检索结果-内蒙古大学图书馆

40th IEEE International Conference on Data engineering, ICDE 2024

作者： Ouyang, Yudian Xie, Kun Wen, Jigang Xie, Gaogang Li, Kenli College of Computer Science and Electronics Engineering Hunan University Changsha China Hangzhou Institute of Advanced Technology Hangzhou China School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan China Institute of Computer Network Information Center Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798350317152

Tensor data is widely used in fields such as smart grids, cloud systems, and deep learning. As the scale of this data increases, storage and transmission costs rise significantly. Many tensor data exhibit low-rank structures, offering the potential for data compression through low-rank decomposition techniques. Tucker decomposition, a typical low-rank decomposition technique, achieves data compression and interpretability by capturing complex data correlations and representing the original tensor with a compact core tensor and factor matrices. However, the compression ratio provided by Tucker decomposition is often insufficient, particularly for large-scale tensors. To tackle this issue, we propose a robust low-rank tensor compression method that leverages Tucker decomposition with quantization and coding. Initially, we establish a robust Tucker decomposition framework that decomposes the low-rank tensor into a core tensor and factor matrices using well-designed Tucker rank-setting rules. This framework effectively handles noise and missing values. Subsequently, we conduct an in-depth analysis of the numerical characteristics of the core tensor and factor matrices within the Tucker decomposition framework. Based on their distinct characteristics, we design tailored quantization and coding schemes to compress the core tensor and factor matrices, respectively, thereby significantly improving the compression ratio of Tucker decomposition while maintaining high accu-racy. Through extensive experiments on four publicly available datasets (which can form 3 or 4 order tensors), we demonstrate that our approach can achieve compression ratios 4×-10× higher than the best competitor, with recovery errors improved by 8% -42%. © 2024 IEEE.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

Solving Large-Scale Pursuit-Evasion Games Using Pre-trained Strategies 37

Solving Large-Scale Pursuit-Evasion Games Using Pre-trained ...

引用

37th AAAI Conference on Artificial Intelligence, AAAI 2023

作者： Li, Shuxin Wang, Xinrun Zhang, Youzhi Xue, Wanqi Černý, Jakub An, Bo School of Computer Science and Engineering Nanyang Technological University Singapore Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation Chinese Academy of Sciences Hong Kong

ISBN: (纸本)9781577358800

Pursuit-evasion games on graphs model the coordination of police forces chasing a fleeing felon in real-world urban settings, using the standard framework of imperfect-information extensive-form games (EFGs). In recent years, solving EFGs has been largely dominated by the Policy-Space Response Oracle (PSRO) methods due to their modularity, scalability, and favorable convergence properties. However, even these methods quickly reach their limits when facing large combinatorial strategy spaces of the pursuit-evasion games. To improve their efficiency, we integrate the pre-training and fine-tuning paradigm into the core module of PSRO – the repeated computation of the best response. First, we pre-train the pursuer’s policy base model against many different strategies of the evader. Then we proceed with the PSRO loop and fine-tune the pre-trained policy to attain the pursuer’s best responses. The empirical evaluation shows that our approach significantly outperforms the baselines in terms of speed and scalability, and can solve even games on street maps of megalopolises with tens of thousands of crossroads – a scale beyond the effective reach of previous methods. Copyright © 2023, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Scalability

来源：评论

学校读者我要写书评

暂无评论

Dual-branch Complementary Multimodal Interaction Mechanism for Joint Video Moment Retrieval and Highlight Detection

Dual-branch Complementary Multimodal Interaction Mechanism f...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Liang, Xuehui Wang, Ruomei Lin, Ge Feng, Jiawei Luo, Yuanmao School of Computer Science and Engineering Sun Yat-sen University National Engineering Research Center of Digital Life Guangzhou China School of Software Engineering Sun Yat-sen University Zhuhai China

