检索结果-内蒙古大学图书馆

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

作者： Tejesh, Vambara Supriya, M. Amrita School of Computing Amrita Vishwa Vidyapeetham Dept. of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798331509828

This research focuses on generating image captions using Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) models. As deep learning advances, the availability of large datasets and increased computing power make it more feasible to build models capable of creating captions for images. This paper uses CNN and RNN models in Python to achieve this. Image captioning combines image recognition and Natural Language Processing (NLP) to interpret image context and express it in English, drawing on core computer vision principles. This study reviews important concepts in image captioning, including the applications of Keras, NumPy, and Jupyter notebook for development. This paper also explores the use of the Flickr dataset and CNN for image classification. The BLEU score of the proposed models is found to be close to 60%. On further enhancement to the model, it could be achieved to get a better score. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Terrain Scene Generation Using A Lightweight Vector Quantized Generative Adversarial Network

引用

IEEE Transactions on Big Data 2025年第03期11卷 988-1000页

作者： Wang, Yan Zhou, Huiyu Dong, Xinghui Ocean University of China School of Computer Science and Technology Qingdao266100 China University of Leicester School of Computing and Mathematical Sciences LeicesterLE1 7RH United Kingdom

Natural terrain scene images play important roles in the geographical research and application. However, it is challenging to collect a large set of terrain scene images. Recently, great progress has been made in image generation. Although impressive results can be achieved, the efficiency of the state-of-the-art methods, e.g., the Vector Quantized Generative Adversarial Network (VQGAN), is still dissatisfying. The VQGAN confronts two issues, i.e., high space complexity and heavy computational demand. To efficiently fulfill the terrain scene generation task, we first collect a Natural Terrain Scene Data Set (NTSD), which contains 36,672 images divided into 38 classes. Then we propose a Lightweight VQGAN (Lit-VQGAN), which uses the fewer parameters and has the lower computational complexity, compared with the VQGAN. A lightweight super-resolution network is further adopted, to speedily derive a high-resolution image from the image that the Lit-VQGAN generates. The Lit-VQGAN can be trained and tested on the NTSD. To our knowledge, either the NTSD or the Lit-VQGAN has not been exploited before11The data set and code are available at: https://***/projects/Lit-VQGAN.. Experimental results show that the Lit-VQGAN is more efficient and effective than the VQGAN for the image generation task. These promising results should be due to the lightweight yet effective networks that we design. © 2015 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Optimal Frame Extraction for Event Detection in Surveillance Videos 16

Optimal Frame Extraction for Event Detection in Surveillance...

引用

16th International Conference on ENTERprise Information Systems, CENTERIS 2024 - 12th International Conference on Project MANagement, ProjMAN 2024 - 14th International Conference on Health and Social Care Information Systems and Technologies, HCist 2024

作者： Ranganath, Venkataraman Padmavathi, S. Aarthi, R. Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Coimbatore641112 India

This paper addresses the efficient identification of candidate keyframes in long and untrimmed surveillance videos. Existing fixed-length segmentation methods for violence detection suffer from computational inefficiency and fragmented short-Term event repre-sentation. To overcome these limitations, we propose an Optimal Keyframe Extraction framework utilizing shot boundary detection to segment videos based on significant visual changes. Candidate Keyframe segments are extracted from the shots, focusing on potential anomalous segments. Keyframes are selected based on the highest motion changes, accurately representing short term dynamic events. This dynamic approach aims to minimize the processing time of long and untrimmed surveillance videos by reducing the number of segments required for analysis of the event. Results show that the complexity of analyzing the event ef-fectively can be done by extracting an optimal set of keyframes within 2-3% of total number frames for each video. This research improves violence detection by efficiently analyzing large video datasets and accurately identifying short-Term dynamic events, thereby enhancing public safety and security applications. © 2025 The Author(s).

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

LayerCFL:an efcient federated learning with layer-wised clustering

引用

Cybersecurity 2025年第1期8卷 72-85页

作者： Jie Yuan Rui Qian Tingting Yuan Mingliang Sun Jirui Li Xiaoyong Li School of Cyberspace Security Beijing University of Posts and TelecommunicationsBeijingChina Key Laboratory of Trustworthy Distributed Computing and Service(BUPT) Ministry of EducationBeijingChina Institute of Computer Science Faculty of Mathematics and Computer ScienceUniversity of GoettingenGöettingenGermany School of Information Technology Henan University of Chinese MedicineZhengzhouHenanChina

Federated Learning(FL)sufers from the Non-IID problem in practice,which poses a challenge for efcient and accurate model *** address this challenge,prior research has introduced clustered FL(CFL),which involves clustering clients and training them *** its potential benefts,CFL can be computationally and communicationally expensive when the data distribution is unknown *** is because CFL involves the entire neural networks of involved clients in computing the clusters during training,which can become increasingly timeconsuming with large-sized *** tackle this issue,this paper proposes an efcient CFL approach called LayerCFL that employs a Layer-wised clustering *** LayerCFL,clients are clustered based on a limited number of layers of neural networks that are pre-selected using statistical and experimental *** experimental results demonstrate the efectiveness of LayerCFL in mitigating the impact of Non-IID data,improving the accuracy of clustering,and enhancing computational efciency.

