检索结果-内蒙古大学图书馆

Video Summarization With Attention-Based encoder-decoder Networks

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2020年第6期30卷 1709-1717页

作者： Ji, Zhong Xiong, Kailin Pang, Yanwei Li, Xuelong Tianjin Univ Sch Elect & Informat Engn Tianjin 300072 Peoples R China Northwestern Polytech Univ Ctr OPT IMagery Anal & Learning Sch Comp Sci Xian 710072 Peoples R China

This paper addresses the problem of supervised video summarization by formulating it as a sequence-to-sequence learning problem, where the input is a sequence of original video frames, and the output is a keyshot sequence. Our key idea is to learn a deep summarization network with attention mechanism to mimic the way of selecting the keyshots of human. To this end, we propose a novel video summarization framework named attentive encoder-decoder networks for video summarization (AVS), in which the encoder uses a bidirectional long short-term memory (BiLSTM) to encode the contextual information among the input video frames. As for the decoder, two attention-based LSTM networks are explored by using additive and multiplicative objective functions, respectively. Extensive experiments are conducted on two video summarization benchmark datasets, i.e., SumMe and TVSum. The results demonstrate the superiority of the proposed AVS-based approaches against the state-of-the-art approaches, with remarkable improvements on both datasets.

关键词： Decoding Visualization Recurrent neural networks Additives Indexes Internet Semantics Video summarization LSTM encoder-decoder attention mechanism

来源：评论

学校读者我要写书评

暂无评论

PixISegNet: pixel-level iris segmentation network using convolutional encoder-decoder with stacked hourglass bottleneck

引用

IET BIOMETRICS 2020年第1期9卷 11-24页

作者： Jha, Ranjeet Ranjan Jaswal, Gaurav Gupta, Divij Saini, Shreshth Nigam, Aditya Indian Inst Technol Sch Comp & Elect Engn Mandi Himachal Prades India Indian Inst Technol Jodhpur Dept Elect Engn Jodhpur Rajasthan India

In this paper, we present a new iris ROI segmentation algorithm using a deep convolutional neural network (NN) to achieve the state-of-the-art segmentation performance on well-known iris image data sets. The authors' model surpasses the performance of state-of-the-art Iris DenseNet framework by applying several strategies, including multi-scale/ multi-orientation training, model training from scratch, and proper hyper-parameterisation of crucial parameters. The proposed PixISegNet consists of an autoencoder which primarily uses long and short skip connections and a stacked hourglass network between encoder and decoder. There is a continuous scale up-down in stacked hourglass networks, which helps in extracting features at multiple scales and robustly segments the iris even in an occluded environment. Furthermore, cross-entropy loss and content loss optimise the proposed model. The content loss considers the high-level features, thus operating at a different scale of abstraction, which compliments the cross-entropy loss, which considers pixel-to-pixel classification loss. Additionally, they have checked the robustness of the proposed network by rotating images to certain degrees with a change in the aspect ratio along with blurring and a change in contrast. Experimental results on the various iris characteristics demonstrate the superiority of the proposed method over state-of-the-art iris segmentation methods considered in this study. In order to demonstrate the network generalisation, they deploy a very stringent TOTA (i.e. train-once-test-all) strategy. Their proposed method achieves $E_1$E1 scores of 0.00672, 0.00916 and 0.00117 on UBIRIS-V2, IIT-D and CASIA V3.0 Interval data sets, respectively. Moreover, such a deep convolutional NN for segmentation when included in an end-to-end iris recognition system with a siamese based matching network will augment the performance of the siamese network.