ISBN: (纸本)9781665410205

Joint video moment retrieval and highlight detection is a video understanding task that requires the model to construct multimodal interaction between heterogeneous features. Recent Transformer-based models mainly focus on promoting global interaction between features. However, local interaction and temporal asynchronism modeling are not deeply considered. To solve this problem, this paper proposes a dual-branch complementary multimodal interaction mechanism (DCMI), which consists of a global difference feature activation module (GDFA) and a local information dynamic aggregation module (LIDA). GDFA measures the difference between the target element and the global features, thus activating important information. LIDA designs a multimodal heterogeneous graph and constructs asynchronous interaction between heterogeneous features to dynamically aggregate local information. DCMI adaptively fuses the complementary dual branches to improve the model's cognitive and decision-making abilities of global and local information. Comprehensive comparisons with existing methods on public datasets verify the superiority of the proposed model. Extensive ablation experiments and qualitative analysis show the effectiveness and rationality of DCMI, which can promote the interaction between multimodal features. © 2024 IEEE.

关键词： Video analysis

来源：评论

学校读者我要写书评

暂无评论

Combining Fourier-based Channel Attention with TCN and Informer for Railway Accident Prediction 15

Combining Fourier-based Channel Attention with TCN and Infor...

引用

15th IEEE Global Reliability and Prognostics and Health Management Conference, PHM-Beijing 2024

作者： Shen, Nahao Li, Honghui Bai, Yanhui Yang, Xiaorui He, Ruiyi School of Computer Science and Technology Beijing Jiaotong University Beijing China School of Computer Science and Technology Beijing Jiaotong University Engineering Research Center of Network Management Technology for High Speed Railway of MOE Beijing China

ISBN: (纸本)9798350354010

The rapid expansion of railway networks and technological advancements has introduced significant challenges in ensuring railway safety. To address the critical need for effective prediction and prevention mechanisms, this paper proposes the FCAM-TCN-DSInformer model, a novel approach to railway accident prediction. The model integrates the Fourier-based Channel Attention Mechanism (FCAM), Temporal Convolutional Network (TCN), and De-stationary Informer (DSInformer) to capture both temporal and spectral features from time series data effectively. Extensive experiments and ablation studies were conducted to validate the model's performance. The results demonstrate that the FCAM-TCN-DSInformer model significantly outperforms both traditional and advanced models, including ARIMA, LSTM, GRU, Transformer, Autoformer, and FEDformer by achieving the highest R2 score and substantial reductions in error metrics such as RMSE, MAE, and MAPE. These improvements confirm the model's accuracy and robustness, making it a powerful tool for railway safety management. Moreover, the model's adaptability to different univariate time series datasets, such as the Daily Minimum Temperatures Dataset and the US Births Dataset, highlights its strong generalization capabilities. Future work will focus on optimizing the model for real-time predictions and expanding its application to multi-step prediction tasks, thereby fully realizing its potential across diverse forecasting contexts. © 2024 IEEE.

关键词： Railroad accidents

来源：评论

学校读者我要写书评

暂无评论

Part-based Person Re-Identification with Swin Transformer 6

Part-based Person Re-Identification with Swin Transformer

引用

6th IEEE International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2023

作者： Qin, Yusong Huang, Pu Zhou, Yao Huang, Zengxi Xihua University School of Computer Science and Software Engineering Chengdu China Xihua University School of Computer and Software Engineering and the Sichuan Xihua Jiaotong Forensics Center Chengdu China

ISBN: (纸本)9798350325485

Person re-identification(Re-ID) is a crucial task in computer vision, which aims to match pedestrian images captured in non-overlapping camera views. It has significant implications for public safety applications. However, current methods primarily rely on global features and thus are vulnerable to background clutters and occlusion. To address these issues, this paper proposes a part-based Re-ID method using the Swin Transformer. In this method, we first utilize human pose estimation method to detect the body keypoints of a pedestrian. We then extract local windows and patches centered at these keypoints, so as to minimize the involvement of background and occlusion information in the down-stream re-identification. These body parts in pose guided windows are fed to the Swin Transformer network. The hierarchical structure of Swin Transformer also enables the proposed method more robust to multi-scale problems. Our experimental results on both holistic and occluded datasets, i.e., Market-1501, DukeMTMC-reID, and Occluded-Duke, demonstrate that the proposed method is on par with the state-of-The-Art methods. © 2023 IEEE.

