检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Wang, Zihan Song, Siyang Luo, Cheng Deng, Songhe Xie, Weicheng Shen, Linlin Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China University of Leicester United Kingdom Monash University Australia

Human facial action units (AUs) are mutually related in a hierarchical manner, as not only they are associated with each other in both spatial and temporal domains but also AUs located in the same/close facial regions show stronger relationships than those of different facial regions. While none of existing approach thoroughly model such hierarchical inter-dependencies among AUs, this paper proposes to comprehensively model multi-scale AU-related dynamic and hierarchical spatio-temporal relationship among AUs for their occurrences recognition. Specifically, we first propose a novel multi-scale temporal differencing network with an adaptive weighting block to explicitly capture facial dynamics across frames at different spatial scales, which specifically considers the heterogeneity of range and magnitude in different AUs’ activation. Then, a two-stage strategy is introduced to hierarchically model the relationship among AUs based on their spatial distribution (i.e., local and cross-region AU relationship modelling). Experimental results achieved on BP4D and DISFA show that our approach is the new state-of-the-art in the field of AU occurrence recognition. Our code is publicly available at https://***/CVI-SZU/MDHR. © 2024, CC BY.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Large Model for Small Data: Foundation Model for Cross-Modal RF Human Activity Recognition

arXiv

引用

arXiv 2024年

作者： Weng, Yuxuan Wu, Guoquan Zheng, Tianyue Yang, Yanbing Luo, Jun Department of Computer Science and Engineering Southern University of Science and Technology China Smart City Center Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology China College of Computer Science Sichuan University China College of Computing and Data Science Nanyang Technological University Singapore

Radio-Frequency (RF)-based Human Activity Recognition (HAR) rises as a promising solution for applications unamenable to techniques requiring computer visions. However, the scarcity of labeled RF data due to their non-interpretable nature poses a significant obstacle. Thanks to the recent breakthrough of foundation models (FMs), extracting deep semantic insights from unlabeled visual data become viable, yet these vision-based FMs fall short when applied to small RF datasets. To bridge this gap, we introduce FM-Fi, an innovative cross-modal framework engineered to translate the knowledge of vision-based FMs for enhancing RF-based HAR systems. FM-Fi involves a novel cross-modal contrastive knowledge distillation mechanism, enabling an RF encoder to inherit the interpretative power of FMs for achieving zero-shot learning. It also employs the intrinsic capabilities of FM and RF to remove extraneous features for better alignment between the two modalities. The framework is further refined through metric-based few-shot learning techniques, aiming to boost the performance for predefined HAR tasks. Comprehensive evaluations evidently indicate that FM-Fi rivals the effectiveness of vision-based methodologies, and the evaluation results provide empirical validation of FM-Fi’s generalizability across various environments. © 2024, CC BY.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Exploring the Influence of Digital Media on Secondary School Students' Daily Lives

Exploring the Influence of Digital Media on Secondary School...

引用

International IEEE Conference and Workshop: Óbuda on Electrical and Power engineering (CANDO-EPE)

作者： Előd Gőgh Attila Kovari Institute of Digital Technology Faculty of Computer Science Eszterházy Károly Catholic University Eger Hungary Institute of Electronics and Communication Systems Kandó Kálmán Faculty of Electrical Engineering Obuda University Budapest Hungary Institute of Computer Science University of Dunaujvaros Dunaujvaros Hungary

ISBN: (数字)9798331531119

ISBN: (纸本)9798331531126

The focus of this study is to investigate how digital media use affects the daily activities, emotional well-being, and general lifestyle of high school students in relation to education amidst concerns about a “new terrain or venue” for learning in an era moving full swing towards digitization. The study, conducted with students from grades 9–11, seeks to identify overall trends and associations involving digital media interactions: considering both byproducts of using new technology as an educational tool- in addition discursive aspects allowing for different forms of distraction. In summary, the results showed that digital media use is common and often regarded as educationally beneficial or a positive form of relaxation; however, daily activities are it affected by substantial adverse impacts on everyday life and time management. Suggestions focus on supporting healthy digital media habits, including content-wise engagement and time management tools.