关键词： Federated learning Clustered federated learning Non-IID Layer-wised clustering

来源：评论

学校读者我要写书评

暂无评论

DT-UPD: User Privacy Data Protection Through Distribution Transformation in Unlearning Cloud Service 24th

DT-UPD: User Privacy Data Protection Through Distribution Tr...

引用

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

作者： Sun, Shouyue Wu, Feng Zhang, Yingzhi Cui, Lei Gao, Longxiang Yu, Shui Jinan China Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan China School of Computer Science University of Technology Sydney Ultimo Australia

ISBN: (纸本)9789819615476

Providing machine unlearning services to users in the cloud, known as Machine Unlearning as a Service (MUaaS), has become a prominent privacy protection strategy. However, existing methods primarily focus on the effectiveness of the unlearning algorithm itself, while neglecting the privacy of the data users upload to the cloud for unlearning. To address this problem, we propose a distribution transformation method that maps users’ private data to a distribution (DT-UPD) that is functionally parallel and orthogonal to the original distribution. We then sample from this transformed distribution and use the sampled data instead of the original data to obtain the unlearning service. In detail, DT-UPD first employs the information bottleneck theory to extract the most relevant features for the unlearning service and then maps these features to a normal distribution. Low-dimensional features are then randomly sampled from this normal distribution and expanded into a high-dimensional space using adversarial reconstruction. This sampling and adversarial reconstruction process removes most of the information from the original private data (including unlearning-related and irrelevant information), ensuring that the final reconstructed data used for the unlearning service has a privacy protection effect. Additionally, we introduce Elastic Weight Consolidation (EWC) loss, which effectively avoids ‘catastrophic unlearning’ during the unlearning process. Extensive experimental results show that DT-UPD can achieve a forgetting accuracy (forget ACC) of 18.22% in the forgetting set with no more than a 6% accuracy loss in the test set. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Webly Supervised Fine-Grained Classification by Integrally Tackling Noises and Subtle Differences

引用

IEEE Transactions on Image Processing 2025年 34卷 2641-2653页

作者： Chen, Junjie Yan, Jiebin Fang, Yuming Niu, Li Jiangxi University of Finance and Economics School of Computing and Artificial Intelligence Jiangxi Nanchang330032 China Shanghai Jiao Tong University Department of Computer Science and Engineering Shanghai China

Webly-supervised fine-grained visual classification (WSL-FGVC) aims to learn similar sub-classes from cheap web images, which suffers from two major issues: label noises in web images and subtle differences among fine-grained classes. However, existing methods for WSL-FGVC only focus on suppressing noise at image-level, but neglect to mine cues at pixel-level to distinguish the subtle differences among fine-grained classes. In this paper, we propose a bag-level top-down attention framework, which could tackle label noises and mine subtle cues simultaneously and integrally. Specifically, our method first extracts high-level semantic information from a bag of images belonging to the same class, and then uses the bag-level information to mine discriminative regions in various scales of each image. Besides, we propose to derive attention weights from attention maps to weight the bag-level fusion for a robust supervision. We also propose an attention loss on self-bag attention and cross-bag attention to facilitate the learning of valid attention. Extensive experiments on four WSL-FGVC datasets, i.e., Web-Aircraft, Web-Bird, Web-Car, and WebiNat-5089, demonstrate the effectiveness of our method against the state-of-the-art methods. © 1992-2012 IEEE.

关键词： Labeled data

来源：评论

学校读者我要写书评

暂无评论

FarExStance: Explainable Stance Detection for Farsi 31

FarExStance: Explainable Stance Detection for Farsi

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Zarharan, Majid Hashemi, Maryam Behroozrazegh, Malika Eetemadi, Sauleh Pilehvar, Mohammad Taher Foster, Jennifer School of Computing Dublin City University Ireland Iran University of Science and Technology Iran Dadmatech Tehran Iran School of Computer Science University of Birmingham United Kingdom School of Computer Science and Informatics Cardiff University United Kingdom

ISBN: (纸本)9798891761964

We introduce FarExStance, a new dataset for explainable stance detection in Farsi. Each instance in this dataset contains a claim, the stance of an article or social media post towards that claim, and an extractive explanation which provides evidence for the stance label. We compare the performance of a fine-tuned multilingual RoBERTa model to several large language models in zero-shot, few-shot, and parameter-efficient fine-tuned settings on our new dataset. On stance detection, the most accurate models are the fine-tuned RoBERTa model, the LLM Aya-23-8B which has been fine-tuned using parameter-efficient fine-tuning, and few-shot Claude-3.5-Sonnet. Regarding the quality of the explanations, our automatic evaluation metrics indicate that few-shot GPT-4o generates the most coherent explanations, while our human evaluation reveals that the best Overall Explanation Score (OES) belongs to few-shot Claude-3.5-Sonnet. The fine-tuned Aya-32-8B model produced explanations most closely aligned with the reference explanations. © 2025 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Adaptive Attribute-Based Honey Encryption: A Novel Solution for Cloud Data Security

