检索结果-内蒙古大学图书馆

Exploring Data and Models in SAR Ship Image Captioning

IEEE ACCESS 2022年 10卷 91150-91159页

作者： Zhao, Kai Xiong, Wei Space Engn Univ Sci & Technol Complex Elect Syst Simulat Lab Beijing 101400 Peoples R China

In recent years, considerable progress has been made in ship detection in synthetic aperture radar (SAR) images;however, no research has been conducted on translating SAR ship images into flexible and accurate sentences. To explore image captions in SAR ship images, we conduct the following work: first, to better describe SAR ship images, we propose certain principles for SAR image annotation based on the characteristics of SAR images. Second, to make better use of SAR ship images, a large-scale SAR ship image captioning dataset is carefully constructed. Finally, we explore encoder-decoder models and the attention mechanism and apply these methods to the SAR ship image captioning task. We conduct detailed experiments on the proposed dataset and find that the encoder-decoder model and attention mechanism can obtain good results in the SAR ship image captioning task. The experiments also reveal that the generated sentences can accurately describe SAR ship images. This dataset has already been published on https://***/5132210/***.

关键词： Marine vehicles Synthetic aperture radar Radar polarimetry Remote sensing Seaports Feature extraction Decoding Encoding Recurrent neural networks SAR image image captioning encoder-decoder recurrent neural network long short-term memory network

来源：评论

学校读者我要写书评

暂无评论

A deep multivariate time series multistep forecasting network

引用

APPLIED INTELLIGENCE 2022年第8期52卷 8956-8974页

作者： Yin, Chenrui Dai, Qun Nanjing Univ Aeronaut & Astronaut Coll Comp Sci & Technol Nanjing 211106 Peoples R China

Due to that multivariate time series, multistep forecasting technology has a guiding role in many fields, such as electricity consumption, traffic flow detection, and stock price prediction, many approaches have been proposed, seeking to realize accurate prediction based on historical data. However, multivariate time series in real-world applications often contain complex and non-linear interdependencies between time steps and series, for which traditional approaches that just model dependencies in time dimension may fail to make forecasting accurately. In addition, the traditional cyclic multistep prediction strategy leads to error accumulation and consequently results in the reduction of prediction performance. To address these limitations, we propose a novel Deep Multivariate Time Series Multistep Forecasting Network based on the encoder-decoder model, abbreviated as DualMNet. DualMNet uses the temporal patterns module to capture long-term patterns between time steps, and, simultaneously, employs the spatial patterns module to discover the interdependencies between time series. Furthermore, the decoder utilizes the historical data of the target sequence to predict the long time-series sequences at the final forward operation, significantly ameliorating the issue of error accumulation. Finally, the conducted t-test results, based upon the extensive experimental results on the three benchmark multivariate time series datasets, they demonstrate that the multistep predictive performance of DualMNet is significantly superior to those of the comparison models, and the ablation study shows that integrating all the components of DualMNet together results in robust forecasting performance.

关键词： Multivariate time series Multistep prediction Deep learning encoder-decoder Attention mechanism

来源：评论

学校读者我要写书评

暂无评论

R-GRU: Regularized gated recurrent unit for handwritten mathematical expression recognition

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2022年第22期81卷 31405-31419页

作者： Pal, Aniket Singh, Krishna Pratap Indian Inst Informat Technol Dept Informat Technol Machine Learning & Optimizat Lab Allahabad Prayagraj India

Handwritten mathematical expression recognition(HMER) plays a wide variety of roles in different domains like online teaching, scientific research, etc. Due to its two-dimensional non-linear structure, it is a challenging problem. In this work, we proposed a novel architecture using regularization(dropout), attention & gated recurrent unit(R-GRU). R-GRU is used as the central decoding unit that takes the intermediate representation produced by the encoder as an input and generates corresponding LaTeX sequences. Simulation on CROHME 2014 and 2016 datasets achieve results comparable to the latest state-of-the-art.

关键词： Handwritten Mathematical Expression Recognition encoder-decoder Gated recurrent unit Dropout Regularization

来源：评论

学校读者我要写书评

暂无评论

MobileXNet: An Efficient Convolutional Neural Network for Monocular Depth Estimation

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2022年第11期23卷 20134-20147页

作者： Dong, Xingshuai Garratt, Matthew A. Anavatti, Sreenatha G. Abbass, Hussein A. Univ New South Wales Sch Engn & Informat Technol Canberra ACT 2612 Australia

Depth estimation from a single RGB image has attracted great interest in autonomous driving and robotics. State-of-the-art methods are usually designed on top of complex and extremely deep network architectures, which require more computational resources. Moreover, the inherent characteristic of the backbone used by the existing approaches results in severe spatial information loss in the produced feature maps, which impairs the accuracy of depth estimation on small sized images. In this study, we aimed to design a novel and efficient Convolutional Neural Network (CNN) to address these problems. Specifically, we stacked two shallow encoder-decoder style subnetworks successively in a unified network. Extensive experiments have been conducted on the NYU depth v2, KITTI, Make3D and Unreal data sets. Experimental results show that the proposed network achieves comparable accuracy to state-of-the-art methods that have extremely deep architectures but runs at a much faster speed on a single, less powerful GPU.

