检索结果-内蒙古大学图书馆

Few-Shot Referring Video Single- and Multi-Object Segmentation Via Cross-Modal Affinity with Instance Sequence Matching

引用

International Journal of computer Vision 2025年 1-19页

作者： Liu, Heng Li, Guanghui Gao, Mingqi Zhen, Xiantong Zheng, Feng Wang, Yang School of Computer Science and Technology Anhui University of Technology Maxiang Road Ma’anshan243032 China Department of Computer Science and Engineering Southern University of Science and Technology Xueyuan Avenue Shenzhen518055 China School of Computer Science and Information Engineering Hefei University of Technology Feicui Road Hefei230601 China

Referring Video Object Segmentation (RVOS) aims to segment specific objects in videos based on the provided natural language descriptions. As a new supervised visual learning task, achieving RVOS for a given scene requires a substantial amount of annotated data. However, only minimal annotations are usually available for new scenes in realistic scenarios. Another practical problem is that, apart from a single object, multiple objects of the same category coexist in the same scene. Both of these issues may significantly reduce the performance of existing RVOS methods in handling real-world applications. In this paper, we propose a simple yet effective model to address these issues by incorporating a newly designed cross-modal affinity (CMA) module based on a Transformer architecture. The CMA module facilitates the establishment of multi-modal affinity over a limited number of samples, allowing the rapid acquisition of new semantic information while fostering the model’s adaptability to diverse scenarios. Furthermore, we extend our FS-RVOS approach to multiple objects through a new instance sequence matching module over CMA, which filters out all object trajectories with similarity to language features that exceed a matching threshold, thereby achieving few-shot referring multi-object segmentation (FS-RVMOS). To foster research in this field, we establish a new dataset based on currently available datasets, which covers many scenarios in terms of single-object and multi-object data, hence effectively simulating real-world scenes. Extensive experiments and comparative analyses underscore the exceptional performance of our proposed FS-RVOS and FS-RVMOS methods. Our method consistently outperforms existing related approaches through practical performance evaluations and robustness studies, achieving optimal performance on metrics across diverse benchmark tests. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Modal analysis

来源：评论

学校读者我要写书评

暂无评论

Utilizing the Power of Residual and Attention Properties with Binary Focal Loss Optimization for Underwater Image Segmentation Using UNet Architecture 7th

Utilizing the Power of Residual and Attention Properties wit...

引用

7th International Conference on Communication, Device and Networking, ICCDN 2024

作者： George, Geomol Anusuya, S. Department of Electronics and Communication Engineering Saveetha School of Engineering SIMATS Tamil Nadu Chennai602105 India Department of Computer Science and Engineering Saveetha School of Engineering SIMATS Tamil Nadu Chennai602105 India

ISBN: (纸本)9789819764648

Recent developments in deep-sea exploration, environmental surveillance, and ocean research, accurate segmentation of underwater images is essential. This study pursues this goal by exploring underwater image segmentation from a deep learning perspective. It specifically looks at how well the Attention Residual UNet architecture, a more sophisticated version of the U-Net, works with the focal loss technique to achieve accuracy in this crucial task. Using attention mechanisms and residual connections, the Attention Residual UNet architecture, based on the U-Net framework, can capture fine details while maintaining contextual coherence. Model loss and accuracy measures are considered as this study carefully assesses the architecture’s performance. Notably, the model exhibits outstanding accuracy, obtaining 97.23% and 92.76% accuracy on the training and validation sets, respectively. The Jaccard coefficient further demonstrates the model’s efficiency, which measures the intersection between predicted and actual segments and has coefficients for the model and validation sets of 74.31% and 66.51%, respectively. The Mean Intersection over Union (MIoU) statistic, which boasts a value 91.24%, validates the model’s superiority. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Underwater imaging

来源：评论

学校读者我要写书评

暂无评论

Detection of Aphasia Using Speech Characteristics: A Comparative Analysis of Learning Models 5th

Detection of Aphasia Using Speech Characteristics: A Compara...