关键词： Surveys Power engineering Mood Education Media Market research

来源：评论

学校读者我要写书评

暂无评论

RDEIC: Accelerating Diffusion-Based Extreme Image Compression with Relay Residual Diffusion

arXiv

引用

arXiv 2024年

作者： Li, Zhiyuan Zhou, Yanhui Wei, Hao Ge, Chenyang Mian, Ajmal Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an710049 China Department of Computer Science and Software Engineering The University of Western Australia Crawley PerthWA6009 Australia

Diffusion-based extreme image compression methods have achieved impressive performance at extremely low bitrates. However, constrained by the iterative denoising process that starts from pure noise, these methods are limited in both fidelity and efficiency. To address these two issues, we present Relay Residual Diffusion Extreme Image Compression (RDEIC), which leverages compressed feature initialization and residual diffusion. Specifically, we first use the compressed latent features of the image with added noise, instead of pure noise, as the starting point to eliminate the unnecessary initial stages of the denoising process. Second, we directly derive a novel residual diffusion equation from Stable Diffusion’s original diffusion equation that reconstructs the raw image by iteratively removing the added noise and the residual between the compressed and target latent features. In this way, we effectively combine the efficiency of residual diffusion with the powerful generative capability of Stable Diffusion. Third, we propose a fixed-step fine-tuning strategy to eliminate the discrepancy between the training and inference phases, thereby further improving the reconstruction quality. Extensive experiments demonstrate that the proposed RDEIC achieves state-of-the-art visual quality and outperforms existing diffusion-based extreme image compression methods in both fidelity and efficiency. The source code and pre-trained models will be released. Copyright © 2024, The Authors. All rights reserved.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

RIDA: Cross-App Record and Replay for Android

RIDA: Cross-App Record and Replay for Android

引用

International Conference on software Testing, Verification, and Validation, ICST

作者： Jiayuan Liang Sinan Wang Xiangbo Deng Yepang Liu Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China

The number of Android apps keeps increasing in recent years. Despite the fact that there exist apps for various kinds of purposes, apps that share similar functionalities with existing ones are still emerging on the market. To reduce the effort in testing such apps, previous research has proposed approaches for migrating test scripts across similar apps. However, such test reuse techniques require existing test suites for migrating, which hinders their practical use in commercial app development. Unlike script-based GUI testing, record-and-replay techniques are more convenient for human testers who are unfamiliar with programming. In this paper, we propose a new testing technique, RIDA, that records interaction sequences on one app (source app) and replays them on another app (target app) with similar functionalities. Such cross-app record-and-replay is challenging. First, there are no clear mappings between the recorded sequences on source apps and the sequences required to be performed on the target apps. Second, reliable indicators of widgets’ functionalities are not always available from the recorded sequences, which limits the effectiveness of event matching between source and target apps. To address the challenges, we design an on-the-fly searching algorithm for finding target widgets during cross-app replay and leverage multiple semantic descriptors together with image captioning techniques to infer the functionalities of widgets. We have implemented RIDA and evaluated it using both controlled and in-the-wild experiments. The results show that RIDA can effectively perform cross-app record-and-replay and outperform baseline methods in terms of the number of completely- and partially- replayed events.

关键词： software testing Semantics Programming Reliability Graphical user interfaces

来源：评论

学校读者我要写书评

暂无评论

The New Frontier in Media: AI-Driven Content Creation for Ad-Supported TV using Generative Adversarial Network

The New Frontier in Media: AI-Driven Content Creation for Ad...

引用

International Conference of computer and Informatics engineering (IC2IE)

作者： Shashishekhar Ramagundam Niharika Karne Software Development & Engineering in Content Discovery & AI Comcast USA AL. Department of Computer Science Masters in Computer Science Troy University Montgomery Campus USA Sr. Principal Systems Engineer in C& RS Platform Services DT Amtrak USA Department of Electrical Engineering Masters in Electrical Engineering University of South Alabama USA