引用

computers, Materials & Continua 2025年第2期82卷 2637-2664页

作者： Reshma Siyal Muhammad Asim Long Jun Mohammed Elaffendi Sundas Iftikhar Rana Alnashwan Samia Allaoua Chelloug School of Computer Science and Engineering Central South UniversityChangsha410083China EIAS LAB College of Computer and Information Sciencesand Center of Excellence in Quantum and Intelligent ComputingPrince Sultan UniversityRiyadh11586Saudi Arabia Gianforte School of Computing Montana State UniversityBozemanMT 59717USA Department of Information Technology College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityRiyadh11671Saudi Arabia

A basic procedure for transforming readable data into encoded forms is encryption, which ensures security when the right decryption keys are used. Hadoop is susceptible to possible cyber-attacks because it lacks built-in security measures, even though it can effectively handle and store enormous datasets using the Hadoop Distributed File System (HDFS). The increasing number of data breaches emphasizes how urgently creative encryption techniques are needed in cloud-based big data settings. This paper presents Adaptive Attribute-Based Honey Encryption (AABHE), a state-of-the-art technique that combines honey encryption with Ciphertext-Policy Attribute-Based Encryption (CP-ABE) to provide improved data security. Even if intercepted, AABHE makes sure that sensitive data cannot be accessed by unauthorized parties. With a focus on protecting huge files in HDFS, the suggested approach achieves 98% security robustness and 95% encryption efficiency, outperforming other encryption methods including Ciphertext-Policy Attribute-Based Encryption (CP-ABE), Key-Policy Attribute-Based Encryption (KB-ABE), and Advanced Encryption Standard combined with Attribute-Based Encryption (AES+ABE). By fixing Hadoop’s security flaws, AABHE fortifies its protections against data breaches and enhances Hadoop’s dependability as a platform for processing and storing massive amounts of data.

关键词： Cybersecurity data security cloud storage hadoop encryption and decryption privacy protection attribute-based honey encryption

来源：评论

学校读者我要写书评

暂无评论

Language Models over Large-Scale Knowledge Base: on Capacity, Flexibility and Reasoning for New Facts 31

Language Models over Large-Scale Knowledge Base: on Capacity...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： He, Qiyuan Wang, Yizhong Yu, Jianfei Wang, Wenya College of Computing and Data Science Nanyang Technological University Singapore Paul G. Allen School of Computer Science & Engineering University of Washington United States School of Computer Science and Engineering Nanjing University of Science and Technology China

ISBN: (纸本)9798891761964

Advancements in language models (LMs) have sparked interest in exploring their potential as knowledge bases (KBs) due to their high capability for storing huge amounts of factual knowledge and semantic understanding. However, existing studies face challenges in quantifying the extent of large-scale knowledge packed into LMs and lack systematic studies on LMs' structured reasoning capabilities over the infused knowledge. Addressing these gaps, our research investigates whether LMs can effectively act as large-scale KBs after training over an expansive set of world knowledge triplets via addressing the following three crucial questions: (1) How do LMs of different sizes perform at storing world knowledge of different frequencies in a large-scale KB? (2) How flexible are these LMs in recalling the stored knowledge when prompted with natural language queries? (3) After training on the abundant world knowledge, can LMs additionally gain the ability to reason over such information to infer new facts? Our findings indicate that while medium-scaled LMs hold promise as world knowledge bases capable of storing and responding with flexibility, enhancements in their reasoning capabilities are necessary to fully realize their potential. © 2025 Association for Computational Linguistics.

关键词： Structured Query Language

来源：评论

学校读者我要写书评

暂无评论

Malicious Attack Detection Using Deep Learning in IoT Network 8th

Malicious Attack Detection Using Deep Learning in IoT Networ...

引用

8th International Conference on Microelectronics Electromagnetics and Telecommunications, ICMEET 2023

作者： Srivastava, Amisha Narayanan, V. Anantha Sumesh, A.K. Department of Computer Science and Engineering Amrita School of Computing Coimbatore India Amrita Vishwa Vidyapeetham Chennai India

ISBN: (纸本)9789819784219

The IOT (Internet of Things) engulfs a widespread ecosystem made up of networks, processing technologies, and smart items. IoT is a popular platform that allows many of the objects in our environment to interact with one another via sensors and, most significantly, the internet, thereby rendering our lives easier. Today, users and attackers are paying close attention to anomaly detection on the Internet of Things. The development we are noticing is the outcome of enhanced sensor monitoring technologies. Gathering data is crucial for creating an estimate for analyzing unhealthy behavior. IoT networks are more accessible to cyberattacks, and the deployment of attacks within the network and user privacy are the primary concerns. Intrusion detection systems might be a smart plan to safeguard IoT networks from various threats. The following strategies were employed in this study to find anomalies: Decision Tree, Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Logistical Classification. An assessment is made using the Accuracy, Precision, Recall, F1-Score, and Confusion Matrix. The UNSW-NB 15 dataset was used. The model’s predicted output is the identification of attacks or anomalies harmful to the devices and potentially damaging to user privacy and security. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Network intrusion

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：