关键词： image segmentation iris recognition feature extraction image coding decoding convolutional neural nets entropy codes image classification image restoration image matching siamese matching network salient iris features pixel-level iris segmentation network stacked hourglass bottleneck nonregular reflections deep convolutional neural network stacked hourglass network cross-entropy loss pixel-to-pixel classification loss deep convolutional NN encoder-decoder image segmentation performance content loss optimisation hyper-parameterisation Iris-DenseNet framework iris image data sets iris ROI image segmentation algorithm biometric segmentation research multiscale-multiorientation training Pix-SegNet train-once-test-all strategy TOTA strategy CASIA V3 0 interval data sets IIT-D interval data sets UBIRIS-V2 interval data sets

来源：评论

学校读者我要写书评

暂无评论

Attentive U-recurrent encoder-decoder network for image dehazing

引用

NEUROCOMPUTING 2021年 437卷 143-156页

作者： Yin, Shibai Wang, Yibin Yang, Yee-Hong Southwestern Univ Finance & Econ Dept Econ Informat Engn Chengdu 611130 Sichuan Peoples R China Sichuan Normal Univ Dept Engn Chengdu 610066 Sichuan Peoples R China Univ Alberta Dept Comp Sci Edmonton AB T6G 2E8 Canada

Haze removal is an important pre-processing step in many computer vision tasks. Convolutional neural networks, especially the U-shaped networks, have shown to be effective in image dehazing. Nevertheless, these networks have three main limitations. First, the relevant haze information, e.g. concentration of haze, is totally ignored. Second, spatial inconsistency and information dilution usually occur when the networks refine the dehazed results with a coarse-to-fine strategy. Third, the receptive field of the network is not large enough to capture structural information. Motivated by these problems, a new attentive U-recurrent encoder-decoder dehazing network is presented, which consists of an attentive recurrent network and a U-recurrent encoder-decoder network. By assuming that haze layers with different depths can be detected by multiple stages, we use an attentive recurrent network to generate the haze attention map for guiding the U-recurrent encoder-decoder network with the concentration of haze to better estimate the clear image. Meanwhile, the features for dehazing are further enhanced and the dehazing results are refined in the U-recurrent encoder-decoder network. This design not only enables spatial consistency but also reduces information dilution with short recurrent pathways. Furthermore, a novel residual pyramid pooling module is also proposed and used in the U-recurrent encoder-decoder network, which provides the network with structural information and with an enlarged receptive field. The experimental results demonstrate that our method outperforms state-of-the-art dehazing algorithms on both synthetic and real hazy images. Haze removal is an important pre-processing step in many computer vision tasks. Convolutional neural networks, especially the U-shaped networks, have shown to be effective in image dehazing. Nevertheless, these networks have three main limitations. First, the relevant haze information, e.g. concentration of haze, is totally ignore

关键词： Image dehazing Attention mechanism Recurrent network encoder-decoder Convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Quick large-scale spatiotemporal flood inundation computation using integrated encoder-decoder LSTM with time distributed spatial output models

引用

JOURNAL OF HYDROLOGY 2024年 634卷

作者： Wei, Guozhen Xia, Wei He, Bin Shoemaker, Christine Dalian Maritime Univ Coll Transport Engn Dalian 116026 Peoples R China Natl Univ Singapore Dept Ind Syst Engn & Management Singapore 117576 Singapore Campus Res Excellence & Technol Enterprise CREATE Energy & Environm Sustainabil Megac E2S2 Phase 2 Singapore 138602 Singapore Politecn Milan Dept Elect Informat & Bioengn I-20133 Milan Italy Dalian Univ Technol Sch Hydraul Engn Dalian 116024 Peoples R China Natl Univ Singapore Dept Civil & Environm Engn Singapore 117576 Singapore

