检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Li, Kun Guo, Dan Wang, Meng School of Computer Science and Information Engineering Hefei University of Technology Hefei230601 China Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Hefei230601 China Intelligent Interconnected Systems Laboratory of Anhui Province Hefei230601 China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei230088 China

The video grounding (VG) task aims to locate the queried action or event in an untrimmed video based on rich linguistic descriptions. Existing proposal-free methods are trapped in complex interaction between video and query, overemphasizing cross-modal feature fusion and feature correlation for VG. In this paper, we propose a novel boundary regression paradigm that performs regression token learning in a transformer. Particularly, we present a simple but effective proposal-free framework, namely Video Grounding Transformer (ViGT), which predicts the temporal boundary using a learnable regression token rather than multi-modal or cross-modal features. In ViGT, the benefits of a learnable token are manifested as follows. (1) The token is unrelated to the video or the query and avoids data bias toward the original video and query. (2) The token simultaneously performs global context aggregation from video and query features. First, we employed a sharing feature encoder to project both video and query into a joint feature space before performing cross-modal co-attention (i.e., video-to-query attention and query-to-video attention) to highlight discriminative features in each modality. Furthermore, we concatenated a learnable regression token [REG] with the video and query features as the input of a vision-language transformer. Finally, we utilized the token [REG] to predict the target moment and visual features to constrain the foreground and background probabilities at each timestamp. The proposed ViGT performed well on three public datasets: ANet Captions, TACoS and YouCookII. Extensive ablation studies and qualitative analysis further validated the interpretability of ViGT. Copyright © 2023, The Authors. All rights reserved.

关键词： Regression analysis

来源：评论

学校读者我要写书评

暂无评论

Multi-objective Aerial IRS-assisted ISAC Optimization via Generative AI-enhanced Deep Reinforcement Learning

arXiv

引用

arXiv 2025年

作者： Xie, Wenwen Sun, Geng Wang, Jiacheng Du, Hongyang Kang, Jiawen Huang, Kaibin Leung, Victor C.M. College of Computer Science and Technology Jilin University Changchun130012 China College of Computing and Data Science Nanyang Technological University Singapore639798 Singapore Department of Electrical and Electronic Engineering The University of Hong Kong 999077 Hong Kong School of Automation Guangdong University of Technology Guangzhou510006 China Artificial Intelligence Research Institute Shenzhen MSU-BIT University Shenzhen518115 China College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Department of Electrical and Computer Engineering The University of British Columbia VancouverV6T 1Z4 Canada

Integrated sensing and communication (ISAC) has garnered substantial research interest owing to its pivotal role in advancing the development of next-generation (6G) wireless networks. However, achieving a performance balance between communication and sensing in the dual-function radar communication (DFRC)-based ISAC system remains a significant challenge. In this paper, an aerial intelligent reflecting surface (IRS)-assisted ISAC system is explored, where a base station (BS) supports dual-functional operations, enabling both data transmission for multiple users and sensing for a blocked target, with the channel quality enhanced by an IRS mounted on the unmanned aerial vehicle (UAV). Moreover, we formulate an integrated communication, sensing, and energy efficiency multi-objective optimization problem (CSEMOP), which aims to maximize the communication rate of the users and the echo rate of the target, while minimizing UAV propulsion energy consumption by jointly optimizing the BS beamforming matrix, IRS phase shifts, the flight velocity and angle of the UAV. Considering the non-convexity, trade-off, and dynamic nature of the formulated CSEMOP, we propose a generative diffusion model-based deep deterministic policy gradient (GDMDDPG) method to solve the problem. Specifically, the diffusion model is incorporated into the actor network of DDPG to improve the action quality, with noise perturbation mechanism for better exploration and recent prioritized experience replay (RPER) sampling mechanism for enhanced training efficiency. Simulation results indicate that the GDMDDPG method delivers superior performance compared to the existing methods. Copyright © 2025, The Authors. All rights reserved.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Examining the Impact of data Mining on Decision-Making Processes

Examining the Impact of Data Mining on Decision-Making Proce...

