverages LLMs to improve the model's understanding of both queries and labels by intent spans extraction and answer space expansion. Third, PLMA refines the QA-FT. A novel QA format template is designed to allow single-step training and inference for each input, improving efficiency. Experiments on NLU++ show that PLMA significantly outperforms other baselines in both in-domain and cross-domain settings, demonstrating its effectiveness in combining the strengths of both small and large models. © 2025 IEEE.

关键词： large language model multi-label intent detection prompt learning spoken language understanding

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Time Series Segmentation Network Based on Eddy Current Testing for Detecting Surface Metal Defects

引用

IEEE/CAA Journal of Automatica Sinica 2025年第3期12卷 528-538页

作者： Xiaorui Li Xiaojuan Ban Haoran Qiao Zhaolin Yuan Hong-Ning Dai Chao Yao Yu Guo Mohammad S.Obaidat George Q.Huang the School of Intelligence Science and Technology University of Science and Technology Beijing the Beijing Advanced Innovation Center for Materials Genome Engineering the Key Laboratory of Intelligent Bionic Unmanned Systems and the Institute of Materials Intelligent Technology Liaoning Academy of Materials IEEE the Department of Computer Science Hong Kong Baptist University the School of Computer and Communication Engineering Key Laboratory of Advanced Materials and Devices for Post-Moore Chips Ministry of Education University of Science and Technology Beijing the Beijing Advanced Innovation Center for Materials Genome Engineering University of Science and Technology Beijing the School of Computer and Communication Engineering University of Science and Technology Beijing the King Abdullah Ⅱ School of Information Technology The University of Jordan the Department of Computational Intelligence the School of Computing SRM University the School of Engineering The Amity University The Hong Kong Polytechnic University

In high-risk industrial environments like nuclear power plants, precise defect identification and localization are essential for maintaining production stability and safety. However, the complexity of such a harsh environment leads to significant variations in the shape and size of the defects. To address this challenge, we propose the multivariate time series segmentation network(MSSN), which adopts a multiscale convolutional network with multi-stage and depth-separable convolutions for efficient feature extraction through variable-length templates. To tackle the classification difficulty caused by structural signal variance, MSSN employs logarithmic normalization to adjust instance distributions. Furthermore, it integrates classification with smoothing loss functions to accurately identify defect segments amid similar structural and defect signal subsequences. Our algorithm evaluated on both the Mackey-Glass dataset and industrial dataset achieves over 95% localization and demonstrates the capture capability on the synthetic dataset. In a nuclear plant's heat transfer tube dataset, it captures 90% of defect instances with75% middle localization F1 score.

关键词： Eddy current testing nondestructive testing semantic segmentation time series analysis

来源：评论

学校读者我要写书评

暂无评论

Class Semantic Prompts Enhanced Prototypical Fusion Method for Few-shot Named Entity Recognition

Class Semantic Prompts Enhanced Prototypical Fusion Method f...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Yu, Mei Tao, Yuang Zhao, Mankun Xu, Tianyi Meng, Zechen Zhang, Wenbin Yu, Jian School of Future Technology Tianjin University Tianjin300350 China College of Intelligence and Computing Tianjin University Tianjin300350 China Tianjin Key Laboratory of Cognitive Computing and Application Tianjin300350 China Tianjin Key Laboratory of Advanced Networking Tianjin300350 China Information and Network Center Tianjin University Tianjin300350 China

ISBN: (纸本)9798350368741

Few-shot named entity recognition is to identify named entities in scenarios where labeled data is scarce. Existing prototype building methods ignore the use of class semantic and it is difficult to obtain accurate prototype representations only by relying on few support samples. In this paper, we propose a class semantic prompts enhanced prototypical fusion method (CSFP). Specifically, we design a class-semantic prototype that adapts to current task through prompts. In order to add intra-class similarity to the existing prototype and obtain a more accurate and stable prototype representation, we consider the samples distribution and fuse class-semantic prototype with existing prototype through a weighted strategy. Experimental results on two few-shot NER benchmarks show that our method outperforms previous SOTA methods. The analysis further verifies the effectiveness of our method. © 2025 IEEE.

关键词： class semantic few-shot NER prompt learning prototype

来源：评论

学校读者我要写书评

暂无评论

Task-Oriented 6-DoF Grasp Pose Detection in Clutters

arXiv

引用

arXiv 2025年

作者： Wang, An-Lan Chen, Nuo Lin, Kun-Yu Li, Yuan-Ming Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

In general, humans would grasp an object differently for different tasks, e.g., "grasping the handle of a knife to cut" vs. "grasping the blade to hand over". In the field of robotic grasp pose detection research, some existing works consider this task-oriented grasping and made some progress, but they are generally constrained by low-DoF gripper type or non-cluttered setting, which is not applicable for human assistance in real life. With an aim to get more general and practical grasp models, in this paper, we investigate the problem named Task-Oriented 6-DoF Grasp Pose Detection in Clutters (TO6DGC), which extends the task-oriented problem to a more general 6-DOF Grasp Pose Detection in Cluttered (multi-object) scenario. To this end, we construct a large-scale 6-DoF task-oriented grasping dataset, 6-DoF Task Grasp (6DTG), which features 4391 cluttered scenes with over 2 million 6-DoF grasp poses. Each grasp is annotated with a specific task, involving 6 tasks and 198 objects in total. Moreover, we propose One-Stage TaskGrasp (OSTG), a strong baseline to address the TO6DGC problem. Our OSTG adopts a task-oriented point selection strategy to detect where to grasp, and a task-oriented grasp generation module to decide how to grasp given a specific task. To evaluate the effectiveness of OSTG, extensive experiments are conducted on 6DTG. The results show that our method outperforms various baselines on multiple metrics. Real robot experiments also verify that our OSTG has a better perception of the task-oriented grasp points and 6-DoF grasp poses. © 2025, CC BY.

关键词： Clutter (information theory)

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

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

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：