检索结果-内蒙古大学图书馆

9th International Symposium on Artificial Intelligence and Robotics, ISAIR 2024

作者： Wang, Wanjun Ma, Chunyan Zhu, Hongjun Xu, Kai Han, Huihui School of Computer and Software Engineering Anhui Institute of Information Technology WuHu241199 China School of Artificial Intelligence Department of Information Hohai University NanJing210024 China Platforms of Automotive Intelligent Software and Systems Anhui Institute of Information Technology WuHu241199 China

ISBN: (纸本)9789819629107

Image super-resolution (SR) and disparity estimation are closely related in stereo images, with effective utilization of disparity maps enhancing SR performance. This paper proposes a stereo image super-resolution reconstruction network utilizing disparity estimation and a domain diffusion model. The network integrates disparity estimation with diffusion models for feature summation and domain space construction, enabling interaction between forward and backward diffusion memory units. To further improve reconstructed image quality, we introduce a novel memory unit inspired by long short-term memory concepts. Disparity loss and structural similarity are included in the loss function to achieve more accurate results. Experiments show that our method outperforms existing techniques. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Stereo image processing

来源：评论

学校读者我要写书评

暂无评论

PA-Rank: A GAN and Reinforcement Learning Powered Framework for Multi-Metric Anomaly Detection and Causal Diagnosis

引用

IEEE Internet of Things Journal 2025年

作者： Wang, Zhaowen Zhou, Yong Zhang, YangSiyu Cong, Fengyu Zhou, Dongdong An, Zhijian School of Software Engineering Dalian University of Technology Dalian116024 China Dalian University of Technology School of Software Dalian116024 China Dalian University of Technology School of Biomedical Engineering Faculty of Medicine Dalian116024 China Ministry of Education Key Laboratory of Social Computing and Cognitive Intelligence Dalian University of Technology China University of Jyväskylä Faculty of Information Technology Jyväskylä40014 Finland Dalian University of Technology School of Computer Science and Technology Dalian116024 China Faculty of Information Technology University of Jyvaskyla Jyvaskyla40014 Finland

The increasing scale and complexity of modern IT systems necessitate advanced solutions for monitoring and managing performance anomalies. Artificial intelligence for IT operations (AIOps) has emerged as a promising approach to enhance the efficiency and effectiveness of IT operations. However, existing methods struggle with effectively detecting anomalies in multi-dimensional performance data and accurately identifying their root causes in complex interdependent systems. This paper proposes a novel framework, PA-Rank, that combines generative adversarial networks (GANs), reinforcement learning, and graph-based methods to address these challenges comprehensively. For anomaly detection, an unsupervised GAN-based model is developed to identify anomalous time periods and assign weighted scores to metrics, facilitating precise anomaly identification. For root cause localization, a Causal Graph Construction Model (CGCM) has been developed, utilizing a reinforcement learning-based causal discovery method that is integrated with graph attention networks (GAT) to construct a causal graph representing the relationships between metrics. A random walk algorithm further ranks metric importance during anomalies, enabling effective root cause localization. Extensive experiments on real-world datasets, including SMD, ASD, and DAMADICS, demonstrate the superiority of PA-Rank over traditional statistical and state-of-the-art machine learning methods. On the SMD dataset, the proposed framework achieved an F1 score of 0.9542 for anomaly detection and consistently identified root causes among top-ranked candidates on the Pymicro and RMS datasets with the highest PR@Avg scores. These results underscore PA-Rank’s efficacy in diagnosing performance anomalies and supporting efficient system maintenance. © 2014 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

From Pixels to Trajectory: Universal Adversarial Example Detection via Temporal Imprints

arXiv

引用

arXiv 2025年

作者： Gao, Yansong Peng, Huaibing Ma, Hua Dai, Zhiyang Wang, Shuo Hu, Hongsheng Fu, Anmin Xue, Minhui The School of Computer Science and Software Engineering The University of Western Australia Australia The School of Computer Science and Engineering Nanjing University of Science and Technology China Data61 CSIRO Australia The School of Cyber Science and Engineering Shanghai Jiao Tong University China The School of Information and Physical Sciences The University of Newcastle Australia