引用

Smart Generation Computing, Communication and Networking (SMART GENCON), International Conference on

作者： Vaishali Singh Pratik Pandey Prateek Aggarwal Reena R Suvarna R. Bhagwat Sunil MP Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Department of Computer Science & Engineering Vivekananda Global University Jaipur India Centre of Interdisciplinary Research in Business and Technology Chitkara University Institute of Engineering and technology Chitkara University Punjab India Department of Computer Science and Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai Department of Artificial Intelligence & Data Science Vishwakarma Institute of Information Technology Pune India Department of Electronics and Communication Engineering Faculty of Engineering and Technology JAIN (Deemed-to-be University) Bangalore Karnataka India

Statistics mining has emerged as a crucial device for agencies in the past two decades that significantly impact selection-making methods. It can be used to gain insights from massive datasets and might assist with an employer's marketing approach, operational performance, customer segmentation, etc. This paper will explore the impact information mining has on decision-making approaches, especially regarding coming across new styles and relationships. It will discuss the blessings of using records mining and how it may help decorate choice-making. It will also look at various methods used to extract statistics from massive datasets and how they facilitate the selection-making method. Finally, it will discuss a number of the constraints of information mining and the ability of answers to overcome them. Standard, this paper aims to pick out the effect of information mining on the choice-making system and how it may be leveraged as a practical device.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Removing Interference and Recovering Content Imaginatively for Visible Watermark Removal

arXiv

引用

arXiv 2023年

作者： Leng, Yicheng Fang, Chaowei Li, Gen Fang, Yixiang Li, Guanbin School of Artificial Intelligence Xidian University Xi’an China School of Data Science The Chinese University of Hong Kong Shenzhen China Afirstsoft Shenzhen China School of Computer Science and Engineering Research Institute of Sun Yat-sen University in Shenzhen Sun Yat-sen University Guangzhou China GuangDong Province Key Laboratory of Information Security Technology China

Visible watermarks, while instrumental in protecting image copyrights, frequently distort the underlying content, complicating tasks like scene interpretation and image editing. Visible watermark removal aims to eliminate the interference of watermarks and restore the background content. However, existing methods often implement watermark component removal and background restoration tasks within a singular branch, leading to residual watermarks in the predictions and ignoring cases where watermarks heavily obscure the background. To address these limitations, this study introduces the Removing Interference and Recovering Content Imaginatively (RIRCI) framework. RIRCI embodies a two-stage approach: the initial phase centers on discerning and segregating the watermark component, while the subsequent phase focuses on background content restoration. To achieve meticulous background restoration, our proposed model employs a dual-path network capable of fully exploring the intrinsic background information beneath semi-transparent watermarks and peripheral contextual information from unaffected regions. Moreover, a Global and Local Context Interaction module is built upon multi-layer perceptrons and bidirectional feature transformation for comprehensive representation modeling in the background restoration phase. The efficacy of our approach is empirically validated across two large-scale datasets, and our findings reveal a marked enhancement over existing watermark removal techniques. Copyright © 2023, The Authors. All rights reserved.

关键词： Restoration

来源：评论

学校读者我要写书评

暂无评论

Transformer-Based Astronomical Time Series Model with Uncertainty Estimation for Detecting Misclassified Instances

arXiv

引用

arXiv 2024年

作者： Cádiz-Leyton, Martina Cabrera-Vives, Guillermo Protopapas, Pavlos Moreno-Cartagena, Daniel Donoso-Oliva, Cristobal Department of Computer Science Universidad de Concepción Chile Center for Data and Artificial Intelligence Universidad de Concepción Edmundo Larenas 310 Concepción Chile Chile Nuncio Monseñor Sotero Sanz 100 Of. 104 Providencia Santiago Chile John A. Paulson School of Engineering and Applied Science Harvard University CambridgeMA02138 United States

In this work, we present a framework for estimating and evaluating uncertainty in deep-attention-based classifiers for light curves for variable stars. We implemented three techniques, Deep Ensembles (DEs), Monte Carlo Dropout (MCD) and Hierarchical Stochastic Attention (HSA) and evaluated models trained on three astronomical surveys. Our results demonstrate that MCD and HSA offers a competitive and computationally less expensive alternative to DE, allowing the training of transformers with the ability to estimate uncertainties for large-scale light curve datasets. We conclude that the quality of the uncertainty estimation is evaluated using the ROC AUC metric. Copyright © 2024, The Authors. All rights reserved.

关键词： Stochastic models

来源：评论

学校读者我要写书评

暂无评论

SmartTrap: An On-Field Insect Monitoring System Empowered by Edge Computing Capabilities

SmartTrap: An On-Field Insect Monitoring System Empowered by...

