检索结果-内蒙古大学图书馆

SAM: cross-modal semantic alignments module for image-text retrieval

MULTIMEDIA TOOLS AND applications 2024年第4期83卷 12363-12377页

作者： Park, Pilseo Jang, Soojin Cho, Yunsung Kim, Youngbin Chung Ang Univ Dept Artificial Intelligence Seoul 06974 South Korea Chung Ang Univ Dept Image Sci & Arts Seoul 06974 South Korea

Cross-modal image-text retrieval has gained increasing attention due to its ability to combine computer vision with natural language processing. Previously, image and text features were extracted and concatenated to feed the transformer-based retrieval network. However, these approaches implicitly aligned the image and text modalities since the self-attention mechanism computes attention coefficients for all input features. In this paper, we propose cross-modal Semantic Alignments Module (SAM) to establish an explicit alignment through enhancing an inter-modal relationship. Firstly, visual and textual representations were extracted from an image and text pair. Secondly, we constructed a bipartite graph by representing the image regions and words in the sentence as nodes, and the relationship between them as edges. Then our proposed SAM allows the model to compute attention coefficients based on the edges in the graph. This process helps explicitly align the two modalities. Finally, a binary classifier was used to determine whether the given image-text pair is aligned. We reported extensive experiments on MS-COCO and Flickr30K test sets, showing that SAM could capture the joint representation between the two modalities and could be applied to the existing retrieval networks.

关键词： image-text retrieval Cross-modal Vision-language Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

An image style transfer model based on convolutional neural network (CNN)

An image style transfer model based on convolutional neural ...

引用

2023 International Conference on Computer Graphics, artificial Intelligence, and Data processing, ICCAID 2023

作者： Li, Shan Li, Min Li, Xiaoying Xiamen Institute of Technology Fujian Province Xiamen China Chengyi College Jimei University Fujian Province Xiamen China College of Marine Engineering Jimei University Fujian Province Xiamen China

ISBN: (纸本)9781510677685

With the rise of deep learning, the cross collision between artificial intelligence and art, represented by image style transfer, has attracted high attention in the fields of graphic and image technology and art. Based on Convolutional neural networks(CNN), this article discusses an image style transfer model. Firstly, define the content loss function and style loss function,weigh them to calculate the total loss function, incorporate texture features extracted by the Canny operator into the content image;secondly, use the cost function to calculate the values representing content and style for comparison between the initial style and the target style, and then generate a new target image through deformation and combination;finally, train the VGG model to generate the output of the content and style layers of the image, and calculated the corresponding layer parameters applied to the original image for retraining to achieve the minimum loss value. The verification results indicate that adding the Canny operator makes the edges of the style transfer graph more delicate and the contours clearer. This model has a very wide range of applications, such as video processing, photo beautification, social communication, etc. It is currently one of the popular technologies in artificial intelligence. © 2024 SPIE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

artificial intelligence (AI) in textile industry operational modernization

引用

RESEARCH JOURNAL OF TEXTILE AND APPAREL 2024年第1期28卷 67-83页

作者： Sikka, Monica Puri Sarkar, Alok Garg, Samridhi Dr BR Ambedkar Natl Inst Technol Dept Text Technol Jalandhar Punjab India

Purpose With the help of basic physics, the application of computer algorithms in the form of recent advances such as machine learning and neural networking in textile Industry has been discussed in this review. Scientists have linked the underlying structural or chemical science of textile materials and discovered several strategies for completing some of the most time-consuming tasks with ease and precision. Since the 1980s, computer algorithms and machine learning have been used to aid the majority of the textile testing process. With the rise in demand for automation, deep learning, and neural networks, these two now handle the majority of testing and quality control operations in the form of image processing. Design/methodology/approach The state-of-the-art of artificial intelligence (AI) applications in the textile sector is reviewed in this paper. Based on several research problems and AI-based methods, the current literature is evaluated. The research issues are categorized into three categories based on the operation processes of the textile industry, including yarn manufacturing, fabric manufacture and coloration. Findings AI-assisted automation has improved not only machine efficiency but also overall industry operations. AI's fundamental concepts have been examined for real-world challenges. Several scientists conducted the majority of the case studies, and they confirmed that image analysis, backpropagation and neural networking may be specifically used as testing techniques in textile material testing. AI can be used to automate processes in various circumstances. Originality/value This research conducts a thorough analysis of artificial neural network applications in the textile sector.