For the first time, we unveil discernible temporal (or historical) trajectory imprints resulting from adversarial example (AE) attacks. Standing in contrast to existing studies all focusing on spatial (or static) imprints within the targeted underlying victim models, we present a fresh temporal paradigm for understanding these attacks. Of paramount discovery is that these imprints are encapsulated within a single loss metric, spanning universally across diverse tasks such as classification and regression, and modalities including image, text, and audio. Recognizing the distinct nature of loss between adversarial and clean examples, we exploit this temporal imprint for AE detection by proposing TRAIT (Traceable Adversarial Temporal Trajectory Imprints). TRAIT operates under minimal assumptions without prior knowledge of attacks, thereby framing the detection challenge as a one-class classification problem. However, detecting AEs is still challenged by significant overlaps between the constructed synthetic losses of adversarial and clean examples due to the absence of ground truth for incoming inputs. TRAIT addresses this challenge by converting the synthetic loss into a spectrum signature, using the technique of Fast Fourier Transform to highlight the discrepancies, drawing inspiration from the temporal nature of the imprints, analogous to time-series signals. Across 12 AE attacks including SMACK (USENIX Sec’2023), TRAIT demonstrates consistent outstanding performance across comprehensively evaluated modalities (image, text, audio), tasks (classification and regression), datasets (nine datasets), and model architectures (e.g., ResNeXt50, BERT, RoBERTa, AudioNet). In all scenarios, TRAIT achieves an AE detection accuracy exceeding 97%, often around 99%, while maintaining a false rejection rate of 1%. TRAIT remains effective under the formulated strong adaptive attacks. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

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

引用

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

Novel Load Balancing Mechanism Based on Deep Reinforcement Learning for Human-Centric Applications in Data Centers

引用

Human-centric Computing and Information Sciences 2025年 15卷

作者： Hu, Jinbin Luo, Wangqing He, Yi Rao, Shuying Alqahtani, Fayez Tolba, Amr Zhu, Min Wang, Jin School of Computer and Communication Engineering Changsha University of Science and Technology Changsha China Software Engineering Department College of Computer and Information Sciences King Saud University Riyadh Saudi Arabia Department of Computer Science Community College King Saud University Riyadh Saudi Arabia College of Information Science and Technology Zhejiang Shuren University Zhejiang China

Human-computer interaction applications require ultra-low response delays to achieve a better user experience. With the rapid growth of data center network (DCN) topologies, the number of equal-cost paths has increased dramatically. It is imperative to use load balancing between parallel paths to improve link utilization. However, the existing load balancing mechanisms cannot make appropriate forwarding decisions for reacting to the dynamic traffic and path congestion status in large-scale DCNs, resulting in poor network performance. In this paper, we have proposed a dynamic load balancing (DLB) mechanism that uses deep reinforcement learning (DRL) to monitor the status of parallel paths in real time and uses the depth deterministic policy gradient algorithm to make the path state weight (PSW) automatically adapt to different network load scenarios. It then automatically configures the PSW through the DRL agent to guide the switch to select the best forwarding path to balance the load. The experimental results show that DLB significantly reduces the average flow completion by up to 36% compared to state-of-the-art load balancing schemes such as DRILL, LetFlow, and RPS under the asymmetric topology scenario, the result of which significantly enhances the efficiency of human-centric interaction. © (2024), (Korea Information Processing Society). All Rights Reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

PAFT: Prompt-Agnostic Fine-Tuning

arXiv

引用

arXiv 2025年

作者： Wei, Chenxing Shu, Yao Ou, Mingwen He, Ying Tiffany Yu, Fei Richard College of Computer Science and Software Engineering Shenzhen University China Tsinghua Shenzhen International Graduate School Tsinghua University China China School of Information Technology Carleton University Canada