引用

IEEE International Conference on Research, Innovation and Vision for the Future

作者： Quan M. Nguyen Duy A. Pham Dong T. Pham An D. Le Nguyen Q. H. Vo Hien B. Vo School of Electrical and Electronic Engineering Hanoi University of Science and Technology Hanoi Vietnam Joint Lab Artificial Intelligence and Data Science Universität Osnabrück Osnabrück Germany Graduate School of Bioresource and Bioenvironmental Sciences Kyushu University Fukuoka Japan Department of Electrical and Computer Engineering University of California San Diego San Diego USA Department of Electrical and Computer Engineering Vietnamese-German University Binh Duong Vietnam

Fruit flies pose a significant threat to fruit yields, necessitating immediate detection solutions for effective pest management. In this study, we present our approach using YOLOv7 and the Jetson Nano 4GB for rapid and accurate fruit fly detection. Our methodology attains an Average Precision (AP) of 0.993 at an Intersection over Union threshold (IoU) of 0.75, facilitating almost instantaneous enumeration of ensnared fruit flies in field conditions, thereby augmenting the efficacy of pest management practices. Concurrently, the system transmits this data to either a local or cloud-based server, assisting end-users in accurately identifying regions with elevated fruit fly densities to strategically administer pesticides. This targeted approach has significant implications for sustainable agriculture as it reduces the need for widespread spraying. Moreover, our versatile method adapts for detecting other pests like aphids or beetles, serving as a valuable tool in agriculture and beyond.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Discovering Innovative Applications for Real-Time data Analysis with Machine Learning

Discovering Innovative Applications for Real-Time Data Analy...

引用

Smart Generation Computing, Communication and Networking (SMART GENCON), International Conference on

作者： Prranjali Jadhav Raja Praveen K N Prateek Aggarwal Sandeep Gautam Preeti Naval D. Nirmala Department of Artificial Intelligence & Data Science Vishwakarma Institute of Information Technology Pune INDIA Computer Science and Engineering Faculty of Engineering and Technology JAIN (Deemed-to-be University) Bangalore Karnataka India Centre of Interdisciplinary Research in Business and Technology Chitkara University Institute of Engineering and technology Chitkara University Punjab India Department of Computer Science & Engineering Vivekananda Global University Jaipur India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Department of Electronics and Communication Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai

This paper investigates the capability for discovering modern programs for actual-time information analysis the use of system learning. We will take a look at the technology and strategies used in system getting to know and talk their adaptive potential to interpret and analyze dynamically changing facts inputs. Especially, we can examine existing technological methods to understand the capacity of AI to discover creative solutions to complicated challenges. We will also explore capability techniques to contain gadget gaining knowledge of into present real-time records analysis platforms and architectures. Finally, we are able to speak the programs of machine studying in real-time records evaluation and its potential to allow fast and correct decision making. This paper gives a theoretical framework to apprehend and harness the power of device gaining knowledge of to investigate and interpret real-time facts in modern approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing data Visualization in Real-Time with Machine Learning

Enhancing Data Visualization in Real-Time with Machine Learn...

引用

Smart Generation Computing, Communication and Networking (SMART GENCON), International Conference on

作者： Sripriya T Renu Kachhoria Sudhanshu Dev Mahesh TR Nivesh Kalyan Acharjya Department of Electronics and Communication Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai Department of Artificial Intelligence & Data Science Vishwakarma Institute of Information Technology Pune India Centre of Interdisciplinary Research in Business and Technology Chitkara University Institute of Engineering and technology Chitkara University Punjab India Computer Science and Engineering Faculty of Engineering and Technology JAIN (Deemed-to-be University) Bangalore Karnataka India Department of Computer Science & Engineering Vivekananda Global University Jaipur India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India

Statistics visualization is an effective tool for information and communicating insights from massive facts sets. However, giving complicated records in a correct and complete style becomes challenging, mainly when the statistics are dynamic and change rapidly in real time. Device learning may be leveraged to enhance records visualization, making it more particular and comprehensive. This paper discusses the integration of machine learning techniques to enhance data visualization in real-time. The exponential growth of data in recent years has made it challenging for traditional techniques to effectively visualize and interpret data in real-time. Machine learning algorithms offer the ability to analyze and classify data in real-time, providing a more accurate and efficient way to visualize complex datasets. By leveraging machine learning, data visualization can be enhanced by automatically generating visual representations that are tailored to the data and user preferences. This paper presents an overview of the different machine learning techniques that can be applied to data visualization, along with their advantages and limitations. Additionally, a case study is presented to demonstrate the effectiveness of using machine learning for real-time data visualization. Through this study, it is shown that the integration of machine learning can significantly improve the speed, accuracy, and usability of data visualization in real-time scenarios. By using including the strength of machine learning to statistics visualization, such methods can permit quicker and deeper insights into records, taking into consideration higher selection making within the modern-day international wherein facts modifications swiftly.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A human activity recognition approach based on skeleton extraction and image reconstruction 21

A human activity recognition approach based on skeleton extr...