关键词： artificial intelligence neural networking Machine learning Deep learning AI in dyeing processing

来源：评论

学校读者我要写书评

暂无评论

Optoelectronic Synapse Enabled by Defect Engineering of Tellurene for Neuromorphic Computing

IEEE ELECTRON DEVICE LETTERS

引用

IEEE ELECTRON DEVICE LETTERS 2025年第1期46卷 68-71页

作者： Guo, Junxiong Huang, Junyan Gu, Shuyi Lin, Lin Zhang, Yafei Wang, Xiang Liu, Yu Gong, Tianxun Lin, Yuan Yu, Bin Huang, Wen Zhang, Xiaosheng Univ Elect Sci & Technol China Sch Integrated Circuit Sci & Engn Chengdu 611731 Peoples R China Sch Elect Informat & Elect Engn Chengdu 610106 Peoples R China Nanjing Univ Posts & Telecommun Coll Integrated Circuit Sci & Engn Nanjing 210023 Peoples R China Univ Elect Sci & Technol China Sch Mat & Energy Chengdu 610054 Peoples R China Zhejiang Univ ZJU Hangzhou Global Sci & Technol Innovat Ctr Hangzhou 311215 Peoples R China

Emerging optoelectronic synapses hold immense potential for advancing neuromorphic computing systems. However, achieving precise control over selective responses in optoelectronic memory and clarifying tunable synaptic weights has remained challenging. This study reports an optoelectronic synapse utilizing oxygen plasma-assisted defect engineering in tellurene for artificial neural networks. Through DFT calculations and experimental analyses, we demonstrate that tellurene conductance can be modulated by controlling plasma-defined defect engineering, allowing a transition from short-term to long-term synaptic plasticity, largely determined by intrinsic large-lattice-relaxation effects. Our artificial synapses exhibit high linearity, a broad dynamic range, and tunable synaptic weights. Additionally, our optoelectronic synapses display selective sensitivity to multi-spectral light and achieve a pattern recognition accuracy of up to 96.7% across five typical datasets, surpassing even the ideal synapse. These tunable spectral responses, combined with high-performance neuromorphic applications using spike coding, establish a foundation for developments in brain-inspired machine learning, robotics, and real-time data processing.

关键词： Optoelectronic synapse defect engineering image recognition neural network Optoelectronic synapse defect engineering image recognition neural network

来源：评论

学校读者我要写书评

暂无评论

An Instrument Tone Recognition System Based on artificial Intelligence and Feature Recognition 2

An Instrument Tone Recognition System Based on Artificial In...

引用

2nd IEEE International Conference on image processing and Computer applications, ICIPCA 2024

作者： Hu, Zheng School of Music Zhaoqing University Guangdong Zhaoqing City526061 China

ISBN: (纸本)9798350360240

Instrument tone recognition systems have over time had the highest application value and significance in information retrieval. Notably, the traditional systems and methods often rely on convolutional neural networks (CNN) that serve as fundamental through reportedly, have a poor performance. To this effect, this work seeks to examine a resent artificial intelligence (AI) and a feature recognition system in instrument tone recognition. A proposed model in this case is integrated in an interactive system of humanoid robot. The findings of this study reveal that the proposed resent artificial intelligence (AI) and a feature recognition system in the design of an instrument tone recognition system outperforms the traditional model in terms of recognition accuracy and tonal loss rate. The findings of the research therefore providing methods and ideas that may be used in instrument tonal recognition. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Quantitative comparison of the computational complexity of optical, digital and hybrid neural network architectures for image classification tasks

引用

OPTICS EXPRESS 2023年第26期31卷 44474-44485页

作者： Chen, Mengxiang Schoenhardt, Steffen Gu, Min Goi, Elena Univ Shanghai Sci & Technol Inst Photon Chips Shanghai 200093 Peoples R China Univ Shanghai Sci & Technol Ctr Artificial Intelligence Nanophoton Sch Opt Elect & Comp Engn Shanghai 200093 Peoples R China

