检索结果-内蒙古大学图书馆

A Novelty Framework in Image-Captioning with Visual Attention-Based Refined Visual Features

computers, Materials & Continua 2025年第3期82卷 3943-3964页

作者： Alaa Thobhani Beiji Zou Xiaoyan Kui Amr Abdussalam Muhammad Asim Mohammed ELAffendi Sajid Shah School of Computer Science and Engineering Central South UniversityChangsha410083China Electronic Engineering and Information ScienceDepartment University of Science and Technology of ChinaHefei230026China EIAS Data Science Lab College of Computer and Information SciencesPrince Sultan UniversityRiyadh11586Saudi Arabia

Image captioning,the task of generating descriptive sentences for images,has advanced significantly with the integration of semantic ***,traditional models still rely on static visual features that do not evolve with the changing linguistic context,which can hinder the ability to form meaningful connections between the image and the generated *** limitation often leads to captions that are less accurate or *** this paper,we propose a novel approach to enhance image captioning by introducing dynamic interactions where visual features continuously adapt to the evolving linguistic *** model strengthens the alignment between visual and linguistic elements,resulting in more coherent and contextually appropriate ***,we introduce two innovative modules:the Visual Weighting Module(VWM)and the Enhanced Features Attention Module(EFAM).The VWM adjusts visual features using partial attention,enabling dynamic reweighting of the visual inputs,while the EFAM further refines these features to improve their relevance to the generated *** continuously adjusting visual features in response to the linguistic context,our model bridges the gap between static visual features and dynamic language *** demonstrate the effectiveness of our approach through experiments on the MS-COCO dataset,where our method outperforms state-of-the-art techniques in terms of caption quality and contextual *** results show that dynamic visual-linguistic alignment significantly enhances image captioning performance.

关键词： Image-captioning visual attention deep learning visual features

来源：评论

学校读者我要写书评

暂无评论

Reversible data hiding scheme using prediction neural network and adaptive modulation mapping

引用

Multimedia Tools and Applications 2025年第9期84卷 6665-6686页

作者： Chen, Si-Sheng Chang, Chin-Chen Horng, Ji-Hwei School of Big Data and Artificial Intelligence Fujian Polytechnic Normal University Fujian Fuzhou35030 China Department of Information Engineering and Computer Science Feng Chia University Taichung40724 Taiwan Department of Electrical Engineering National Quemoy University Kinmen89250 Taiwan

Prediction error expansion (PEE) is an attractive approach for reversible data hiding (RDH). The key issue for PEE-based RDH is to improve the prediction accuracy and design a better modulation mapping. This paper proposes a novel prediction error modulation (PEM) scheme, which comprises a prediction neural network and a modulation mapping rule generation algorithm. We use the multi-scale feature extraction (MSFE) module and the residual dense networks (RDN) to construct the prediction neural network. In the proposed RDH scheme, the cover image is divided into two parts, the reference pixel set and the cover pixel set, based on the chessboard pattern. The prediction network serves to predict the values of the cover pixel set using the reference pixel set. An optimization model is set up to adaptively determine the optimal modulation mapping for data hiding based on the specific prediction-error histogram and payload constraint. Experimental results show the superiority of the proposed prediction neural network and the optimized modulation mapping compared with related works. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Deep Networks as Denoising Algorithms: Sample-Efficient Learning of Diffusion Models in High-Dimensional Graphical Models

引用

IEEE Transactions on Information Theory 2025年第4期71卷 2930-2954页

作者： Mei, Song Wu, Yuchen University of California at Berkeley Department of Statistics Department of Electrical Engineering and Computer Sciences BerkeleyCA94720 United States University of Pennsylvania Wharton School Department of Statistics and Data Science PhiladelphiaPA19104 United States

