检索结果-内蒙古大学图书馆

Dense spatially-weighted attentive residual-haze network for image dehazing

APPLIED INTELLIGENCE 2022年第12期52卷 13855-13869页

作者： Singh, Mohit Laxmi, Vijay Faruki, Parvez MNIT Jaipur Rajasthan India AVPTI Rajkot Gujarat India

Haze severely affects computer vision algorithms by degrading the quality of captured images and results in image data loss. With several available approaches for dehazing, single image dehazing is most preferred and challenging. We proposed a Dense Spatially-weighted Attentive Residual-haze Network (DSA Net), a novel end-to-end encoder-decoder architecture to learn the residual haze layer between the hazy and haze-free image. We use encoder-decoder blocks with multiple skip connections to improve feature propagation. Feature Learning block uses a novel Residual Inception fused with Attention (RIA) block to learn the complex non-linearity from features extracted from the encoder part. Learning residual image is more straightforward than the whole haze-free image, and it improves the ability of the network to estimate the haze thickness accurately. DSA Net learns this less complex residual-map from the hazy input image and subtracts it from the input to obtain the dehazed images. Detail ablation study shows the effectiveness of different modules used in our architecture. Experiment results on different haze conditions demonstrate that our method shows significant improvement over other state-of-the-art methods.

关键词： Dehazing Attention mechanism encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

FMAM-Net: Fusion Multi-Scale Attention Mechanism Network for Building Segmentation in Remote Sensing Images

引用

IEEE ACCESS 2022年 10卷 134241-134251页

作者： Ye, Huanran Zhou, Run Wang, Jianhao Huang, Zhiliang Yiwu Ind & Commercial Coll Sch Mech & Elect Informat Jinhua 322000 Zhejiang Peoples R China Zhejiang Normal Univ Coll Phys & Elect Informat Engn Jinhua 321004 Zhejiang Peoples R China

As the largest target in remote sensing images, buildings have important application value in urban planning and old city reconstruction. However, most networks have poor recognition ability on high resolution images, resulting in blurred boundaries in the segmented building maps. Then, the similarity between buildings and backgrounds will lead to inter-class indistinction. Finally, the diversity of buildings brings difficulties to segmentation, which requires the network to have better generalization ability. To address these problems, we propose Fusion Multi-scale Attention Mechanism Network (FMAM-Net). Firstly, we design Feature Refine Compensation Module(FRCM) to improve the boundary ambiguity problem, including Feature Refinement Module(FRM) and Feature Compensation Module(FCM). FRM utilizes the densely connected architecture to refine features and increase recognition capabilities. FCM introduces low-level features to make up for the lack of boundary information in high-level features. Secondly, to handle inter-class indistinction, we design Tandem Attention Module(TAM) and Parallel Attention Module(PAM). TAM is designed to sequentially filter some features from channels and spaces for adaptive feature refinement. PAM combines context information and uses high-level features to guide low-level features to select more distinguishable features. Finally, based on the binary cross entropy loss function, we add an evaluation index to reduce the error caused by determining the optimization direction only through cross entropy. On the Inria Aerial Image Labeling Dataset, FMAM-Net achieves mean IoU of 85.34%, which is 5.58% higher than AMUNet and 3.77% higher than our baseline(U-Net ResNet-34). On the WHU Dataset, IoU reached the maximum value of 91.06% on FMAM-Net, 1.67% higher than SARB-UNet and 0.2% higher than MAP-Net. The visualization results show that FMAM-Net improves the fuzzy boundary of building segmentation and reduces the inter-class indistinction.