引用

5th International Conference on Computing and Network Communications, CoCoNet 2023

作者： Surisetty, Hima Varshini Gottimukkala, Sarayu Varma Vekkot, Susmitha Gupta, Deepa Alotaibi, Yousef A. M. Department of Computer Science and Engineering Amrita School of Computing Bengaluru Amrita Vishwa Vidyapeetham Bengaluru India Department of Electronics and Communication Engineering Amrita School of Engineering Amrita Vishwa Vidyapeetham Bengaluru India Department of Computer Engineering College of Computer and Information Sciences King Saud University Riyadh11451 Saudi Arabia

ISBN: (纸本)9789819747108

Aphasia is one of the brain disorders that affects the part of the brain that is responsible for communication. This work deals with the detection of aphasia from speech features. The features extracted from the speech samples are MFCC, mel spectrogram, zero crossing rate, chroma, energy, spectral centroid, spectral roll-off, fundamental frequency and utterance duration. These different speech features were then ranked based on the SHapley Additive exPlanations (SHAPs), and the most important features were retained in an optimized feature set that was given to various machine learning models like support vector machine and decision trees and deep learning models like LSTM, LSTM with GRU, Bi-LSTM and Bi-LSTM with GRU. These models were then evaluated based on their train and test set accuracy, F1 score, recall, precision, plots of training loss and validation loss and confusion matrix. Based on the analysis of the performance metrics, Bi-LSTM with GRU was found to be the best model among all the models used. The model’s performance was evaluated using metrics like accuracy, F1 score, recall and precision when trained and tested with the optimal feature set which were 87.5%, 79.7%, 90% and 75%, respectively. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-based Hybrid Recommendation System for Safe Approach to Curated Cosmetics 3

Deep Learning-based Hybrid Recommendation System for Safe Ap...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Rohitha Chowdary, G. Tharun, J. Sivaiah, G. Raveena, S. Surendran, R. Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Insititute of Medical and Technical Science Chennai India

ISBN: (数字)9798331527549

ISBN: (纸本)9798331527549

In the rapidly evolving cosmetics market, it is imperative to prioritize customer safety while offering personalized recommendations. This study introduces a hybrid recommendation system for cosmetics, using deep learning to combine the advantages of collaborative filtering with content-based filtering. The system assesses user preferences, skin types, and ingredient sensitivities, recommending solutions that are both effective and safe. The system proposes an integration of user-based and item-based collaborative filtering methodologies with deep neural networks to effectively elucidate intricate links among individuals, items, and their characteristics. This hybrid technique facilitates the system's ability to propose goods that provide both aesthetic appeal and skin safety, therefore fostering a healthier and more confident lifestyle. The system has an impressive accuracy of 92.5% in recommending suitable cosmetic products for individual clients. This enhanced accuracy reduces the likelihood of negative reactions and elevates customer satisfaction via personalized suggestions. © 2025 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

LiVeDet: Lightweight Density-Guided Adaptive Transformer for Online On-Device Vessel Detection

引用

IEEE Robotics and Automation Letters 2025年第6期10卷 5513-5520页

作者： Zhang, Zijie Fu, Changhong Cao, Yongkang Li, Mengyuan Zuo, Haobo Tongji University School of Mechanical Engineering Shanghai201804 China University of Hong Kong Department of Computer Science 999077 Hong Kong

Vision-based online vessel detection boosts the automation of waterways monitoring, transportation management and navigation safety. However, a significant gap exists in on-device deployment between general high-performance PCs/servers and embedded AI processors. Existing state-of-the-art (SOTA) online vessel detectors lack sufficient accuracy and are prone to high latency on the edge AI camera, especially in scenarios with dense vessels and diverse distributions. To solve the above issues, a novel lightweight framework with density-guided adaptive Transformer (LiVeDet) is proposed for the edge AI camera to achieve online on-device vessel detection. Specifically, a new instance-aware representation extractor is designed to suppress cluttered background noise and capture instance-aware content information. Additionally, an innovative vessel distribution estimator is developed to direct superior feature representation learning by focusing on local regions with varying vessel density. Besides, a novel dynamic region embedding is presented to integrate hierarchical features represented by multi-scale vessels. A new benchmark comprising 100 high-definition, high-framerate video sequences from vessel-intensive scenarios is established to evaluate the efficacy of vessel detectors under challenging conditions prevalent in dynamic waterways. Extensive evaluations on this challenging benchmark demonstrate the robustness and efficiency of LiVeDet, achieving 32.9 FPS on the edge AI camera. Furthermore, real-world applications confirm the practicality of the proposed method. © 2016 IEEE.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