Accurate spatiotemporal flood simulations are essential for making informed decisions regarding flood release in affected regions, such as flood detention areas. Traditional spatiotemporal flood simulation approach uses partial differential equation (PDE) models (or physics-based models), which need high computational time. Although many machine learning (ML) models for inundation are increasingly being used to emulate the PDE models to address this issue, utilizing conventional ML models to achieve large-scale spatiotemporal flood prediction (i.e., simulation output in tens of thousands of grids and time steps over the whole flood event) remains a significant challenge. Therefore, we developed a new inundation model (IM) using encoder-decoder long short-term memory (ED-LSTM) with Time Distributed Spatial output model (ED-LSTM-TDS) that can acquire accurate spatially distributed flood information more rapidly. In the new IM framework, each ED-LSTM-TDS is built to simultaneously generate output for multiple (K) cell grids and multiple ED-LSTM-TDS models are built for prediction at all grids of entire PDE model. This study is the first of its kind to employ the ED-LSTM-TDS method to address spatiotemporal flood inundation simulation problems for flood detention areas. A 1994 km2 flood detention area in northeastern China was used as a case study. ED-LSTM-TDS exhibited better performance in predicting flood characteristics (e.g., water depth, velocity) than alternative methods, including ordinary LSTM, artificial neural network (ANN), and multiple linear regression (MLR). In addition, we investigated the trade-off relationship between the accuracy of flood characteristic prediction and the computation time of the proposed model by considering different numbers of K cell grids in each ED-LSTM-TDS model. The final proposed inundation model could accurately predict the spatiotemporal flood characteristics within 1.5 min to acquire the same information that required approx

关键词： encoder-decoder LSTM Physics-based model Flood inundation prediction Machine learning

来源：评论

学校读者我要写书评

暂无评论

An Attention encoder-decoder Network Based on Generative Adversarial Network for Remote Sensing Image Dehazing

引用

IEEE SENSORS JOURNAL 2022年第11期22卷 10890-10900页

作者： Zhao, Liquan Zhang, Yupeng Cui, Ying Northeast Elect Power Univ Key Lab Modern Power Syst Simulat & Control & Ren Minist Educ Jilin 132012 Jilin Peoples R China Guangdong Elect Power Corp Zhuhai Power Supply Bu Zhuhai 519000 Peoples R China

Remote sensing image dehazing is a difficult problem for its complex characteristics. It can be regarded as the preprocessing of high-level tasks of remote sensing images. To remove haze from the hazy remote sensing image, an encoder-decoder based on generative adversarial network is proposed. It first learns the low-frequency information of the image, and then learns the high-frequency information of the image. The skip connection is also added in the network to avoid losing information. To further improve the ability of learning more useful information, a multi-scale attention module is proposed. Meanwhile, a CBlock module is also designed to extract more feature information. It can capture different size of receptive fields. In order to reduce the computational pressure of the network, a distillation module is used in the network. Inspired by multi-scale network, an enhance module is designed and introduced it in the end of the network to further improve the dehazing ability of the network by integrating context information on multi-scale. We compared with five methods and our proposed method on RICE dataset. Experimental results show that our method achieves the best effect, both qualitatively and quantitatively.

关键词： Atmospheric modeling Feature extraction Remote sensing Generative adversarial networks Training Scattering Learning systems Remote sensing image dehazing generative adversarial network encoder-decoder multi-scale attention module

来源：评论

学校读者我要写书评

暂无评论

Compensating for Local Ambiguity With encoder-decoder in Urban Scene Segmentation

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2022年第10期23卷 19224-19235页

作者： Tang, Quan Liu, Fagui Zhang, Tong Jiang, Jun Zhang, Yu Zhu, Boyuan Tang, Xuhao South China Univ Technol Sch Comp Sci & Engn Guangzhou 510006 Peoples R China

Semantic segmentation plays a critical role in scene understanding for self-driving vehicles. A line of efforts has proven that global context matters in urban scene segmentation due to massive scale changes. However, we find that existing methods suffer from local ambiguities when dissipating continuous local context, i.e. scrambling to a huge receptive field of global cues by coarse pooling. To this end, this paper proposes a new Context Aggregation Module (CAM) that consists of two primary components: context encoding using no coarse pooling but encoder-decoders with appropriate sampling scales and gated fusion that extends gate attention mechanism to balance different-scale context during feature fusion. Weeding out coarse pooling and applying the encoder-decoder inherits the merits of exploring global context while avoiding the drawback of losing local contextual continuity. We then construct a Context Aggregation Network (CANet) and conduct extensive evaluations on challenging autonomous driving benchmarks of Cityscapes, CamVid and BDD100K. Consistently improved results evidence the effectiveness. Notably, we attain competitive mIoU 82.7% on Cityscapes and optimal mIoU 80.5% on CamVid.