We investigate the efficiency of deep neural networks for approximating scoring functions in diffusion-based generative modeling. While existing approximation theories leverage the smoothness of score functions, they suffer from the curse of dimensionality for intrinsically high-dimensional data. This limitation is pronounced in graphical models such as Markov random fields, where the approximation efficiency of score functions remains unestablished. To address this, we note score functions can often be well-approximated in graphical models through variational inference denoising algorithms. Furthermore, these algorithms can be efficiently represented by neural networks. We demonstrate this through examples, including Ising models, conditional Ising models, restricted Boltzmann machines, and sparse encoding models. Combined with off-the-shelf discretization error bounds for diffusion-based sampling, we provide an efficient sample complexity bound for diffusion-based generative modeling when the score function is learned by deep neural networks. © 1963-2012 IEEE.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Combining data augmentation and model fine-tuning for learning from limited data

引用

International Journal of Machine Learning and Cybernetics 2025年 1-18页

作者： Shi, Hongbo Zhang, Ying Wan, Bowen School of Information Shanxi University of Finance and Economics Taiyuan030031 China School of Data Science Jinzhong College of Information Jinzhong030800 China School of Computer Science and Technology Harbin Engineering University Harbin150000 China

Obtaining sufficient data is often challenging, costly, or even infeasible in real-world applications. To address this issue, researchers have developed methods for learning from limited data, which involves discovering the underlying pattern using a small amount of available data. data augmentation and model fine-tuning are two methods commonly used for learning with limited data. However, both methods have limitations: model fine-tuning methods often face difficulties in acquiring relevant data for pre-training in certain fields, such as drug discovery, whereas data augmentation methods have the potential risk of causing bias. To address this challenge, we propose a general learning framework for limited data using a combination of data augmentation and model fine-tuning (DAMFT). This framework comprises data augmentation and model fine-tuning modules. The data augmentation module is responsible for generating relevant data that are utilized to pre-train the target model, and the model fine-tuning module aims to correct the potential bias of the pre-trained model caused by data augmentation. DAMFT not only solves the difficulty in obtaining relevant data needed for model fine-tuning but also alleviates the bias caused by data augmentation. Furthermore, under the DAMFT framework, we provide a supervised learning algorithm, DAMFT_GH, which adopts a generative adversarial network and head fine-tuning to generate the new instances and tune the pre-trained model, respectively. The experimental results demonstrate that the proposed learning algorithm can effectively improve the performance of the classification model in the case of limited data. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

MLPFormer: MLP-integrated transformer for colorectal histopathology whole slide image segmentation

引用

Neural Computing and Applications 2025年第6期37卷 4651-4661页

作者： Wang, Yuxuan Li, Dan Li, Xuechen Guo, Yan Zuo, Yanfei Shen, Linlin Department of Computer Science Wenzhou-Kean University Wenzhou China School of Electronics and Information Engineering Wuyi University Jiangmen China Department of Histo Pathology Shanghai Histo Pathology Diagnostic Center Shanghai China College of Computer Sicence and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China

Colorectal intraepithelial neoplasia is a precancerous lesion of colorectal cancer, which is mainly diagnosed using pathological images. According to the characteristics of lesions, precancerous lesions can be classified into four different grades, i.e., background, normal, low and high level. However, due to the continuity of lesion development, tissue in different stages has high similarity. Recently, visual transformers have achieved impressive results in different visual tasks, due to their capacity of capturing long-range dependencies. However, due to computational cost, transformer cannot well extract detailed feature, which is important for lesion grading. To accurately segment pathological tissues with high similarity, in this work, we embed the multi-head MLP mixer module in the transformer network to extract cell and edge information. Furthermore, we propose a hierarchical MLP decoder to facilitate multi-scale feature fusion. The proposed transformer, namely MLPFormer, achieves remarkable results against competitive baselines on the Histo-CRC Biopsy dataset. The experimental results demonstrate that MLPFormer significantly outperforms the competitive baselines, i.e., a 3% dice improvement is achieved over the SegFormer series. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Artificial intelligence algorithms for object detection and recognition in video and images