关键词： Remote sensing image building segmentation attention mechanism feature refinement encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

Video summarization with a dual-path attentive network

引用

NEUROCOMPUTING 2022年 467卷 1-9页

作者： Liang, Guoqiang Lv, Yanbing Li, Shucheng Wang, Xiahong Zhang, Yanning Northwestern Polytech Univ Sch Comp Sci Natl Engn Lab Integrated Aerosp Ground Ocean Big Xian Peoples R China

With the explosive growth of videos captured everyday, how to efficiently extract useful information from videos has become a more and more important problem. As one of the most effective methods, video summarization aiming to extract the most important frames or shots has attracted more interests recently. Currently, lots of methods employ a recurrent structure. However, due to its step-by-step char-acteristic, it is difficult to parallelize these models. To address this problem, we propose a dual-path attentive video summarization framework consisting of a temporal spatial encoder, a score-aware enco-der and a decoder. And all of them are mainly based on multi-head self-attention and convolutional block attention module. The temporal spatial encoder is to capture the temporal and spatial information while the score-aware encoder incorporates the appearance features with previously predicted frame-level importance scores. By combining the scores and appearance features, our model can better capture the long-range global dependencies and update the importance scores of previous frames continuously. Moreover, entirely based on attention mechanism, our model can be trained in full parallel, which leads to less training time. To validate the method, we employ the two popular datasets SumMe and TVSum. The experimental results show the effectiveness of the proposed method. (c) 2021 Elsevier B.V. All rights reserved.

关键词： Video summarization Attention mechanism encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

Dynamic Attention Filter Capsule Network for Medical Images Segmentation 19th

Dynamic Attention Filter Capsule Network for Medical Images ...

引用

19th International Conference on Advanced Intelligent Computing Technology and Applications (ICIC)

作者： Chen, Ran Hu, Kai Zhao, Zhong-Qiu Hefei Univ Technol Coll Comp & Informat Hefei Peoples R China HFUT Intelligent Mfg Inst Hefei Peoples R China Hefei Univ Technol Intelligent Interconnected Syst Lab Anhui Prov Hefei Peoples R China Guangxi Acad Sci Nanning Guangxi Peoples R China

ISBN: (纸本)9789819947416;9789819947423

In the existing works, Capsule Networks (CapsNets) have been proven to be promising alternatives to Convolutional Neural Networks (CNNs). However, CapsNets perform poorly on complex datasets with RGB backgrounds and cannot handle images with large input sizes. We propose a Dynamic Attention Filter (DAF) method to improve the performance of CapsNets. DAF is a filter unit between low-level capsule layers and voting layers, which can effectively filter the invalid background capsules and improve the classification performance of CapsNet. Besides, we propose DAF-CapsUNet for inputting medical images of large sizes, combining the advantages of the U-shaped encoder-decoder structure and DAF-CapsNet. Specifically, it contains three fundamental operations: an encoder is responsible for extracting shallow feature information, a capsule module is responsible for capturing the detailed feature information lost due to the pooling layer of the CNNs, and a decoder is responsible for fusing the feature information extracted from the two stages. Extensive experiments demonstrate that DAF can improve the performance of CapsNets on complex datasets and reduce the number of parameters, GPU memory cost, and running time of CapsNets. Benefiting from DAF-CapsNet, our model can achieve more useful information for precise localization. The medical experiments show that DAF-CapsUNet achieves SOTA performance compared to other segmentation models.

关键词： CapsNets DAF encoder-decoder DAF-CapsUNet

来源：评论

学校读者我要写书评

暂无评论

Relative Position Embedding Asymmetric Siamese Network for Offline Handwritten Mathematical Expression recognition 17th

Relative Position Embedding Asymmetric Siamese Network for O...

引用

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

作者： Wang, Chunyi Luo, Hurunqi Rao, Xiaqing Hui, Wei Bi, Ning Tan, Jun Sun Yat Sen Univ Sch Math Guangzhou 510275 Peoples R China Sun Yat Sen Univ Guangdong Prov Key Lab Computat Sci Guangzhou 510275 Peoples R China Meituan Shanghai Peoples R China

