检索结果-内蒙古大学图书馆

Enhanced Recognition of Offline Marathi Handwriting via a Self-Additive Attention Mechanism

TRAITEMENT DU SIGNAL 2023年第6期40卷 2853-2860页

作者： Chikmurge, Diptee Vishwanath Raghunathan, Shriram VIT Bhopal Univ Sch Comp Sci & Engn Bhopal 466114 Madhya Pradesh India MIT Acad Engn Sch Comp Engn Alandi 412105 Maharashtra India

Background: Offline Marathi handwriting recognition presents a significant challenge due to the script's complexity and the variability of individual writing styles. Methods: In the present work, an advanced encoder-decoder framework is introduced, wherein a novel self -additive-attention mechanism is integrated. This model capitalizes on a Convolutional Neural Network paired with a Joint Scale Feature Extractor (CNN-JSE) to discern low-level image features within the IIIT-HW-Dev dataset. Such features are subsequently fed into an encoder model that employs a dual-phase fusion process: initially leveraging a Bidirectional Long Short-Term Memory (BiLSTM) network, followed by the self-additive-attention mechanism to maintain dependencies over extensive sequences. Results: The fusion output, comprising BiLSTM and self-additive attention data, is conveyed to a Connectionist Temporal Classifier (CTC) decoder. This decoder adeptly identifies character sequences within Marathi words. The introduction of self-additive attention alongside BiLSTM is instrumental in preserving dependencies that are both long-range and multi-stage. Performance Evaluation: The efficacy of the proposed system was rigorously evaluated on the multi-author IIIT-HW-Dev dataset. Performance metrics, specifically Character Error Rate (CER) and Word Error Rate (WER), were employed for benchmarking against various established models. Conclusion: The proposed methodology demonstrates a significant enhancement in the recognition of handwritten Marathi text, thus facilitating the conversion of handwritten documents into machine-editable text. The utilization of self -additive attention within the BiLSTM framework underscores its potential in capturing complex dependencies, setting a new precedent in automated handwriting recognition technologies. Significance: This study not only paves the way for increased accuracy in handwritten text recognition but also contributes a novel approach to the encoding of fea

关键词： optical character recognition bidirectional long short-term memory convolutional neural network encoder-decoder and connectionist temporal classifier

来源：评论

学校读者我要写书评

暂无评论

Coastal Land Cover Classification of High-Resolution Remote Sensing Images Using Attention-Driven Context Encoding Network

引用

SENSORS 2020年第24期20卷 7032-7032页

作者： Chen, Jifa Chen, Gang Wang, Lizhe Fang, Bo Zhou, Ping Zhu, Mingjie China Univ Geosci Coll Marine Sci & Technol Wuhan 430074 Peoples R China China Univ Geosci Key Lab Geol Survey & Evaluat Minist Educ Wuhan 430074 Peoples R China China Univ Geosci Sch Comp Sci Wuhan 430074 Peoples R China

Low inter-class variance and complex spatial details exist in ground objects of the coastal zone, which leads to a challenging task for coastal land cover classification (CLCC) from high-resolution remote sensing images. Recently, fully convolutional neural networks have been widely used in CLCC. However, the inherent structure of the convolutional operator limits the receptive field, resulting in capturing the local context. Additionally, complex decoders bring additional information redundancy and computational burden. Therefore, this paper proposes a novel attention-driven context encoding network to solve these problems. Among them, lightweight global feature attention modules are employed to aggregate multi-scale spatial details in the decoding stage. Meanwhile, position and channel attention modules with long-range dependencies are embedded to enhance feature representations of specific categories by capturing the multi-dimensional global context. Additionally, multiple objective functions are introduced to supervise and optimize feature information at specific scales. We apply the proposed method in CLCC tasks of two study areas and compare it with other state-of-the-art approaches. Experimental results indicate that the proposed method achieves the optimal performances in encoding long-range context and recognizing spatial details and obtains the optimum representations in evaluation indexes.

关键词： coastal zone land cover classification semantic segmentation encoder-decoder context encoding attention mechanism

来源：评论

学校读者我要写书评

暂无评论

CvT-UNet: A weld pool segmentation method integrating a CNN and a transformer

引用

HELIYON 2024年第15期10卷 e34738页

作者： Yang, Longcheng Wang, Huajun Meng, Wenjie Pan, Hongyu Chengdu Normal Univ Sichuan Key Lab Indoor Space Layout Optimizat & Se Chengdu 611130 Peoples R China Chengdu Univ Technol Minist Educ Key Lab Earth Explorat & Informat Technol Chengdu 610059 Peoples R China