引用

Multimedia Tools and Applications 2025年 1-18页

作者： Dakshinamoorthy, Prabakar Rajaram, Gnanajeyaraman garg, Shruti Murugan, Prabhu Manimaran, A. Sundar, Ramesh Department of Data Science and Business System School of Computing SRM Institute of Science and Technology SRM Nagar Kattankulathur Chennai India Department of Computer Science Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamilnadu Chennai India Birla Institute of Technology Mesra Ranchi India Department of ECE Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai602105 India Department of Computer Science Engineering Saveetha School Of EngineeringSaveetha Institute of Medical and Technical Sciences Chennai6021055 India Department of Netwoking and Communication School of Computing SRM Institute of Science and Technology SRM Nagar Kattankulathur Chennai India

The usage of machine learning and deep learning algorithms have necessitated Artificial Intelligence'. AI is aimed at automating things by limiting human interference. It is widely used in IT, healthcare, finance, and agriculture. It is achieved through several deep learning algorithms that reflect the human brain's intelligence. These AI algorithms can be manipulated according to changing needs and improved efficiency. This paper tries to utilize the developments made in AI technology to classify the images and recognize the objects present in them. One widely used AI algorithm is CNN (Convolutional Neural Networks). The CNN is a deep learning-based algorithm that consists of various layers that extract and filters the parameters present in the images. Some additional layers of ResNet50 and the CNN algorithm are used to extract the parameters to improve image recognition accuracy. The image dataset taken for training and testing the proposed model is imageNet. The images are initially processed before sending them to the proposed model. The proposed model is trained, validated, and tested through the images obtained after the initial processing. The same process is repeated several times until getting the maximum accuracy. The accuracy of the proposed model in terms of image recognition is recorded. The obtained results are compared with other image classification algorithms like VGG16 and VGG19. It is concluded that the proposed model outperforms other traditional methods in terms of accuracy. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Solving Overlapping Coalition Structure Generation in Task-Based Settings

引用

Journal of Artificial Intelligence Research 2025年 82卷 2125-2166页

作者： Zhang, Guofu Su, Zhaopin Song, Xiaoxiao Gao, Zixuan Li, Miqing Yao, Xin School of Computer Science and Information Engineering Hefei University of Technology Anhui Hefei China Intelligent Interconnected Systems Laboratory of Anhui Province Anhui Hefei China Anhui Province Key Laboratory of Industry Safety and Emergency Technology Anhui Hefei China CERCIA School of Computer Science University of Birmingham Birmingham United Kingdom School of Data Science Lingnan University Hong Kong

The overlapping coalition structure generation problem (OCSGP) is a challenging computational problem in multi-agent systems. It focuses on selecting possibly overlapping coalitions from a set of agents to maximize the social welfare of all coalitions while containing all agents. However, in practical applications, coalitions may be formed to selectively respond to tasks from a pool of potential tasks assigned to agents. Consequently, this study considers OCSGP in a task-based setting, where each agent has finite resources and can only respond to tasks of interest, and each coalition can only take on mutually disjoint subsets of tasks. Specifically, we first present a model of the task-based OCSGP and investigate its computational complexity. Our theoretical results demonstrate that this specific OCSGP remains intractable even under restrictive assumptions. Subsequently, we develop a generic evolutionary algorithm framework (EAF) to find an approximately optimal overlapping coalition structure (OCS) in time quartic polynomial in the size of the instance. Particularly, we devise a specific solution-repair based heuristic of cubic time complexity to generate a feasible OCS. Finally, we compare the proposed EAF with a task-oriented heuristic and a hybrid algorithm for OCSGP, and examine its applicability in the pursuit-evasion problem. The experimental results reveal that the proposed EAF exhibits superior performance in finding feasible OCSs and demonstrates flexible adaptability to problem size and resource status. ©2025 The Authors.