引用

5th International Conference on Graphics and Signal Processing, ICGSP 2021

作者： Chen, Yanbing Ke, Wei Chan, Ka-Hou Xiong, Zhang School of Applied Sciences Macao Polytechnic Institute Macao SAR China Engineering Research Centre of Applied Technology on Machine Translation and Artificial Intelligence Ministry of Education Macao Polytechnic Institute Macao SAR China School of Computer Science and Engineering Beihang University Beijing China

ISBN: (纸本)9781450389419

Human Activity Recognition (HAR) has wide applications in surveillance, assisted living and robotic systems that interact with people. Traditional methods for HAR usually input source images directly. Various factors of these direct source images can affect the accuracy of recognition, such as heights, weights, poses, angles and whether being obscured or not. Most of the latest research on HAR has mainly focused on the use of 2D skeleton data, extracted from videos captured by standard cameras. Inspired by this trend, we propose a novel way of using skeleton data in this paper. As a pre-processing phase, we adopt the OpenPose library to extract 2D positions of human skeleton joints, then reconstruct, or synthesize, the skeleton image from these joints, together with coloring to encode the categories of different human parts. The reconstructed images are put into a Convolutional Neural Network (CNN) structure for classification, to obtain the recognition result. We implement the typical four activity classes, i.e., squat, stand, walk and work, in our experiments. Compared with feeding the original complex source images, our approach reduces the complexity of the neural network thus the time consumption, and improves the recognition accuracy significantly. All the images that we used for training and testing are collected from the real public places. We achieved a recognition accuracy of 97.3% in our experiments, indicating that our method has very good performance. Thanks to the lightning speed of the OpenPose library, our method can be carried out in real-time. The demonstration of using synthesized input to bridge existing technologies also has its general significance. © 2021 ACM.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Adaptive Solar Energy Storage with Deep Learning for Improved Grid Resilience

Adaptive Solar Energy Storage with Deep Learning for Improve...

引用

Trends in Material science and Inventive Materials (ICTMIM), International Conference on

作者： C.Shobana Nageswari Pramod Pandey Sujitha R Sujatha M S. Senthilkumar S. Sujatha Department of ECE R.M.D. Engineering College Chennai Tamil Nadu India Symbiosis Institute of Technology Nagpur Campus Symbiosis International (Deemed University) Pune Maharashtra India Department of Computer Science and Engineering Annapoorana Engineering College (Autonomous) Salem Tamil Nadu India Department of Electrical and Electronics Engineering Easwari Engineering College Chennai Tamil Nadu India Department of Computer Science and Engineering Centre for Artificial Intelligence & Data Science (CAI) Vinayaka Mission’s Kirupananda Variyar Engineering College Vinayaka Mission’s Research Foundation ( DU) Salem Tamil Nadu India Department of Biomedical Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamil Nadu India

ISBN: (数字)9798331501488

ISBN: (纸本)9798331501495

Implementing renewable energy sources, especially solar power, into the electrical grid has distinct difficulties and potential for improving system resilience. This research investigates an adaptive solar energy storage system using deep learning methodologies, particularly Long Short-Term Memory (LSTM) networks, to enhance energy management and grid stability. The proposed system utilizes past solar generating data and usage patterns to forecast future energy needs and generation capacities. LSTM allows the model to efficiently reflect temporal interdependence and variation in solar energy output, facilitating more precise forecasting. The adaptive storage system modifies its charging and discharging processes in real time, optimizing efficiency and reducing energy waste. LSTM-based forecasting improves the storage system’s response to variations in supply and demand, enhancing load balancing and grid resilience. This method facilitates a change in renewable energy sources while enhancing the resilience of grid infrastructure to sustain delays. Findings indicate that integrating flexible energy storage using advanced deep-learning methodologies may significantly improve the efficacy and dependability of solar energy systems. This paper challenges solar energy intermittency with LSTM-based adaptive storage, enhancing forecasting precision, grid resilience, and energy efficiency enhancing stable energy management and optimized battery use.

关键词： Deep learning Renewable energy sources Computational modeling Solar energy Predictive models Real-time systems Robustness Forecasting Long short term memory Resilience

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：