ISBN: (纸本)9783031416750;9783031416767

Currently, Recurrent Neural Network(RNN)-based encoder-decoder models are widely used in handwritten mathematical expression recognition (HMER). Due to its recursive pattern, the problem of gradient disappearance or gradient explosion also exists for RNN, which makes them inefficient in processing long HME sequences. In order to solve above problems, this paper proposes a Transformer-based encoder-decoder model consisting of an asymmetric siamese network, relative position embedding Transformer (ASNRT). With the assistance of printed images, the asymmetric siamese network further narrows the difference betweeen feature maps of similar formula images and increases the encoding gap between dissimilar formula images. We insert coordinate attention into the encoder, additionally we replace RNN with Transformer as the decoder. Moreover, rotary position embedding is used, incorporating relative position information through absolute embedding ways. Given the symmetry of MEs, we adopt the bidirectional decoding strategy. Extensive experiments show that our model improves the ExpRate of state-of-the-art methods on CROHME 2014, CROHME 2016, and CROHME 2019 by 0.94%, 2.18% and 2.12%, respectively.

关键词： Handwritten Contrastive Learning encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

An Efficient Embedding Framework for Uncertain Attribute Graph 34th

An Efficient Embedding Framework for Uncertain Attribute Gra...

引用

34th International Conference on Database and Expert Systems Applications (DEXA)

作者： Jiang, Ting Yu, Ting Qiao, Xueting Zhang, Ji Zhejiang Lab Hangzhou Peoples R China Univ Southern Queensland Toowoomba Qld Australia

ISBN: (纸本)9783031398209;9783031398216

Graph data with uncertain connections between entities is commonly represented using uncertain graphs. This paper tackles the challenge of graph embedding within such uncertain attribute graphs. Current graph embedding techniques are typically oriented towards deterministic graphs, or uncertain graphs that lack attribute data. Furthermore, the majority of studies on uncertain graph learning simply adapt conventional algorithms for deterministic graphs to handle uncertainty, leading to compromised computational efficiency. To address these issues, we introduce an optimized embedding framework UAGE for uncertain attribute graphs. In UAGE, nodes are represented within a Gaussian distribution space to learn node attributes. We also propose a Probability Similarity Value (PSV) to manage relationship uncertainty and ensure that nodes with higher-order similar structures are located more closely in the latent space. Real-world dataset experiments confirm that UAGE surpasses contemporary methods in performance for downstream tasks.

关键词： Uncertain graph Gaussian embedding encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

A ROBUST CHANGE DETECTION METHODOLOGY FOR FLOOD EVENTS USING SAR IMAGES

A ROBUST CHANGE DETECTION METHODOLOGY FOR FLOOD EVENTS USING...

引用

IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

作者： Al-Saad, Mina Aburaed, Nour Zitouni, M. Sami Alkhatib, Mohammed Q. Almansoori, Saeed Al Ahmad, Hussain Univ Dubai Coll Engn & IT Dubai U Arab Emirates Univ Strathclyde Dept Elect & Elect Engn Glasgow Lanark Scotland Mohammed Bin Rashid Space Ctr Dubai U Arab Emirates

ISBN: (纸本)9798350320107

Accurate flood mapping plays a critical role in disaster management, allowing for effective response and mitigation efforts. Thus, researchers seek to boost the accuracy of flood mapping algorithms, especially in terms of generalization capability and minimizing False Positive and False Negative detection. This paper presents a robust flood mapping algorithm from SAR images via Deep Convolutional Neural Network (DCNN) that follows encoder-decoder scheme. By introducing Bidirectional Convolutional LSTM (ConvLSTM) layers into its architecture, the proposed Temporal-Spatial encoder-decoder Network (TSEDN) network is able to extract temporal information and produce more accurate change maps. The training and testing are carried using OMBRIA dataset, which is known to be challenging to train. The proposed network is evaluated and compared to other state-of-the-art approaches in terms of Overall Accuracy (OA), Precision, Recall, and mean Intersection over Union (mIoU).

