Resource Type

Journal Article 34

Conference Videos 1

Year

2024 6

2023 10

2022 7

2021 4

2020 1

2019 1

2017 1

2010 1

2008 2

2007 2

open ︾

Keywords

Attention mechanism 4

Attention 3

Deep learning 3

deep learning 3

COVID-19 2

Long short-term memory (LSTM) 2

Self-attention mechanism 2

attention 2

-xylene 1

Answer selection 1

Behavior heterogeneity 1

Bi-directional gated recurrent unit (BiGRU) 1

CO2 1

Capsule network 1

Community assembly 1

Computed tomography 1

Coronavirus disease 2019 pneumonia 1

Data-driven process model 1

Deep neural network 1

open ︾

Search scope:

排序： Display mode:

Prediction and cause investigation of ozone based on a double-stage attention mechanism recurrent neural

Frontiers of Environmental Science & Engineering 2023, Volume 17, Issue 2, doi: 10.1007/s11783-023-1621-4

Abstract:

● Used a double-stage attention mechanism model to predict ozone.

Keywords： Ozone prediction     Deep learning     Time series     Attention     Volatile organic compounds    

HTML PDF Collect

Hard-rock tunnel lithology identification using multi-scale dilated convolutional attention network based

Frontiers of Structural and Civil Engineering 2023, Volume 17, Issue 12,   Pages 1796-1812 doi: 10.1007/s11709-023-0002-1

Abstract: learning for training a deep convolutional neural network (DCNN), and a multi-scale dilated convolutional attentionMoreover, the attention mechanism is utilized to select the salient features adaptively and further improve

Keywords： hard-rock tunnel face     intelligent lithology identification     multi-scale dilated convolutional attention    

HTML PDF Collect

Meter-scale variation within a single transect demands attention to taxon accumulation curves in riverine

Frontiers of Environmental Science & Engineering 2022, Volume 16, Issue 5, doi: 10.1007/s11783-022-1543-6

Abstract:

● Riverine microbiomes exhibited hyperlocal variation within a single transect.

Keywords： Microbiome     Freshwater     Taxon accumulation curve     Community assembly    

HTML PDF Collect

Less attention paid to waterborne SARS-CoV-2 spreading in Beijing urban communities

Frontiers of Environmental Science & Engineering 2021, Volume 15, Issue 5, doi: 10.1007/s11783-021-1398-2

Abstract:

• A survey on individual’s perception of SARS-CoV-2 transmission was conducted.

Keywords： Environmental dissemination     Risk communication     Individual perception    

HTML PDF Collect

Erratum to: Meter-scale variation within a single transect demands attention to taxon accumulation curves

Frontiers of Environmental Science & Engineering 2022, Volume 16, Issue 6, doi: 10.1007/s11783-022-1560-5

HTML PDF Collect

Endothelial dysfunction in COVID-19 calls for immediate attention: the emerging roles of the endothelium

Weijian Hang, Chen Chen, Xin A. Zhang, Dao Wen Wang

Frontiers of Medicine 2021, Volume 15, Issue 4,   Pages 638-643 doi: 10.1007/s11684-021-0831-z

Abstract: We are calling for closer attention to endothelial dysfunction in COVID-19 not only for fully revealing

Keywords： COVID-19     endothelial dysfunction     inflammation reaction     cytokine storm    

HTML PDF Collect

Attention-based encoder-decoder model for answer selection in question answering Article

Yuan-ping NIE, Yi HAN, Jiu-ming HUANG, Bo JIAO, Ai-ping LI

Frontiers of Information Technology & Electronic Engineering 2017, Volume 18, Issue 4,   Pages 535-544 doi: 10.1631/FITEE.1601232

Abstract: In this paper, we introduce an attention-based deep learning model to address the answer selection taskOur model also uses a step attention mechanism which allows the question to focus on a certain part of

Keywords： Question answering     Answer selection     Attention     Deep learning    

HTML PDF Collect

NGAT: attention in breadth and depth exploration for semi-supervised graph representation learning Research Articles

Jianke HU, Yin ZHANG,yinzh@zju.edu.cn

Frontiers of Information Technology & Electronic Engineering 2022, Volume 23, Issue 3,   Pages 409-421 doi: 10.1631/FITEE.2000657

Abstract: Recently, graph neural networks (GNNs) have achieved remarkable performance in representation learning on graph-structured data. However, as the number of network layers increases, GNNs based on the neighborhood aggregation strategy deteriorate due to the problem of oversmoothing, which is the major bottleneck for applying GNNs to real-world graphs. Many efforts have been made to improve the process of feature information aggregation from directly connected nodes, i.e., breadth exploration. However, these models perform the best only in the case of three or fewer layers, and the performance drops rapidly for deep layers. To alleviate oversmoothing, we propose a nested graph network (NGAT), which can work in a semi-supervised manner. In addition to breadth exploration, a -layer NGAT uses a layer-wise aggregation strategy guided by the mechanism to selectively leverage feature information from the -order neighborhood, i.e., depth exploration. Even with a 10-layer or deeper architecture, NGAT can balance the need for preserving the locality (including root node features and the local structure) and aggregating the information from a large neighborhood. In a number of experiments on standard tasks, NGAT outperforms other novel models and achieves state-of-the-art performance.