关键词： Clutter (information theory)

来源：评论

学校读者我要写书评

暂无评论

Towards efficient generative AI and beyond-AI computing:New trends on ISSCC 2024 machine learning accelerators

引用

Journal of Semiconductors 2024年第4期45卷 12-15页

作者： Bohan Yang Jia Chen Fengbin Tu Department of Electronic and Computer Engineering The Hong Kong University of Science and TechnologyHong KongChina AI Chip Center for Emerging Smart Systems The Hong Kong University of Science and TechnologyHong KongChina School of the Gifted Young University of Science and Technology of ChinaHefei 230026Chin

Compared to the last decade when the convolution neu-ral network(CNN)dominated the research field,machine learn-ing(ML)algorithms have reached a pivotal moment called the generative artificial intelligence(AI)*** the emer-gence of large-scale foundation models[1],such as large multi-modal model(LMM)GPT-4[2]and text-to-image generative model DALL·E[3].

关键词： ISSCC beyond AI

来源：评论

学校读者我要写书评

暂无评论

Edge AI-Driven Video Analytics: A Mobile Deep Learning Framework for Victim Detection in SAR robotics 3

Edge AI-Driven Video Analytics: A Mobile Deep Learning Frame...

引用

3rd FORTEI-International Conference on Electrical engineering, FORTEI-ICEE 2024

作者： Ihsan, Muhammad Putra, Karisma Trinanda Mustar, Muhamad Yusvin Setyawan, Aufa Faiz Chu, Hsueh-Ting Chen, Hsing-Chung Department of Electrical Engineering Universitas Muhammadiyah Yogyakarta Bantul Indonesia Department of Electrical Engineering Center of Artificial Intelligence and Robotics Studies Universitas Muhammadiyah Yogyakarta Bantul Indonesia Department of Computer Science and Information Engineering Asia University Taichung Taiwan

ISBN: (纸本)9798331542207

In post-disaster search and rescue (SAR) missions, it is crucial for robots to distinguish between actual victims and dummy objects, despite their similar characteristics. Edge video analytics have demonstrated exceptional performance in such missions, however, the trade-off between high-performing deep learning models and computational complexity often results in inadequate computational efficiency for SAR robotics. This study tackles this challenge by deploying a deep learning (DL) algorithm, i.e., MobileNet Single Shot Detector (SSD), specifically tailored for embedded systems, to perform object detection and classification tasks on lab-scale SAR robots. The proposed algorithm is developed in Python and implemented on a low-powered edge computing device. The effectiveness of the proposed algorithm in object localization is highlighted by its mAP score of 0.6247 and an average IoU of 0.9036. Experimental tests using a confusion matrix showed that the model accurately predicted 42 dummy objects and 43 victim dolls. The model achieved an overall accuracy of 89.47%, with a precision of 1.0, a recall of 0.8947, and an F1 Score of 0.9444. Real-time testing confirmed the model’s robust performance, maintaining high accuracy and a stable frame rate of 47 FPS. These findings corroborate the efficacy of the MobileNet SSD algorithm in reliably detecting and differentiating objects within embedded SAR robotic operations. © 2024 IEEE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

Software Crowdsourcing Allocation Algorithm Based on Task Priority 24th

Software Crowdsourcing Allocation Algorithm Based on Task Pr...