关键词： Estimation Convolution Convolutional neural networks Task analysis Decoding Computer architecture Semantics Monocular depth estimation depth prediction convolutional neural networks encoder-decoder autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

VAE and AAE Networks Segment Brain Tumors from MRI 30

VAE and AAE Networks Segment Brain Tumors from MRI

引用

30th National and 8th International Iranian Conference on Biomedical Engineering (ICBME)

作者： Mirani, Mehri Soltani-Gol, Mohammad Soltanian-Zadeh, Hamid Univ Tehran Sch Elect & Comp Engn CICPE Tehran Iran

ISBN: (纸本)9798350359732;9798350359749

Brain tumor segmentation is essential in medical imaging for accurate diagnosis and effective treatment planning. Brain tumors are formed during the uncontrolled growth of cells and are divided into two primary and secondary categories. The most common type of primary brain tumors is gliomas, which are examined in this research. In recent years, deep learning models have shown promising results in automating tumor segmentation from medical imaging data. This study compares the performance of Variational Autoencoder (VAE) and Adversarial Autoencoder (AAE) networks for brain tumor segmentation based on an encoder-decoder architecture. The encoder part extracts image features, while the decoder part reconstructs segmentation labels. These two networks are powerful generative models that capture the underlying distribution of the data. This capability makes them suitable for extracting meaningful tumor features. In the VAE network, a variational autoencoder branch is added to reconstruct the input images. In the adversarial network, the discriminator part is added to train the encoder-decode network and helps the decoder to generate outputs that closely match the tumor labels. The results indicate that both VAE and AAE achieve satisfactory segmentation accuracy. However, AAE achieves higher Dice scores compared to VAE, indicating that it is more effective at segmenting tumor regions.

关键词： Brain tumor segmentation deep learning encoder-decoder Variational Autoencoder (VAE) Adversarial Autoencoder (AAE)

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Model for Multilingual OCR 17th

A Hybrid Model for Multilingual OCR

引用

17th International Conference on Document Analysis and Recognition (ICDAR)

作者： Etter, David Carpenter, Cameron King, Nolan Johns Hopkins Univ Human Language Technol Ctr Excellence Baltimore MD 21218 USA SCALE Laurel MD USA

ISBN: (纸本)9783031416750;9783031416767

Large-scale document processing pipelines are required to recognize text in many different languages. The writing systems for these languages cover a diverse set of scripts, such as the standard Latin characters, the logograms of Chinese, and the cursive right-to-left of Arabic. Multilingual OCR continues to be a challenging task for document processing due to the large vocabulary sizes and diversity of scripts. This work introduces a multilingual model that recognizes over nine thousand unique characters and seamlessly switches between ten different scripts. Our transformer-based encoder-decoder approach combines a CTC objective on the encoder with a cross-entropy objective on the full autoregressive decoder. The hybrid approach allows the fast non-autoregressive encoder to be used in standalone mode or with the full autoregressive decoder. We evaluate our approach on a large multilingual dataset, where we achieve state-of-the-art character error rate results in all thirteen languages. We also extend the encoder with auxiliary heads to identify language, predict font, and detect vertical lines.

关键词： Multilingual OCR Transformer Hybrid encoder-decoder CTC Auxiliary heads Synthetic data

来源：评论

学校读者我要写书评

暂无评论

Multi-task Learning Based Skin Segmentation 16th

Multi-task Learning Based Skin Segmentation

引用

16th International Conference on Knowledge Science, Engineering and Management (KSEM)

作者： Tan, Taizhe Shan, Zhenghao Guangdong Univ Technol Sch Comp Sci & Technol Guangzhou 510006 Peoples R China Heyuan Bay Area Digital Econ Technol Innovat Ctr Heyuan 517001 Peoples R China

ISBN: (纸本)9783031402883;9783031402890

Skin segmentation is a critical task in computer vision that has diverse applications in several fields such as biometrics, medical imaging, and video surveillance. Despite its importance, the acquisition of high-quality data remains a significant challenge in skin segmentation research. In this paper, we propose a novel skin segmentation algorithm for single-person images by utilizing a dual-task neural network built on the multi-task learning framework. Specifically, the algorithm employs an encoder-decoder architecture consisting of a shared backbone, two dynamic encoders, and a decoder. The dynamic encoders use dynamic convolution to extract more spatial location information, while the decoder utilizes a query-based dual-task approach that allows each task to utilize the information generated by the other one efficiently. The experimental results indicate that the proposed skin segmentation algorithm outperforms or matches the current state-of-the-art techniques on the benchmark test set.