Keywords： Graph learning     Semi-supervised learning     Node classification     Attention    

HTML PDF Collect

Efficient decoding self-attention for end-to-end speech synthesis Research Article

Wei ZHAO, Li XU

Frontiers of Information Technology & Electronic Engineering 2022, Volume 23, Issue 7,   Pages 1127-1138 doi: 10.1631/FITEE.2100501

Abstract: has been innovatively applied to text-to-speech (TTS) because of its parallel structure and superior strength in modeling sequential data. However, when used in with an autoregressive decoding scheme, its inference speed becomes relatively low due to the quadratic complexity in sequence length. This problem becomes particularly severe on devices without graphics processing units (GPUs). To alleviate the dilemma, we propose an (EDSA) module as an alternative. Combined with a dynamic programming decoding procedure, TTS model inference can be effectively accelerated to have a linear computation complexity. We conduct studies on Mandarin and English datasets and find that our proposed model with EDSA can achieve 720% and 50% higher inference speed on the central processing unit (CPU) and GPU respectively, with almost the same performance. Thus, this method may make the deployment of such models easier when there are limited GPU resources. In addition, our model may perform better than the baseline Transformer TTS on out-of-domain utterances.

Keywords： Efficient decoding     End-to-end     Self-attention     Speech synthesis    

HTML PDF Collect

Deep learning based water leakage detection for shield tunnel lining

Frontiers of Structural and Civil Engineering 2024, Volume 18, Issue 6,   Pages 887-898 doi: 10.1007/s11709-024-1071-5

Abstract: Our proposal includes a ConvNeXt-S backbone, deconvolutional-feature pyramid network (D-FPN), spatial attention

Keywords： water leakage detection     deep learning     deconvolutional-feature pyramid     spatial attention    

HTML PDF Collect

An Interpretable Light Attention–Convolution–Gate Recurrent Unit Architecture for the Highly Accurate Article

Yue Li, Ning Li, Jingzheng Ren, Weifeng Shen

Engineering 2024, Volume 39, Issue 8,   Pages 104-116 doi: 10.1016/j.eng.2024.07.009

Abstract: equip data-driven dynamic chemical process models with strong interpretability, we develop a light attentiongate recurrent unit (LACG) architecture with three sub-modules—a basic module, a brand-new light attentionincluding the feedforward neural network, convolution neural network, long short-term memory (LSTM), and attention-LSTMinteractions can be observed from the model parameters in comparison with the traditional interpretable model attention-LSTM

Keywords： Interpretable machine learning     Light attention–convolution–gate recurrent unit architecture     Process    

HTML PDF Collect

EDVAM: a 3D eye-tracking dataset for visual attention modeling in a virtual museum Research Article

Yunzhan ZHOU, Tian FENG, Shihui SHUAI, Xiangdong LI, Lingyun SUN, Henry Been-Lirn DUH,yunzhan.zhou@durham.ac.uk,t.feng@zju.edu.cn

Frontiers of Information Technology & Electronic Engineering 2022, Volume 23, Issue 1,   Pages 101-112 doi: 10.1631/FITEE.2000318

Abstract: Predicting facilitates an adaptive virtual museum environment and provides a context-aware and interactive user experience. Explorations toward development of a mechanism using eye-tracking data have so far been limited to 2D cases, and researchers are yet to approach this topic in a 3D virtual environment and from a spatiotemporal perspective. We present the first 3D Eye-tracking Dataset for modeling in a virtual Museum, known as the EDVAM. In addition, a model is devised and tested with the EDVAM to predict a user's subsequent from previous eye movements. This work provides a reference for modeling and context-aware interaction in the context of .