引用

24th International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2024

作者： Mei, Ao Yu, Dunhui School of Computer Science and Information Engineering Hubei University Wuhan430062 China Engineering and Technical Research Center of Hubei Province in Educational Informatization Wuhan430062 China

ISBN: (纸本)9789819615278

Aiming at the problem of insufficient consideration of skill rarity and worker skill coverage in the task allocation decision of the current software crowdsourcing platform, this paper proposes a task priority-based software crowdsourcing allocation algorithm. First, the skill rarity is calculated based on the tasks to be assigned and the development skills of workers, and the task priority is determined accordingly. Then, the pre-allocation scheme based on the priority is used as the initial input of the allocation algorithm. Finally, the parameters of the algorithm are set based on the global optimization objectives of maximizing the number of tasks to be assigned and minimizing the number of workers to complete the crowdsourcing task allocation. The experimental results show that compared with allocation algorithms such as candidate task worker group algorithm based on allocation utility and preference matching satisfaction maximization, The algorithms in this paper improves the number of successful task allocations and average worker overhead by 15.23% and 12.76% on average. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Consensus algorithm

来源：评论

学校读者我要写书评

暂无评论

Ensemble Knowledge Distillation for Federated Semi-Supervised Image Classification

引用

Tsinghua science and Technology 2025年第1期30卷 112-123页

作者： Ertong Shang Hui Liu Jingyang Zhang Runqi Zhao Junzhao Du School of Computer Science and Technology Xidian UniversityXi’an 710126China Engineering Research Center of Blockchain Technology Application and Evaluation Ministry of EducationXi’an 710126China Key Laboratory of Smart Human-Computer Interaction and Wearable Technology of Shaanxi Province Xi’an 710126China

Federated learning is an emerging privacy-preserving distributed learning paradigm,in which many clients collaboratively train a shared global model under the orchestration of a remote *** current works on federated learning have focused on fully supervised learning settings,assuming that all the data are annotated with ground-truth ***,this work considers a more realistic and challenging setting,Federated Semi-Supervised Learning(FSSL),where clients have a large amount of unlabeled data and only the server hosts a small number of labeled *** to reasonably utilize the server-side labeled data and the client-side unlabeled data is the core challenge in this *** this paper,we propose a new FSSL algorithm for image classification based on consistency regularization and ensemble knowledge distillation,called *** algorithm uses the global model as the teacher in consistency regularization methods to enhance both the accuracy and stability of client-side unsupervised learning on unlabeled ***,we introduce an additional ensemble knowledge distillation loss to mitigate model overfitting during server-side retraining on labeled *** experiments on several image classification datasets show that our EKDFSSL outperforms current baseline methods.

关键词： federated learning semi-supervised learning federated semi-supervised learning knowledge distillation

来源：评论

学校读者我要写书评

暂无评论

Improving Speaker Verification Back-End with Graph Neural Networks

引用

Journal of Shanghai Jiaotong University (science) 2025年 1-9页

作者： Chen, Jinfeng Fang, Zhihua He, Liang School of Computer Science and Technology Xinjiang University Urumqi830017 China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi830017 China School of Intelligence Science and Technology Xinjiang University Urumqi830017 China Department of Electronic Engineering Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China

Currently, research on speaker verification tasks is primarily concentrated on enhancing deep speaker models to extract high-quality speaker embeddings. Nevertheless, this speaker embeddings can be regarded as potential graph structures. Therefore, this paper introduces a graph neural network-based speaker verification back-end approach, treating the speaker embeddings derived from the front-end as graph structures and leveraging graph neural networks to uncover the relationships among embeddings, thereby achieving superior-quality speaker embeddings. In addition, we propose a group updating method to solve the problem of memory overflow when the number of nodes is excessive. Extensive experiments and ablation studies were carried out on the VoxCeleb dataset, and the experimental outcomes validate the effectiveness of our proposed graph neural network speaker back-end in significantly boosting the performance of speaker verification systems. (Figure presented.) © Shanghai Jiao Tong University 2025.

关键词： Graph embeddings

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：