By implementing neuromorphic paradigms in processing visual information, machine learning became crucial in an ever-increasing number of applications of our everyday lives, ever more performing but also computationally demanding. While a pre-processing of the information passively in the optical domain, before optical-electronic conversion, can reduce the computational requirements for a machine learning task, a comprehensive analysis of computational requirements for hybrid optical-digital neural networks is thus far missing. In this work we critically compare and analyze the performance of different optical, digital and hybrid neural network architectures with respect to their classification accuracy and computational requirements for analog classification tasks of different complexity. We show that certain hybrid architectures exhibit a reduction of computational requirements of a factor >10 while maintaining their performance. This may inspire a new generation of co-designed optical-digital neural network architectures, aimed for applications that require low power consumption like remote sensing devices.

关键词： Machine learning neural networks Optical neural systems Optical systems Point spread function Spatial light modulators

来源：评论

学校读者我要写书评

暂无评论

image encoded time series classification of small datasets: an innovative architecture using deep learning ensembles

引用

INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS 2025年 1-16页

作者： Indrasiri, Pubudu L. Kashyap, Bipasha Pathirana, Pubudu N. Deakin Univ Sch Engn 75Pigdons Rd Waurn Ponds Vic 3216 Australia

Convolutional neural networks (CNNs) are often favored for their strong learning abilities in tackling automatic intelligent models. The classification of time series data streams spans across many applications of intelligent systems. However, the scarcity of effective Machine Learning architectures to handle limited time-series data adversely affects the realization of some crucial applications. In particular, healthcare-related applications are inherently concerned with limited time series datasets. Indeed, building effective artificial intelligence (AI) models for rare diseases using conventional techniques can pose a significant challenge. Utilizing recent advances in deep learning and signal processing techniques, this study introduces a new ensemble deep learning (DL) approach for time series categorization in the presence of limited datasets. Physiological data, such as ECG and voice, are used to demonstrate the functionality of the proposed DL architecture with data obtained from IoT and non-IoT devices. The proposed framework comprises a self-designed deep CNN-LSTM along with ResNet50 and MobileNet transfer learning approaches. The CNN-LSTM architecture includes an enhanced squeeze and excitation block that improves overall *** architecture processes time series data transformed into a 3-Channel image structure via improved recurrence plot (RP), Gramian angular field (GAF), and fuzzy recurrence plot (FRP) methods. The proposed model demonstrated superior classification accuracy on the ECG5000 and TESS datasets compared to other state-of-the-art techniques, validating its efficacy for binary and multiclass classification.

关键词： Limited datasets Healthcare time series Squeeze and excitation Ensemble learning

来源：评论

学校读者我要写书评

暂无评论

Human footprint biometrics for personal identification using artificial neural networks

引用

INTERNATIONAL JOURNAL OF BIOMETRICS 2023年第3-4期15卷 272-290页

作者： Nagwanshi, Kapil Kumar Gupta, Amit Kumar Goswami, Tilottama Pathak, Sunil Khan, Maleika Heenaye-Mamode Guru Ghasidas Vishwavidyalaya Cent Univ SoS E&T Bilaspur India Amity Univ Rajasthan Dept CSE ASET Jaipur RJ India Anurag Univ Dept Artificial Intelligence Hyderabad India Univ Mauritius Dept Software & Informat Syst Reduit Mauritius

The philosophy of this study focuses on human footprint identification applicable for high-security applications such as the safety of public places, crime scene investigation, impostor identification, biotech labs and blue-chip labs, and identification of infants in hospitals. The paper proposes one of the low-cost hardware to scan the biometric human footprints that utilise image pre-processing and enhancement capabilities for obtaining the features. The algorithm enhances the footprint matching performance by selecting the three sets of local invariant feature detectors - histogram of gradients, maximally stable external regions, and speed up robust features;local binary pattern as texture descriptor, corner point detector, and PCA. Furthermore, descriptive statistics are generated from all the above mentioned footprint features and concatenated to create the final feature vector. The proposed footprint biometric identification will correctly identify or classify the person by training the system with patterns of the interested subjects using an artificial neural network model specially designed for this task. The proposed method gives the classification accuracy at a very encouraging level of 99.55%.