关键词： Image segmentation Semantics Logic gates Transformers Computational modeling Convolutional neural networks Convolution Context continuity encoder-decoder gate attention semantic segmentation autonomous driving

来源：评论

学校读者我要写书评

暂无评论

Dual Attention-Based encoder-decoder: A Customized Sequence-to-Sequence Learning for Soft Sensor Development

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2021年第8期32卷 3306-3317页

作者： Feng, Liangjun Zhao, Chunhui Sun, Youxian Zhejiang Univ Coll Control Technol & Engn State Key Lab Ind Control Technol Hangzhou 310027 Peoples R China

Soft sensor techniques have been applied to predict the hard-to-measure quality variables based on the easy-to-measure process variables in industry scenarios. Since the products are usually produced with prearranged processing orders, the sequential dependence among different variables can be important for the process modeling. To use this property, a dual attention-based encoder-decoder is developed in this article, which presents a customized sequence-to-sequence learning for soft sensor. We reveal that different quality variables in the same process are sequentially dependent on each other and the process variables are natural time sequences. Hence, the encoder-decoder is constructed to explicitly exploit the sequential information of both the input, that is, the process variables, and the output, that is, the quality variables. The encoder and decoder modules are specified as the long short-term memory network. In addition, since different process variables and time points impose different effects on the quality variables, a dual attention mechanism is embedded into the encoder-decoder to concurrently search the quality-related process variables and time points for a fine-grained quality prediction. Comprehensive experiments are performed based on a real cigarette production process and a benchmark multiphase flow process, which illustrate the effectiveness of the proposed encoder-decoder and its sequence to sequence learning for soft sensor.

关键词： Task analysis Decoding Feature extraction Industries Prediction algorithms Humidity Predictive models Attention mechanism encoder-decoder long short-term memory (LSTM) network process industry sequence to sequence learning soft sensor modeling

来源：评论

学校读者我要写书评

暂无评论

STAGED: A Spatial-Temporal Aware Graph encoder-decoder for Fault Diagnosis in Industrial Processes

引用

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS 2024年第2期20卷 1742-1752页

作者： Li, Shizhong Meng, Wenchao He, Shibo Bi, Jichao Liu, Guanglun Zhejiang Univ State Key Lab Ind Control Technol Coll Control Sci & Engn Hangzhou 310027 Peoples R China Zhejiang Univ Key Lab CS&AUS Zhejiang Prov Hangzhou 310027 Peoples R China Zhejiang Inst Ind & Informat Technol Hangzhou 310000 Peoples R China

Data-driven fault diagnosis for critical industrial processes has exhibited promising potential with massive operating data from the supervisory control and data acquisition system. However, automatically extracting the complicated interactions between measurements and subtly integrating it with temporal evolutions have not been fully considered. Besides, with the increasing complexity of industrial processes, accurately locating fault roots is of tremendous significance. In this article, we propose an unsupervised spatial-temporal aware graph encoder-decoder (STAGED) model for industrial fault diagnosis. Firstly, the high-dimensional measurements are constructed as a weighted graph to depict the complicated interactions. Then, the graph convolutional network, long short-term memory network and attention mechanism are applied to learn a comprehensive representation for multi-series. To enforce the model to better capture the temporal evolution, the dual decoder that performs reconstruction and prediction tasks simultaneously is adopted with a well-designed comprehensive loss function. By learning the spatial-temporal evolutions of datasets, faults can be diagnosed and located at a fine-grained level based on reconstruction deviations. To verify the performance of STAGED, experiments on Cranfield three-phase flow facility and secure water treatment datasets are implemented and the results indicate that it can provide insight into fault evolution and accurately diagnose faults.