ISBN: (数字)9798331505530

ISBN: (纸本)9798331505547

The use of Artificial intelligence (AI) technology in the content creation to produce creative aspects like editing, audience analysis, creating ideas, writing copy, etc. The major aim is to streamline and automate the process of content creation and convert it into a more efficient and effective way. There is a lack of transparency in the AI content production process and hence it does not exactly mimic human activities, which includes fantasizing and picking up new abilities. AI content creation requires more creativity while investigating with a specific goal in mind. Although, AI faces many challenges since it constantly expands its base knowledge. One of the biggest ethical problems is the probability that AI content is used to deceive or influence people. Hence, to overcome these difficulties a machine learning-based Artificial Intelligent content creation framework is generated for content creation in Ad-supported TV. Here, an effective model Generative Adversarial Network (GAN) introduced to deliver enterprise data, customize descriptions, and adjust content based on consumer behaviors. This developed model produces material that is closely related to the preferences of the user. AI content creation increases efficiency and productivity by saving time and money. It also leads to the development of better content. Finally, the experimental analysis is performed to find the effectiveness of the developed deep learning-based AI content creation framework via various metrics.

关键词： Productivity Measurement Deep learning Ethics TV Media Generative adversarial networks Artificial intelligence Informatics Faces

来源：评论

学校读者我要写书评

暂无评论

Research on Fault Diagnosis Method Based on Structural Causal Model in Tennessee Eastman Process 7th

Research on Fault Diagnosis Method Based on Structural Causa...

引用

7th International Conference on Computing, Control and Industrial engineering, CCIE 2023

作者： Pu, Haoyuan Liu, Jie Chen, Zhi Yang, Xiaohua Ren, Changan Xu, Zhuoran Jian, Yifan School of Computer Science University of South China Hengyang China Science and Technology on Reactor System Design Technology Laboratory Nuclear Power Institute of China Chengdu China Intelligent Equipment Software Evaluation Engineering Technology Research Center of Hunan Hengyang China CNNC Key Laboratory on High Trusted Computing Hengyang China School of Nuclear Science and Technology University of South China Hengyang China

ISBN: (纸本)9789819927296

In the practical application of fault diagnosis in large-scale chemical systems, due to the danger of faults, the machine learning diagnosis methods used in current research often face the problem of scarcity of fault samples. This makes it difficult for the model to be trained effectively, thus affecting the fault detection rate of the model. Therefore, for the fault diagnosis of chemical system with small sample data, this paper proposes a diagnostic method that uses structural causal model to further combine the diagnostic results of the two machine learning methods, thereby improving global diagnostic performance. With the help of powerful system description ability of structural causal model, we can establish a causal graph for diagnostic process of the chemical system, and accurately construct the corresponding structural equations for the various diagnostic results of the two machine learning methods to combine them, thus improve the fault detection rate. The global results make up for the shortcomings of single machine learning method in small sample chemical system fault diagnosis. The verification on the chemical system simulation platform Tennessee Eastman process shows that, compared with the diagnosis results of the selected Gaussian Naive Bayes method and the K-nearest neighbour method, the results obtained by our method are effectively improved in fault detection rate of each fault in TEP. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

A Framework for Cyber-Secure Monitoring and Safe Operation of Solar PV Microgrids

A Framework for Cyber-Secure Monitoring and Safe Operation o...

引用

IEEE Energy Conversion Congress and Exposition, ECCE

作者： Jaewon Kim Marija Ilic Le Xie Laboratory for Information & Decision Systems Massachusetts Institute of Technology Cambridge MA USA Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Cambridge MA USA Department of Electrical & Computer Engineering Texas A&M University College Station TX USA

ISBN: (数字)9798350376067

ISBN: (纸本)9798350376074

In this paper, we introduce a systematic design of an end-to-end cyber-secure monitoring and safe operation framework for solar photovoltaic (PV)-rich microgrids, by focusing on the use of on-line attack detector for defending against potential cyber-physical attacks and sensor measurement data processing for operational safety. The proposed approach is based on: 1) identifying component models using their input and output measurements; 2) dynamic watermarking (DW) methodology for on-line cyber-attack detection and its timing; and 3) an adaptive event-driven safe shutdown procedure after attack detection. It is shown how these three components interactive steps jointly to ensure safe operation under both normal operational scenarios and compromised operational scenarios with some malicious sensors caused by cyber-attacks on solar PV microgrids. Through this on-line integration, the proposed framework dynamically adapts to varying solar irradiance, load demands, operating conditions, and potential cyber-physical attacks. This forms a cyber-physical system which can pro-actively detect and mitigate potential cyber-physical attacks on solar PV microgrids. We describe its proof-of-concept implementation using real-world industrial solar farm data provided by the CenterPoint Energy. This study contributes to enhancing the cyber-security and safe operation of solar PVrich power systems, offering a scalable solution to other types of emerging renewable-rich energy distribution systems.