关键词： Skin segmentation query-based multi-task learning encoder-decoder deep learning

来源：评论

学校读者我要写书评

暂无评论

The Application of Generating API Call Sequence Code for Android Driven by Neural Network

The Application of Generating API Call Sequence Code for And...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Yang, Jingbo Wu, Wenjun Ren, Jian Beihang Univ Sch Comp Sci & Engn Beijing Peoples R China Beihang Univ Inst Artificial Intelligence Beijing Peoples R China

ISBN: (纸本)9781665488679

API, namely application programming interface, can help developers implement their functions conveniently. To implement a function like dialing in Android, developers sometimes need to call many APIs organised in a special pattern, called API call sequence. However, existing methods rarely focus on code generation for API call sequence. In this paper, we introduce neural network into the application field of generating API call sequence code for Android. The purpose is realising Android code automatically generation by inputting function description. To reach this goal, we first design an API call sequence code graph which is named ACSCG to well represent the Android function code structure and then we convert the ACSCG to API call sequence. Besides, we devise an AI model based on encoder-decoder neural network to study the corresponding relation feature of function description and API call sequence. When finishing training the model, one can give a function description to it and generate corresponding API call sequence. After all above has been done, an algorithm is implemented to successfully convert the API call sequence into target code. To verify the efficiency of our method, we collect high quality code from Github and Gitee to build a dataset including 1000 items associated with essential functions in Android such as taking photo, file management, android browser and so on. The experiment shows that our model has a better performance in generating API call sequence code than state-of-the-art technologies.

关键词： API call sequence neural network encoder-decoder AI code generation

来源：评论

学校读者我要写书评

暂无评论

Bridging the Language Gap: Enhancing English-to-Telugu Translation using NMT and Encoding Decoding Techniques 15

Bridging the Language Gap: Enhancing English-to-Telugu Trans...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Asmitha, M. Kavitha, C.R. Amrita Vishwa Vidyapeetham Amrita School of Computing Dept. of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350370249

Language translation, particularly in the context of natural language processing, involves converting text or speech from one language into another while preserving its meaning, context, and cultural nuances. This task is critical for enabling communication across different languages and is a significant area of research and development in artificial intelligence. Machine translation has a wide range of real-time applications that have significantly impacted various fields by bridging language barriers. Some of the real time application includes Google Translate, Microsoft Translator, Skype Translator. NMT has revolutionized language translation with models like Google's Transformer, OpenAI's GPT, Facebook's BART, and Google's T5. Development of a machine translation system to translate English sentences into Telugu. The system utilizes a neural network model based on an encoder-decoder architecture with attention mechanism. Preprocessing techniques are applied to the dataset, including lowercasing, removal of special characters, and tokenization. The sparse categorical cross-entropy loss function and Adam optimizer are used to train the model. The actual vs. projected output is used to evaluate performance. Pre-trained GloVe word embeddings are used in the implementation to improve the model's capacity to extract semantic information. © 2024 IEEE.

关键词： Attention mechanism encoder-decoder GloVe word embeddings Machine translation Neural network Pre-processing

来源：评论

学校读者我要写书评

暂无评论

Transformer-Based Multivariate Time Series Forecasting

Transformer-Based Multivariate Time Series Forecasting

引用

2024 IEEE International Students' Conference on Electrical, Electronics and Computer Science, SCEECS 2024

作者： Bharti, Mukesh Kumar Wadhvani, Rajesh Gyanchandani, Manasi Gupta, Muktesh Maulana Azad National Institute of Technology Department of Cse Bhopal India

ISBN: (纸本)9798350348460

This study explores multivariate time series forecasting, centering on the transformer model. It examines the shortcomings of other predictive models like Recurrent Neural Networks (RNN) and Temporal Convolutional Networks (TCN), particularly their inadequacies in handling autocorrelation. The transformer model stands out for its accuracy, thanks to its attention mechanism that focuses on essential parts of the input. The research introduces a novel approach that employs the transformer's architecture for effective feature selection in time series data. A vital aspect of this approach is the use of unsupervised pre-training, which shows superior results compared to traditional fully supervised methods. This advancement underscores the effectiveness of unsupervised learning in time series regression, offering significant benefits for diverse scientific and industrial fields. © 2024 IEEE.

关键词： Attention Mechanism Autocorrelation Deep Learning encoder-decoder Heteroskedasticity Quantile Regression Time Series Forecasting Transformers

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：