A Novel OPAL-RT Real-time Simulator-based Experimental Approach to Study Open-Switch Faults of Interfacing Inverters of Renewable Distributed Generation in Microgrids

引用

IEEE Transactions on Industry Applications 2025年第3期61卷 5218-5229页

作者： Liang, Xiaodong Talha, Muhammad Pannell, Jason Su, Hanguang Bowes, Austin University of Saskatchewan Department of Electrical and Computer Engineering SaskatoonS7N 5A9 Canada Northeastern University The School of Information Science and Engineering Shenyang110004 China

With increasing penetration of renewable energy sources in electric distribution systems, the microgrid is a fundamental building block for grid modernization. Renewable distributed generation (DG) units are connected within a microgrid through interfacing inverters equipped with advanced control schemes, and these inverters play an essential role in microgrid operations. However, DG interfacing inverters may fail due to various faults. In this paper, an experimental investigation of open-switch faults using a 2 kW three-phase two-level conventional voltage source inverter (VSI) is conducted through the Opal-RT real-time simulator test bench in the lab, where three grid-forming inverter control schemes (droop control, virtual synchronous generator (VSG) control, and VSG with a Fuzzy secondary controller) are implemented under healthy and 21 single- and multi-open-switch fault conditions. Five inverter loadings (30%, 45%, 60%, 75% and 90%) are also implemented in the testing. Three phase voltage and current signals were recorded at the inverter output/load terminal during experiments, which provided unique and novel datasets for studying inverter open-switch fault diagnosis in microgrids. © 1972-2012 IEEE.

关键词： Microgrids

来源：评论

学校读者我要写书评

暂无评论

Detection, Challenges for Wormhole Attacks and Blackhole Attacks in WSN to Find the Shortest Path of the Node Using the Traditional Algorithm

Detection, Challenges for Wormhole Attacks and Blackhole Att...

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Ramesh, R. Barath Thangaraj, S. John Justin Saveetha School Of Engineering Saveetha Institute of Medical and Technical Sciences Engineering Department of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798331509828

These networks are seriously threatened by wormhole and blackhole attacks, which manipulate the routing protocol for malicious paths to disrupt data communication. Classic route optimization algorithms between nodes include Dijkstra's and AODV;these might fall to those types of attacks. The present paper intends to give an overview of the detection, mitigation strategies, and challenges of prevention methods of Wormhole and Blackhole attacks over WSNs. This paper, therefore, is concerned with the impacts of these attacks on network dynamics and provides for a detection and mitigation scheme coupling conventional algorithms with trust-based metrics and secure routing enhancements. Beyond that, one can estimate the efficiency of the proposed methodology in detecting malicious nodes, preserving packet integrity, and making routing hence resilient by simulations in NS3. These results indicate improved network performance with lower latency, higher packet delivery rates, and extended lifetime, thus providing a practical solution for enhancing security in WSNs. © 2025 IEEE.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Glass Packaging for 6G Applications

引用

IEEE Microwave Magazine 2025年第6期26卷 46-64页

作者： Swaminathan, Madhavan Li, Xingchen Vijay Kumar, Lakshmi Narasimha Jia, Xiaofan Erdogan, Serhat Rehman, Mutee ur Huang, Kai-Qi Kim, Joon Woo Al-Juwhari, Mohammed Ahamed, Mahin Georgia Institute of Technology School of Electrical and Computer Engineering AtlantaGA30332 United States Penn State University Department of Electrical Engineering State CollegePA16801 United States

With the increasing demand for channel capacity, higher data rate, and wider bandwidth for wireless communication and sensing, the focus of millimeter-wave (mmWave) technology development is moving toward higher frequencies. For example, the 5G standard maps the frequency range 2 (FR2) bands into 24.25–52.6 GHz to satisfy the need for higher bandwidth, while the upcoming 6G communications is considering W-band (75–110 GHz), D-band (110–170 GHz), and even G-band (110–300 GHz) as the targeted operating frequencies. This evolution is driving mmWave systems toward the miniaturization of devices and components. This trend advocates the need for integrating compact passive and active components into the package, leading to complex heterogeneous integration platforms. © 2000-2012 IEEE.