关键词： Photovoltaic systems Adaptation models Systematics Solar farms Power system dynamics Microgrids Watermarking Timing Monitoring Cyberattack

来源：评论

学校读者我要写书评

暂无评论

SABER: Model-agnostic Backdoor Attack on Chain-of-Thought in Neural Code Generation

arXiv

引用

arXiv 2024年

作者： Jin, Naizhu Li, Zhong Guo, Yinggang Su, Chao Zhang, Tian Zeng, Qingkai State Key Laboratory for Novel Software Technology Nanjing University Jiangsu Nanjing210023 China School of Computer Science and Engineering Changshu Institute of Technology Jiangsu Suzhou215506 China

Recent studies have proposed integrating Chain-of-Thought (CoT) reasoning to further enhance the reliability of Code Language Models (CLMs) in generating code, a step-by-step approach that breaks down complex programming tasks into manageable sub-problems. Advances in this area have introduced CoT models, specifically designed to integrate CoT reasoning effectively into language models, achieving notable improvements in code generation. Despite these advancements, the security of CoT models has not been systematically studied. In this study, we aim to fill this gap by investigating the vulnerability of CoT models to backdoor injection in code generation tasks. To address this, we propose a model-agnostic backdoor attack method SABER (Self-Attention-BasEd backdooR) based on the self-attention mechanism. SABER begins by selecting a malicious output as the backdoor using code mutation operations. It then identifies tokens most relevant to poisoned content by analyzing self-attention scores in the CodeBERT model. Finally, it applies semantic-preserving perturbations to generate adaptive and natural triggers. Our experiments on HumanEval-CoT and OpenEval-CoT test sets demonstrate that CoT models are susceptible to backdoor attacks via data poisoning. Taking the OpenEval-CoT dataset as an example, SABER achieves an ASR of 76.19%, representing an improvement of 14.29% over RIPPLe and a substantial 23.08% enhancement compared to BadPre. Further evaluations using ONION for automated detection and human studies reveal that SABER is stealthier and harder to detect, bypassing 77.27% of automated detection, with a human detection rate of just 3.17%. Our findings reveal that backdoors can be injected into CoT models to manipulate downstream code generation tasks. This highlights the urgent need for further research to understand and mitigate the security vulnerabilities in CoT models. We advocate for increased efforts to explore the security threats facing CoT models and to devel

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A probabilistic model for personality trait focused explainability 15

A probabilistic model for personality trait focused explaina...

引用

15th European Conference on software Architecture - Companion, ECSA-C 2021

作者： Alharbi, Mohammed N. Huang, Shihong Garlan, David Department of Computer and Electrical Engineering and Computer Science Florida Atlantic University Boca RatonFL United States Institute for Software Research School of Computer Science Carnegie Mellon University PittsburghPA United States

Explainability refers to the degree to which a software system’s actions or solutions can be understood by humans. Giving humans the right amount of explanation at the right time is an important factor in maximizing the effective collaboration between an adaptive system and humans during interaction. However, explanations come with costs, such as the required time of explanation and humans’ response time. Hence it is not always clear whether explanations will improve overall system utility and, if so, how the system should effectively provide explanation to humans, particularly given that different humans may benefit from different amounts and frequency of explanation. To provide a partial basis for making such decisions, this paper defines a formal framework that incorporates human personality traits as one of the important elements in guiding automated decision-making about the proper amount of explanation that should be given to the human to improve the overall system utility. Specifically, we use probabilistic model analysis to determine how to utilize explanations in an effective way. To illustrate our approach, Grid – a virtual human and system interaction game - is developed to represent scenarios for human-systems collaboration and to demonstrate how a human’s personality traits can be used as a factor to consider for systems in providing appropriate explanations. Copyright © 2021 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

关键词： Human computer interaction

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：