While Large Language Models (LLMs) adapt well to downstream tasks after fine-tuning, this adaptability often compromises prompt robustness, as even minor prompt variations can significantly degrade performance. To address this, we propose prompt-agnostic fine-tuning (PAFT), a simple yet effective approach that dynamically adjusts prompts during fine-tuning. This encourages the model to learn underlying task principles rather than overfitting to specific prompt formulations. PAFT operates in two stages: First, a diverse set of meaningful, synthetic candidate prompts is constructed. Second, during fine-tuning, prompts are randomly sampled from this set to create dynamic training inputs. Extensive experiments across diverse datasets and LLMs demonstrate that models trained with PAFT exhibit strong robustness and generalization across a wide range of prompts, including unseen ones. This enhanced robustness improves both model performance and inference speed while maintaining training efficiency. Ablation studies further confirm the effectiveness of PAFT. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Sovereign Allocation of Resources in Cloud Milieus Using a Causal Dilated Geometric Algebra Approach for Dynamic Scalability 2

Enhancing Sovereign Allocation of Resources in Cloud Milieus...

引用

2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025

作者： Katru, Chandrasekhar Rao Srinivasan, Sathish Kumar, Mohan Yadwad, Sunita Satish, G. Maranan, Ramya Lead Software Engineer Indian LandSC29707 United States Machine Learning & AI Development Oracle Cloud Infrastructure Division San FranciscoCA United States Nitte Meenakshi Institute of Technology Department of Information Science and Engineering Karnataka Bengaluru India Parul institute of Engineering and Technology Parul University Computer science and Engineering Faculty of Engineering and Technology Gujarat India Sree Dattha Institute of Engineering and Science Department of Electrical and Electronics Engineering Telangana Sheriguda India Saveetha School of Engineering SIMATS Department of Research and Innovation Tamil Nadu Chennai India

ISBN: (纸本)9798331505745

Cloud environments utilize availability and usage of resources as crucial components in order to produce scalability, reliability and low cost. Such resource capabilities require autonomous systems that can handle these resources dynamically in spite of fluctuating workloads and service delivery requirements. Static models of resource management suffer from scalability and inability to react on the fly and accurately predict the demand thus causing Service Level Agreement (SLA) breaches and affecting the Quality of Service (QoS) as well as energy consumption profile. Advanced and elaborative cloud workloads require an intelligent system that can analyse the temporal and spatial patterns without impacting the overall system's performance significantly. Inspired by these challenges, this research proposes a Causal Dilated Geometric Algebra Convolutional Transformer Network (CATNet) along with the Prairie-Dog Optimizer (P-DogO), referred to as CAT-DogNet to learn and predict the dynamic scalability. CATNet integrates Causal Dilated Convolutional Networks in time domain for temporal structure capturing and Geometric Algebra Transformer for spatial resource coding. P-DogO adjusts weight parameters and losses for resource allocation, enhancing them depending on a work environment. A set of comprehensive assessments demonstrate a 0.85% SLA violation rate, average response time of less than 10ms, and overall 12.3% less energy consumption than baseline methods. The system had favourable predictability rates over 99.4% for the resource demand estimate. CAT-DogN et presents a sound and agnostic architecture for autonomous resource allocation in cloud environment, which indeed extend the state of art by considering flexibility, power consumption and QoS compliance. © 2025 IEEE.

关键词： Infrastructure as a service (IaaS)

来源：评论

学校读者我要写书评

暂无评论

High-Fidelity Editable Portrait Synthesis with 3D GAN Inversion

High-Fidelity Editable Portrait Synthesis with 3D GAN Invers...

引用

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

作者： Jindong Xie Jiachen Liu Yupei Lin Jinbao Wang Xianxu Hou Linlin Shen Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University School of Information Engineering Guangdong University of Technology Guangzhou China Guangdong Provincial Key Laboratory of Intelligent Information Processing School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

The 3D generative adversarial network (GAN) inversion converts an image into 3D representation to attain high-fidelity reconstruction and facilitate realistic image manipulation within the 3D latent space. However, previous approaches face challenges regarding the trade-off between the reconstruction ability and editability. That is, reversing a real-world image to a low-dimensional latent code would inevitably lead to information loss, and achieving a near-perfect reconstruction using high-rate triplane representation often limits the ability to manipulate the image freely in the latent space. To address these issues, we propose a novel latent conditioning encoder-based framework with the alignment between the low-dimensional latent and high-dimensional triplane. A non-semantic guided editing strategy bridges the intrinsic relation between the latent condition and triplane generation, making it possible to edit the high-dimensional representation by latent manipulation. As a result, our method can achieve high-fidelity reconstruction and editing simultaneously by directly controlling the latent code. Experimental results demonstrate that our approach excels in reconstruction and editing quality compared to previous 3D inversion methods. Furthermore, our method can also edit even real faces with large poses and out-of-domain cases.