关键词： Wireless communication Fabrication 6G mobile communication Wireless sensor networks Bandwidth Sensors Millimeter wave communication Substrates Standards Channel capacity

来源：评论

学校读者我要写书评

暂无评论

MetaCon: Revitalizing Internet Congestion Control with Meta-Reinforcement Learning

MetaCon: Revitalizing Internet Congestion Control with Meta-...

引用

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

作者： Bai, He Li, Hui Que, Jianming Zhang, Minglong Chong, Peter Han Joo Sudheera, Kalupahana Liyanage Kushan Pei, Xinyuan School of Electronic and Computer Engineering Peking University Shenzhen China School of Computer Science Fuyao University of Science and Technology Fuzhou China Department of Electrical and Computer Engineering Mississippi State University Starkville United States School of Engineering Computer and Mathematical Sciences Auckland University of Technology Auckland New Zealand Department of Electrical and Information Engineering Faculty of Engineering University of Ruhuna Sri Lanka

ISBN: (纸本)9798350368741

Effective congestion control algorithms (CCAs) are crucial for the smooth operation of Internet communication infrastructure. CCAs adjust transmission rates based on congestion signals, optimizing resource utilization and user experience. However, existing studies, both rule-based and learning-based CCAs, often struggle with generalization and underperform when deployed in real-world environments. When applied to unseen network conditions, hand-crafted schemes or pre-trained models may experience significant performance degradation. To address this challenge, we propose MetaCon, a novel adaptive Internet congestion control approach based on meta-reinforcement learning. MetaCon leverages knowledge learned from prior scenarios to quickly adapt to new environments. Experimental results show that MetaCon outperforms existing algorithms by exhibiting superior generalization and achieving better transmission performance across a wide variety of network conditions. © 2025 IEEE.

关键词： communication network congestion control meta-learning reinforcement learning transport protocol

来源：评论

学校读者我要写书评

暂无评论

A Tolerant and Energy Optimization Approach for Internet of Things to Enhance the QoS Using Adaptive Blended Marine Predators Algorithm

引用

computers, Materials & Continua 2025年第5期83卷 2449-2479页

作者： Vijaya Krishna Akula Tan Kuan Tak Pravin Ramdas Kshirsagar Shrikant Vijayrao Sonekar Gopichand Ginnela Department of Information Technology G.Narayanamma Institute of Technology and Science for WomenHyderabad500104India Engineering Cluster Singapore Institute of Technology10 Dover DriveSingapore138683Singapore Department of Electronics and Telecommunication Engineering J.D.College of Engineering&ManagementNagpur441501India Department of Computer Science and Engineering J.D.College of Engineering&ManagementNagpur441501India School of Computer Science and Engineering Vellore Institute of TechnologyVellore632014TamilnaduIndia

The rapid expansion of Internet of Things(IoT)networks has introduced challenges in network management,primarily in maintaining energy efficiency and robust connectivity across an increasing array of *** paper introduces the Adaptive Blended Marine Predators Algorithm(AB-MPA),a novel optimization technique designed to enhance Quality of Service(QoS)in IoT systems by dynamically optimizing network configurations for improved energy efficiency and *** results represent significant improvements in network performance metrics such as energy consumption,throughput,and operational stability,indicating that AB-MPA effectively addresses the pressing needs ofmodern IoT *** are initiated with 100 J of stored energy,and energy is consumed at 0.01 J per square meter in each node to emphasize energy-efficient *** algorithm also provides sufficient network lifetime extension to a resourceful 7000 cycles for up to 200 nodes with a maximum Packet Delivery Ratio(PDR)of 99% and a robust network throughput of up to 1800 kbps in more compact node *** study proposes a viable solution to a critical problem and opens avenues for further research into scalable network management for diverse applications.

关键词： Internet of things trust energy marine predators algorithm(MPA) differential evolution(DE) nodes throughput lifetime

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：