关键词： artificial neural networks ANNs biometric classification footprint segmentation

来源：评论

学校读者我要写书评

暂无评论

An optimized heterogeneous multi-access edge computing framework based on transfer learning and artificial internet of things

引用

ALEXANDRIA ENGINEERING JOURNAL 2024年 109卷 176-190页

作者： Yu, Ping Zhao, Hongwei Geng, Xiaozhong Hu, Ming Yan, Hui Long, Duo Guo, Huangbin Zong, Baoshu Jilin Univ Coll Comp Sci & Technol Changchun 130015 Jilin Peoples R China Changchun Inst Technol Changchun 130012 Jilin Peoples R China Jilin Univ Architecture & Technol Changchun 130114 Jilin Peoples R China Suqian Univ Suqian 223800 Jiangsu Peoples R China

In most practical applications, the feature space of the training datasets and the target domain datasets are inconsistent, or the data distribution between them is inconsistent, which leads to the problem of data starvation and makes it difficult for terminal devices to obtain high accurate results. Aiming at the problems of limited terminal device resources, low accuracy of data processing results, and unsatisfactory processing speed, a Heterogeneous Multi-access Edge Computing (MEC) Framework based on Transfer Learning (TL) is proposed, abbreviated as HMECF-TL. This framework adopts a cloud-edge-end three-layer architecture. It uses model transfer to optimize the Convolutional neural networks (CNN) model at each layer to achieve the goal of improving data processing speed and accuracy. Furthermore, a multi-agent Deep Reinforcement Learning Algorithm having Attention Mechanism (DRLAAM) is designed to further increase the timeliness performance of computation-intensive applications. The performance of HMECSF-TL framework is verified by simulation experiments, which not only reduces the delay by more than 24.66 %, but also improves the accuracy by more than 8.34 %. The framework not only increase the computing capacity to solve the shortage of terminal device resources, but also improve the quality of data processing to solve the problem of data starvation.

关键词： Multi-access edge computing Task offloading Transfer learning artificial intelligence Attention mechanism Deep reinforcement learning image classification

来源：评论

学校读者我要写书评

暂无评论

Radar Signal processing and Its Impact on Deep Learning-Driven Human Activity Recognition

引用

SENSORS 2025年第3期25卷 724-724页

作者： Ayaz, Fahad Alhumaily, Basim Hussain, Sajjad Imran, Muhammad Ali Arshad, Kamran Assaleh, Khaled Zoha, Ahmed Univ Glasgow James Watt Sch Engn Glasgow City G12 8QQ England Ajman Univ Coll Engn & Informat Technol Dept Elect & Comp Engn POB 346 Ajman U Arab Emirates Ajman Univ Artificial Intelligence Res Ctr POB 346 Ajman 346 U Arab Emirates

Human activity recognition (HAR) using radar technology is becoming increasingly valuable for applications in areas such as smart security systems, healthcare monitoring, and interactive computing. This study investigates the integration of convolutional neural networks (CNNs) with conventional radar signal processing methods to improve the accuracy and efficiency of HAR. Three distinct, two-dimensional radar processing techniques, specifically range-fast Fourier transform (FFT)-based time-range maps, time-Doppler-based short-time Fourier transform (STFT) maps, and smoothed pseudo-Wigner-Ville distribution (SPWVD) maps, are evaluated in combination with four state-of-the-art CNN architectures: VGG-16, VGG-19, ResNet-50, and MobileNetV2. This study positions radar-generated maps as a form of visual data, bridging radar signal processing and image representation domains while ensuring privacy in sensitive applications. In total, twelve CNN and preprocessing configurations are analyzed, focusing on the trade-offs between preprocessing complexity and recognition accuracy, all of which are essential for real-time applications. Among these results, MobileNetV2, combined with STFT preprocessing, showed an ideal balance, achieving high computational efficiency and an accuracy rate of 96.30%, with a spectrogram generation time of 220 ms and an inference time of 2.57 ms per sample. The comprehensive evaluation underscores the importance of interpretable visual features for resource-constrained environments, expanding the applicability of radar-based HAR systems to domains such as augmented reality, autonomous systems, and edge computing.

关键词： human activity classification radar domain representations deep learning computational cost transfer learning

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：