In the acquisition of weld seam images, the presence of light and impurity interference often leads to weak edge problems in weld seam images, making the identification of weld seam defects challenging. In such scenarios, segmentation processing must be performed specifically at the fusion pool of the weld seam. In recent years, Transformers, which leverage self-attention mechanisms, have demonstrated superior sequence modeling capabilities compared to convolutional neural networks (CNNs). The Transformer excels at weighting different positions within a sequence, enabling effective handling of long-range dependencies. However, Transformers lack the ability of CNNs to extract local information. To address this limitation, this paper introduces a novel CvT-UNet semantic segmentation model that combines the strengths of both the convolutional neural network and the transformer. The model combines the global context information capabilities of the Transformer with the spatial information advantages provided by the convolutional neural network. The proposed model employs an encoder-decoder architecture by building a U-shaped network with designed CvT blocks. Depthwise separable convolutions are utilized to balance parameter quantities, and the skip-connection module is redesigned to enable the model to achieve more precise segmentation of weld seam fusion pools with fewer parameters. Experimental evaluations on diverse weld seam datasets under different environmental conditions demonstrate promising results. The model achieves average intersection over union (IoU) values of 93.75 %, 88.31 %, and 90.86 %, respectively. Specifically, on an automotive weld seam dataset, CvT-UNet outperforms the purely convolutional neural network structure UNet3+, with a 1.63 % increase in the mean IoU (MIOU) and a 1.39 % increase in the mean pixel accuracy (MPA). Compared to the TransUNet fusion model, CvT-UNet results in a 0.33 % increase in the MIOU and a 0.6 % increase in the MPA. Furth

关键词： encoder-decoder Transformer Deep separable convolution Skip connection

来源：评论

学校读者我要写书评

暂无评论

The Impact of Text Generation Techniques on Neural Image Captioning: An Empirical Study

引用

INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS 2023年第10期14卷 1080-1090页

作者： Ding, Linna Jiang, Mingyue Nie, Liming Qing, Zuzhang Ding, Zuohua Zhejiang Sci Tech Univ Fac Comp Sci & Technol Hangzhou Zhejiang Peoples R China Nanyang Technol Univ Sch Comp Sci & Technol Singapore Singapore Zhejiang Petr Integrated Energy Sales Co Ltd Hangzhou Zhejiang Peoples R China

Image captioning is an advanced NLP task that has various practical applications. To meet the requirement of visual information understanding and textual information generation, the encoder-decoder framework has been widely adopted by image captioning models. In this context, the encoder is responsible for transforming an image into vector representation, and the decoder acts as a text generator for yielding an image caption. It is obvious and intuitive that the decoder is crucial for the entire image captioning model. However, there is a lack of comprehensive studies in which the impact of various aspects of the decoder on the image captioning is investigated. To advance the understanding of the impacts of text generation techniques employed by the decoder, we conduct an extensive empirical analysis of three types of language models, two types of decoding strategies and two types of training methods, based on four stateof-the-art image captioning models. Our experimental results demonstrate that the language model affects the performance of image captioning models, while different language models may benefit different image captioning models. In addition, it is also revealed that among the decoding and training strategies under investigation, the beam search, AOA mechanism and the reinforcement learning based training method can generally improve the performance of image captioning models. Moreover, the results also show that the combinational usage of these strategies always outperforms the use of single strategy for the task of image captioning.

关键词： Image captioning encoder-decoder text generation techniques

来源：评论

学校读者我要写书评

暂无评论

Automatic Generation of Chest X-Ray Medical Imaging Reports using LSTM-CNN

Automatic Generation of Chest X-Ray Medical Imaging Reports ...

引用

Proceedings of the International Conference on Data Science, Machine Learning and Artificial Intelligence

作者： Vivek Tiwari Krutika Bapat Kushashwa R. Shrimali Saurabh K. Singh Basant Tiwari Swati Jain Hemant Kumar Sharma Comp. Sci. & Engg. DSPM IIIT Naya Raipur Chhattisgarh India Computer Science Hawassa University Hawassa Ethiopia Computer Science Govt. J. Yoganandam Chhattisgarh College Raipur (CG) India DKS PGI & Research Center Raipur (CG) India

ISBN: (纸本)9781450387637

Generating medical reports manually is a difficult task, especially in rural areas and in urgent medical cases, where there is an emergency. It can also be error-prone for inexperienced physicians to generate a medical report. There are various deep learning methodologies such as Image captioning, image classification that has been implemented earlier to solve this problem. Generating a medical report automatically is a difficult task, considering the less amount of open-source data available and the paired data which contains medical Images and the report is also limited. One of the challenging tasks is data bias in medical Imaging. A generative encoder-decoder model is suggested to solve this problem in an efficient way. There are various other challenges. First, the medical report itself contains various heterogeneous information such as paragraphs, tags, keywords. Secondly, it is also difficult to identify the abnormal regions in medical images. To solve this problem, a multi-task framework is built, which can perform tag generation and paragraph generation. LSTM (Long Short Term Memory) is built to generate long heterogeneous paragraphs in the medical report. The model working is demonstrated on Chest X-Ray dataset and also on pathology dataset.