Keywords： Visual attention     Virtual museums     Eye-tracking datasets     Gaze detection     Deep learning    

HTML PDF Collect

Filter-cluster attention based recursive network for low-light enhancement Research Article

Zhixiong HUANG, Jinjiang LI, Zhen HUA, Linwei FAN,hzxcyanwind@163.com,lijinjiang@gmail.com-

Frontiers of Information Technology & Electronic Engineering 2023, Volume 24, Issue 7,   Pages 1028-1044 doi: 10.1631/FITEE.2200344

Abstract: FCA and self-attention are used to highlight the low-light regions and important channels of the feature

Keywords： Low-light enhancement     Filter-cluster attention     Dense connection pyramid     Recursive network    

HTML PDF Collect

A robust tensor watermarking algorithm for diffusion-tensor images Research Article

Chengmeng LIU, Zhi LI, Guomei WANG, Long ZHENG,62377400@qq.com,zhili@gzu.edu.cn,306252084@qq.com,zhenglong178@163.com

Frontiers of Information Technology & Electronic Engineering 2024, Volume 25, Issue 3,   Pages 384-397 doi: 10.1631/FITEE.2200628

Abstract: Watermarking algorithms that use convolution neural networks have exhibited good robustness in studies of deep learning networks. However, after embedding watermark signals by convolution, the feature fusion efficiency of convolution is relatively low; this can easily lead to distortion in the embedded image. When distortion occurs in medical images, especially in (DTIs), the clinical value of the DTI is lost. To address this issue, a for DTIs implemented by fusing convolution with a is proposed to ensure the robustness of the watermark and the consistency of sampling distance, which enhances the quality of the reconstructed image of the watermarked DTIs after embedding the watermark signals. In the watermark-embedding network, T1-weighted (T1w) images are used as prior knowledge. The correlation between T1w images and the original DTI is proposed to calculate the most significant features from the T1w images by using the mechanism. The maximum of the correlation is used as the most significant feature weight to improve the quality of the reconstructed DTI. In the watermark extraction network, the most significant watermark features from the watermarked DTI are adequately learned by the to robustly extract the watermark signals from the watermark features. Experimental results show that the average peak signal-to-noise ratio of the watermarked DTI reaches 50.47 dB, the diffusion characteristics such as mean diffusivity and fractional anisotropy remain unchanged, and the main axis deflection angle is close to 1. Our proposed algorithm can effectively protect the copyright of the DTI and barely affects the clinical diagnosis.

Keywords： Robust watermarking algorithm     Transformer     Image reconstruction     Diffusion tensor images     Soft attention     Hard attention     T1-weighted images    

HTML PDF Collect

Fast detection algorithm for cracks on tunnel linings based on deep semantic segmentation

Frontiers of Structural and Civil Engineering 2023, Volume 17, Issue 5,   Pages 732-744 doi: 10.1007/s11709-023-0965-y

Abstract: Finally, an efficient attention module that significantly improves the anti-interference ability of the

Keywords： tunnel engineering     crack segmentation     fast detection     DeepLabv3+     feature fusion     attention mechanism    

HTML PDF Collect

Title Author Date Type Operation

Prediction and cause investigation of ozone based on a double-stage attention mechanism recurrent neural

Journal Article

Hard-rock tunnel lithology identification using multi-scale dilated convolutional attention network based

Journal Article

Meter-scale variation within a single transect demands attention to taxon accumulation curves in riverine

Journal Article

Less attention paid to waterborne SARS-CoV-2 spreading in Beijing urban communities

Journal Article

Erratum to: Meter-scale variation within a single transect demands attention to taxon accumulation curves

Journal Article

Endothelial dysfunction in COVID-19 calls for immediate attention: the emerging roles of the endothelium

Weijian Hang, Chen Chen, Xin A. Zhang, Dao Wen Wang

Journal Article

Attention-based encoder-decoder model for answer selection in question answering

Yuan-ping NIE, Yi HAN, Jiu-ming HUANG, Bo JIAO, Ai-ping LI

Journal Article

NGAT: attention in breadth and depth exploration for semi-supervised graph representation learning

Jianke HU, Yin ZHANG,yinzh@zju.edu.cn

Journal Article

Efficient decoding self-attention for end-to-end speech synthesis

Wei ZHAO, Li XU

Journal Article

Deep learning based water leakage detection for shield tunnel lining

Journal Article

An Interpretable Light Attention–Convolution–Gate Recurrent Unit Architecture for the Highly Accurate

Yue Li, Ning Li, Jingzheng Ren, Weifeng Shen

Journal Article

EDVAM: a 3D eye-tracking dataset for visual attention modeling in a virtual museum

Yunzhan ZHOU, Tian FENG, Shihui SHUAI, Xiangdong LI, Lingyun SUN, Henry Been-Lirn DUH,yunzhan.zhou@durham.ac.uk,t.feng@zju.edu.cn

Journal Article

Filter-cluster attention based recursive network for low-light enhancement

Zhixiong HUANG, Jinjiang LI, Zhen HUA, Linwei FAN,hzxcyanwind@163.com,lijinjiang@gmail.com-

Journal Article

A robust tensor watermarking algorithm for diffusion-tensor images

Chengmeng LIU, Zhi LI, Guomei WANG, Long ZHENG,62377400@qq.com,zhili@gzu.edu.cn,306252084@qq.com,zhenglong178@163.com

Journal Article

Fast detection algorithm for cracks on tunnel linings based on deep semantic segmentation

Journal Article