关键词： Graph convolutional networks fault diagnosis encoder-decoder unsupervised learning time series complex industrial processes.

来源：评论

学校读者我要写书评

暂无评论

Multi-dimensional feature extraction-based deep encoder-decoder network for automatic surface defect detection

引用

NEURAL COMPUTING & APPLICATIONS 2023年第4期35卷 3263-3282页

作者： Uzen, Huseyin Turkoglu, Muammer Hanbay, Davut Bingol Univ Engn Fac Comp Engn Dept Bingol Turkey Samsun Univ Engn Fac Software Engn Dept Samsun Turkey Inonu Univ Engn Fac Comp Engn Dept Malatya Turkey

The control of surface defects is of critical importance in manufacturing quality control systems. Today, automatic defects detection using imaging and deep learning algorithms has produced more successful results than manual inspections. Thanks to these automatic applications, manufacturing systems will increase the production quality, and thus financial losses will be prevented. However, since the appearance and dimensions of the defects on the surface are very variable, automatic surface defect detection is a complex problem. In this study, multi-dimensional feature extraction-based deep encoder-decoder network (MFE-DEDNet) network developed to solve such problems. An effective encoder-decoder model with lower parameters compared to the state-of-the-art methods is developed using the depthwise separable convolutions (DSC) layers in the proposed model. In addition, the 3D spectral and spatial features extract (3DFE) module of the proposed model is developed to extract deep spectral and spatial features, as well as deep semantic features. During the combination of these features, the multi-input attention gate (MIAG) module is used so that important details are not lost. As a result, the proposed MFE-DEDNet model based on these structures enabled the extraction of powerful and effective features for defect detection in surface datasets containing few images. In experimental studies, MVTec and MT datasets were used to evaluate the performance of the MFE-DEDNet. The experimental results achieved 80.01% and 56% mean intersection-over-union (mIoU) scores for the MT and MVTec datasets, respectively. In these results, it was observed that the proposed model produced higher success compared to other state-of-the-art methods.

关键词： Surface defect detection Deep learning 3D spectral and spatial features extract encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

A Nested Residual encoder-decoder Network for Overhead Contact System Fastener Anomaly Detection

引用

IEEE ACCESS 2021年 9卷 74959-74968页

作者： Wei, Tiantian Guo, Qifan Zhang, Xuewu Zhang, Cheng Jing, Wenfeng Xi An Jiao Tong Univ Sch Math & Stat Xian 710049 Peoples R China China Railway First Survey & Design Inst Grp Co L Xian 710043 Peoples R China

An overhead contact system (OCS) is key to providing power to high-speed railways. OCS detection is an important measure to ensure the safe operation of a high-speed railway. At present, OCS anomaly detection mainly relies on the manual analysis of the images regularly collected by the 4C system, which is very inefficient and can easily miss anomalies. Although some classification and object detection methods based on deep learning can be used for OCS anomaly detection, the effective training of deep networks can be difficult to support due to the small number of anomaly OCS image samples. Considering that most OCS faults are abnormal fasteners, we propose an abnormal detection method based on normal images, called the nested residual encoder-decoder network (NRE-Net). This network consists of two nested encoder-decoder networks, where the encoder is the shared part, and a residual structure is added to the encoding and decoding branches to enhance the feature expression ability. The experimental results show that the method can greatly improve the accuracy of anomaly detection for the CIFAR-10 dataset and OCS fastener dataset. Compared with the previous state-of-the-art approaches, the F-1 score of the proposed method for the two classes fastener in the OCS fastener dataset has increased by 10.8% and 11.9%, respectively.

关键词： OCS anomaly detection encoder-decoder distance measurement

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：