关键词： Deep Learning LSTM X-Ray encoder-decoder medical imaging

来源：评论

学校读者我要写书评

暂无评论

Domain Adapted Abstractive Summarization of Dialogue using Transfer Learning

Domain Adapted Abstractive Summarization of Dialogue using T...

引用

2021年第四届算法、计算和人工智能国际会议

作者： Rohit Sroch Course5 AI Labs

Recently, the abstractive dialogue summarization task has been gaining a lot of attention from researchers. Also, unlike news articles and documents with well-structured text, dialogue differs in the sense that it often comes from two or more interlocutors,exchanging information with each other and having an inherent hierarchical structure based on the sequence of utterances by different speakers. This paper proposes a simple but effective hybrid approach that consists of two modules and uses transfer learning by leveraging pretrained language models(PLMs) to generate an abstractive summary. The first module highlights important utterances, capturing the utterance level relationship by adapting an auto-encoding model like BERT based on the unsupervised or supervised method. And then, the second module generates a concise abstractive summary by adapting encoder-decoder models like T5,BART, and PEGASUS. Experiment results on benchmark datasets show that our approach achieves a state-of-the-art performance by adapting to dialogue scenarios and can also be helpful in lowresource settings for domain adaptation.

关键词： dialogue summarization abstractive summary PLMs encoder-decoder BERT T5 BART PEGASUS

来源：评论

学校读者我要写书评

暂无评论

基于深度学习的端到端场景文本识别方法研究

基于深度学习的端到端场景文本识别方法研究

引用

作者：刘衍平华南理工大学

学位级别：硕士

图片能带给人们丰富的信息,而文字作为人类智慧的结晶,其所包含的信息量往往要比色彩纹理等携带的信息量大得多,因此对场景图像中文字的识别和理解显得十分有必要和重要。由于场景文本图像的复杂性,传统OCR文字识别不再适应这种新的挑... 详细信息

图片能带给人们丰富的信息,而文字作为人类智慧的结晶,其所包含的信息量往往要比色彩纹理等携带的信息量大得多,因此对场景图像中文字的识别和理解显得十分有必要和重要。由于场景文本图像的复杂性,传统OCR文字识别不再适应这种新的挑战。人工智能及计算机科学技术的新突破,使得基于深度学习算法理论的场景文本识别方法较传统OCR技术有了较大的提升,但离实际的运用还有不小的差距。因此,本文进行基于深度学习的场景文本识别方法研究具有重要的理论研究意义及广泛的应用前景。本文旨在研究自然场景下中文文本图像的文本识别方法,提出一种基于卷积神经网络及递归神经网络的端到端场景文本识别模型与方法。与传统文本识别方法相比,该模型与方法具有更好的特征学习和特征分类能力。本文完成的主要工作包括:1、提出了一种基于可变形卷积网络的场景文本图像特征提取模型。该模型利用可变形卷积神经网络实现了文本图像特征的自动提取,与其他模型相比具有更好的特征学习能力,对复杂场景文本图像的识别具有更好的鲁棒性,尤其表现在文本图像中字体存在几何变形变换时,鲁棒性更好。利用本文提出的特征提取模型,能较好地提取场景文本图像中的特征,可以有效改善文本识别的性能。2、提出了一种改进的encoder-decoder框架中的注意力机制计算模型。标准注意力机制通常采用全局注意力的方式进行解码,并且当前时刻的输入为全部输入信息的加权和。改进后的注意力机制采用了局部注意力的方式,且当前时刻的输入为局部输入信息的加权卷积平均,即先对局部输入信息求解权重因子,各局部输入信息依据权重因子进行加权后,进行卷积操作产生多个新的输入信息,最后将多个新输入信息的平均值作为当前时刻的输入。实验结果表明,本文注意力机制的改进可以提高0.5%文本识别的准确率。3、提出了一种改进的解码输出后处理操作。现有的后处理操作通常采用纯搜索算法或者融合了简单语言模型的搜索算法,其中有些搜索算法存在因搜索简单而性能较差或因搜索复杂而耗时偏长的现象。改进后的后处理操作在不降低解码性能的前提下减少了搜索空间和时间,并融合了有效的统计语言模型。实验结果表明,本文改进的编码输出后处理可以提高解码效率和解码准确率。4、提出了一种自然场景下复杂文本图像的数据增广方法。该方法通过对少量的真实场景文本图像建模,使合成的图像在字体、颜色、噪声、仿射失真等方面更加贴近真实文本图像。通过本文所给的数据增广方法,可以快速合满足自己需要的数据集,减少数据采集的人力物力。5、提出了一种基于二维递归网络的编码解码网络模型。该模型可以避免文本图像特征图降维和利用字符结构信息,实现了端到端的文字识别。在传统的encoder-decoder框架中,通常采用一维递归神经网络作为其编码解码的核心结构。然而一维递归神经网络仅仅适应于序列识别,因此为了采用encoder-decoder框架进行文本识别,通常需要将二维文本图像的特征图进行降维,转为一维序列输入到encoder-decoder框架中。这一操作严重破坏了中文汉字的空间结构,丢失了很大一部分的空间结构特征。本文采用二维递归网络作为encoder-decoder框架的核心,使其可以直接与深度卷积网络中提取的特征图相连。encoder-decoder框架利用了中文汉字的空间结构特征,同时对文本图像中在纵坐标上的形变具有更好的鲁棒性。实验结果表明,较一维递归网络,使用二维递归网络编码解码可以提高2.6%的文本识别准确率,达到最高为78.6%的识别率。较标准二维递归网络,本文的二维递归网络在性能上接近标准二维递归网络,具有计算速度快,网络模型设计简单等特点。