关键词： Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

VaeDiff-DocRE: End-to-end data Augmentation Framework for Document-level Relation Extraction 31

VaeDiff-DocRE: End-to-end Data Augmentation Framework for Do...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Tran, Khai Phan Hua, Wen Li, Xue School of Electrical Engineering and Computer Science The University of Queensland Australia Department of Data Science and Artificial Intelligence The Hong Kong Polytechnic University Hong Kong

ISBN: (纸本)9798891761964

Document-level Relation Extraction (DocRE) aims to identify relationships between entity pairs within a document. However, most existing methods assume a uniform label distribution, resulting in suboptimal performance on real-world, imbalanced datasets. To tackle this challenge, we propose a novel data augmentation approach using generative models to enhance data from the embedding space. Our method leverages the Variational Autoencoder (VAE) architecture to capture all relation-wise distributions formed by entity pair representations and augment data for underrepresented relations. To better capture the multi-label nature of DocRE, we parameterize the VAE's latent space with a Diffusion Model. Additionally, we introduce a hierarchical training framework to integrate the proposed VAE-based augmentation module into DocRE systems. Experiments on two benchmark datasets demonstrate that our method outperforms state-of-the-art models, effectively addressing the long-tail distribution problem in DocRE. Our code is released at: https://***/khaitran22/VaeDiff-DocRE. © 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

Robust primary quantization step estimation on resized and double JPEG compressed images

引用

Multimedia Tools and Applications 2025年第12期84卷 11097-11118页

作者： Zhang, Lei Chen, XuGuang Niu, YaKun Zuo, XianYu Wang, Huaqing School of Computer and Information Engineering Henan Kaifeng475004 China Henan Key Laboratory of Big Data Analysis and Processing Kaifeng Henan Henan Kaifeng475004 China National Internet Emergency Center Henan Zhengzhou450000 China

As one of the most important forensic tasks, reconstruction of the original information in tampered images is a key step for tampering detection and localization. Currently, a number of methods have been designed to estimate the primary quantization steps of double compressed JPEG images. However, the estimation in the presence of resizing operation remains a challenge. In this paper, we propose a robust primary quantization steps estimation method on resized and double JPEG compressed images. Specifically, the distribution of Discrete Cosine Transform (DCT) coefficients is firstly analyzed on the inverse resized image. Then, a maximum likelihood function together with a filtering strategy is designed to obtain the primary quantization step on Alternating Current (AC) bands. In addition, we find the prominent peak in the Discrete Fourier Transform (DFT) spectrum of the distribution of Direct Current (DC) coefficients is nonlinearly related to the step. Based on this observation, a mapping function derived from the geometric fitting is proposed to estimate the step on DC band. Experimental results demonstrate the proposed method provides superior estimation performance. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

Automated AI-Powered Fruit Identification Using Convolutional Neural Network

Automated AI-Powered Fruit Identification Using Convolutiona...

引用

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

作者： Sai Tejasree, K. Surendran, R. Rajakumar, B. Gomathi, R.M. Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Chennai India J.N.N Institute of Engineering Department of Artificial Intelligence and Data Science Chennai India School of Computing Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (数字)9798331509828

ISBN: (纸本)9798331509828

Clever system that can look at pictures of fruits and figure out what kind of fruit each picture shows. AI algorithms like deep learning, which is like giving the Machine learning model a crash course in fruit recognition. This method teaches the ML Model we clearly explained the Model using application's agent using PEAS and the application's task environment using the 6 dimensions by showing it tons of fruit images, so over time, it gets really good at spotting the differences and similarities between, say, a banana and a grape. We also used another technique called pattern recognition, which helps the computer pay attention to specific details like the fruit's color, shape, size and texture. Overcoming multiple obstacles in order to automatically identify the type of fruit from the picture. The variety of images is influencing the color, texture, and shape of many different types of fruits. When it came to fruit picture detection, Convolutional Neural Network (CNN) Algorithm outperformed standard support-vector-machine-based approaches using handcrafted features in terms of accuracy also, it is a lot faster to implement for new fruits. By integrating deep learning and pattern recognition techniques such as Convolutional Neural Network Algorithm we have got the accuracy of 84%, our system efficiently identified different fruit types from images, demonstrating the power and effectiveness of our methods. The goal of our project is to create a tool that can quickly and correctly identify many types of fruits in photos, which could be useful for things like sorting fruits in a grocery store or helping people learn about different fruits by using Convolutional Neural Network Algorithm. This is not just about teaching a computer to recognize fruits;it is about making technology that can understand and interact with the world in a way that is helpful to us. © 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

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：