关键词： Bridges Three-dimensional displays Codes Signal processing Generative adversarial networks Vectors Acoustics Speech processing Image reconstruction Faces

来源：评论

学校读者我要写书评

暂无评论

Comparison of machine learning techniques to predict students’ CGPA by using course learning outcomes datasets

引用

Human-Intelligent Systems Integration 2025年 1-11页

作者： Siraj, Saima Dahri, Fida Hussain Chandio, Jamil Ahmed Jalbani, Akhtar Hussain Laghari, Asif Ali Quaid-E-Awam University of Engineering Science & Technology Nawabshah Pakistan School of Computer Science and Engineering Southeast University Nanjing China Shah Abdul Latif University Khairpur Pakistan Software College Shenyang Normal University Shenyang China

As technology advances, traditional teaching, training, and performance evaluation approaches are being replaced by computer-based tools (CBT) such as online video courses, online exams, offline video classes, and flip classes. To improve the teaching and learning performance of the students, the education system (ES) assesses the course learning outcomes (CLO) by using the bloom taxonomy (BT). Owing to the abrupt COVID-19 epidemic, traditional classrooms are molded into online classes; therefore, it is very hard to assess the CLO because physical and online teaching pedagogies are heterogeneous, and it is very hard to classify either content has been generated by the students or any other online sources used to answer the questions. Thus, it is necessary to construct the classification model using artificial intelligence (AI) techniques and to assist educational stakeholders like schools, colleges, universities, NGOs, and the government in measuring student performance. This research proposes a comparative analysis of machine learning techniques to mitigate all the above-stated problems. It proposes methods to perform data cleaning in its first phase, whereas the second phase constructs classification models using machine learning algorithms such as decision tree, support vector machine, and random forest. In the third phase, performance evaluation is performed to estimate the results. The highest accuracy was achieved using a decision tree with 96.99% and 10 k-fold cross-validation. This research contributes (a) a real-world dataset and (b) the highest classification accuracy to analyze education.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ACRL-10K: A Dataset for Air Conditioner Refrigerant Leak Smoke Detection

ACRL-10K: A Dataset for Air Conditioner Refrigerant Leak Smo...

引用

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

作者： Yuhan Jiang Zhongyuan Wang Jie Hua Jinbi Liang Zengmin Xu National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan China School of Mathematics and Computing Science Guilin University of Electronic Technology Guilin China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In this paper, we introduce a new dataset for air conditioner refrigerant leak smoke detection, called ACRL-10K. The dataset is designed to develop algorithms for detecting refrigerant leak smoke faults during air conditioner recycling. It contains a total of 10,724 images covering three common scenarios of air conditioner refrigerant leak: loading port, refrigerant extraction, and disassembly. All images are sourced from 656 video segments of real air conditioner recycling scenarios, captured by surveillance cameras deployed on an environmental company’s recycling production line. The annotations for the refrigerant leak smoke in the images are performed by industry experts to ensure high accuracy and consistency. To the best of our knowledge, ACRL-10K is the first dataset specifically designed for refrigerant leak smoke detection. Based on the ACRL-10K dataset, we present the performance of mainstream object detectors, including the YOLO series, as a baseline to conduct the following work: 1) preliminarily summarize the challenges of using the dataset for refrigerant leak smoke detection; 2) show the detection results of benchmark methods; and 3) make a comparison to identify the strengths and weaknesses of the baseline algorithms. In practice, the ACRL-10K dataset would hopefully advance research and applications in refrigerant leak early warning during air conditioner dismantling and recycling processes.

关键词： YOLO Image segmentation Accuracy Surveillance Loading Signal processing algorithms Production Detectors Cameras Recycling

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：