关键词：文本识别深度学习卷积神经网络 encoder-decoder 注意力机制

来源：评论

学校读者我要写书评

暂无评论

Text Detection and Recognition in Natural Scenes Based on TWO-DIMENSIONAL Attention 22

Text Detection and Recognition in Natural Scenes Based on TW...

引用

Proceedings of the 2022 4th International Conference on Video, Signal and Image Processing

作者： Baicun Guo Computer Science North China Electric Power University China

ISBN: (纸本)9781450397810

In this paper, we improve the natural scene text detection and recognition technology based on 2d attention and encoder-decoder framework. Firstly, the related work of text detection and recognition in different natural view is discussed. Secondly, we work on the basis of encoder-decoder framework and two-dimention module, and improve it through aggregation and hybridisation. Finally, we discussed and analyzed the results,and figured out the possible shortcomings of the model.

关键词： two-dimention attention aggregation encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

MMAG: Mutually Motivated Attention Gates for Simultaneous Extraction of Contextual and Spatial Information from a Monocular Image 23

MMAG: Mutually Motivated Attention Gates for Simultaneous Ex...

引用

Proceedings of the Fourteenth Indian Conference on Computer Vision, Graphics and Image Processing

作者： Aditya Singh Saloni Mohan Vandana Kushwaha G C Nandi IIIT Allahabad IN

ISBN: (纸本)9798400716256

In order to effectively interact with its environment, an agent must possess the ability to comprehend the ’what’ and the ’where.’ Two vision-based approaches, namely semantic segmentation and depth estimation, can be employed to provide this information. This paper introduces a unified model that combines these two tasks and utilizes a shared latent space. The chosen approach for the model involves an encoder-decoder architecture accompanied by a novel attention gate mechanism called MMAG, which has been proven to be highly effective. Furthermore, a common skip connection method, in conjunction with the proposed attention gate, is included to emphasize crucial features for both prediction purposes. By leveraging the complementary information within the shared representations, the model is capable of generating more accurate predictions compared to other joint-prediction models, all while utilizing fewer network parameters. To enhance performance, dilated layers are incorporated, allowing for focused attention through different receptive fields. The model’s performance has been evaluated on the NYU Depth v2 and Camvid datasets, demonstrating improved results on both tasks when compared to other state-of-the-art models. With its reduced parameter count, this model is particularly suitable for low-cost robots and has undergone successful testing for inference on the LoCoBot robot.

关键词： attention gate mechanism encoder-decoder monocular depth estimation semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

创新构想话题生成

引用

山西大学学报(自然科学版) 2019年第1期42卷 51-58页

作者：陈丽娟兰艳艳庞亮李家宁郭嘉丰徐君程学旗中国科学院计算技术研究所中国科学院网络数据科学与技术重点实验室

文章提出了创新构想话题的自动生成任务,主动生成具有新颖性、权威性的话题,能够激发群体讨论热情,有助于推动相关领域的发展。以encoder-decoder文本生成技术为基础,构建了一套创新构想话题生成框架。首先通过实时爬取相关网站的内容,... 详细信息

文章提出了创新构想话题的自动生成任务,主动生成具有新颖性、权威性的话题,能够激发群体讨论热情,有助于推动相关领域的发展。以encoder-decoder文本生成技术为基础,构建了一套创新构想话题生成框架。首先通过实时爬取相关网站的内容,作为信息获取的主要来源;然后利用数据分析工具提取文本的关键词和摘要,使用了TF-IDF算法和TextRank算法;最后利用训练好的话题生成模型得到话题表达。实验结果展示了生成的创新构想话题,说明基于该文提出的流程可以有效挖掘文档中潜在的话题。

关键词：创新构想话题 encoder-decoder 话题生成模型 TextRank

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：