关键词： SAR change detection flood mapping encoder-decoder Bidirectional LSTM

来源：评论

学校读者我要写书评

暂无评论

DSEAformer: Forecasting by De-stationary Autocorrelation with Edgebound 1

引用

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

作者： Ding, Peihao Tang, Yan Chen, Yingpei Li, Xiaobing Southwest Univ Sch Comp & Informat Sci Chongqing Peoples R China

ISBN: (数字)9783031402838

ISBN: (纸本)9783031402821;9783031402838

Time series analysis is vital for various real-world scenarios. Enhancing multivariate long-sequence time-series forecasting (MLTF) accuracy is crucial due to the increasing data volume and dimensionality. Current MLTF methods face challenges such as over-stationarization and distribution shift, affecting prediction accuracy. This paper proposes DSEAformer, a unique MLTF method that addresses distribution shift by normalizing and de-normalizing time series data. To avoid over-stationarization, a de-stationary autocorrelation method is suggested. Additionally, a time series optimization regularization based on weighted moving average helps prevent overfitting. Tests on three datasets confirm that DSEAformer outperforms existing MLTF techniques. In conclusion, DSEAformer introduces innovative ideas and methods to enhance time series prediction and offers improved practical applications.

关键词： Multivariate long-sequence time-series forecasting encoder-decoder Autocorrelation mechanism Temporal optimization regularization Sequence decomposition

来源：评论

学校读者我要写书评

暂无评论

A novel method for 12-lead ECG reconstruction 57

A novel method for 12-lead ECG reconstruction

引用

57th Asilomar Conference on Signals, Systems and Computers

作者： EPMoghaddam, Dorsa Banta, Anton Post, Allison Razavi, Mehdi Aazhang, Behnaam Rice Univ Dept Elect & Comp Engn POB 1892 Houston TX 77251 USA Texas Heart Inst Electrophysiol Clin Res & Innovat Houston TX USA Texas Heart Inst Dept Cardiol Houston TX USA

ISBN: (纸本)9798350325744

This paper presents a novel approach to synthesize a standard 12-lead electrocardiogram (ECG) from any three independent ECG leads using a patient-specific encoder-decoder convolutional neural network. The objective is to decrease the number of recording locations required to obtain the same information as a 12-lead ECG, thereby enhancing patients' comfort during the recording process. We evaluate the proposed algorithm on a dataset comprising fifteen patients, as well as a randomly selected cohort of patients from the PTB diagnostic database. To evaluate the precision of the reconstructed ECG signals, we present two metrics: the correlation coefficient and root mean square error. Our proposed method achieves superior performance compared to most existing synthesis techniques, with an average correlation coefficient of 0.976 and 0.97 for datasets, respectively. These results demonstrate the potential of our approach to improve the efficiency and comfort of ECG recording for patients, while maintaining high diagnostic accuracy.

关键词： electrocardiogram (ECG) Signal reconstruction cardiovascular diseases convolutional neural network encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

Triple Extraction with Generative Technique for Constructing Weighted Knowledge Graph 22

Triple Extraction with Generative Technique for Constructing...

引用

22nd IEEE/WIC International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT)

作者： Parniani, Mohammad Sahand Reformat, Marek Z. Univ Alberta Elect & Comp Engn Edmonton AB Canada Univ Social Sci Inst Informat Technol PL-90113 Lodz Poland

ISBN: (纸本)9798350309188

Extracting relational facts from unstructured text is crucial in natural language processing used in many applications, particularly in constructing knowledge graphs. Relational facts are represented as triples in which two entities are connected through a relation. This work introduces a new and effective end-to-end method to generate triples from the input text. In the proposed method, we develop an encoder-decoder-based transformer model and warm-start both the encoder and decoder with pretrained checkpoints that are publicly accessible. These checkpoints can be taken from models such as BERT, GPT-2, and RoBERTa. Experimental results show that our method achieves better results for triple extraction on publicly available datasets (NYT and WebNLG) than the other state-of-the-art techniques. Further, the extracted triples are processed and used to build a knowledge graph. Complete control of this process allows for determining the weights of the relations (triples). The weights reflect the frequency of occurrences of facts represented by the relations and provide the degree of confidence in the facts.

关键词： triple extraction knowledge graph encoder-decoder transformer

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：