检索结果-内蒙古大学图书馆

VATEX2020: pLSTM framework for video captioning

Procedia Computer Science 2023年 218卷 1229-1237页

作者： Alok Singh Salam Michael Singh Loitongbam Sanayai Meetei Ringki Das Thoudam Doren Singh Sivaji Bandyopadhyay

Captioning a video involves condensing the video's information into text, which can be useful in video sentiment analysis, video-guided machine translation (VMT), visual question-answering and humanitarian aid. This paper discusses the details of the architecture of the pLSTM framework that is employed for the VATEX-2020 video captioning challenge. In this work, a sequential method is employed wherein to encode visual features a 3D convolutional neural network (C3D) is used. C3D was pretrained using the Sports-1M dataset. In the decoding phase, the input captions and visual features are fused separately in Long Short Term Memory networks (LSTM). The element-wise dot product is performed on the output of both LSTMs to get the final output. On both publicly available and private test data sets, our model achieves BLEU-4 scores of 0.20 and 0.22, respectively.

关键词： Video captioning 3D CNN encoder-decoder VATEX LSTM C3D

来源：评论

学校读者我要写书评

暂无评论

Multi-Path U-Net Architecture for Cell and Colony-Forming Unit Image Segmentation

引用

SENSORS 2022年第3期22卷 990-990页

作者： Jumutc, Vilen Bliznuks, Dmitrijs Lihachev, Alexey Riga Tech Univ Inst Smart Comp Technol LV-1658 Riga Latvia Univ Latvia Inst Atom Phys & Spect LV-1586 Riga Latvia

U-Net is the most cited and widely-used deep learning model for biomedical image segmentation. In this paper, we propose a new enhanced version of a ubiquitous U-Net architecture, which improves upon the original one in terms of generalization capabilities, while addressing several immanent shortcomings, such as constrained resolution and non-resilient receptive fields of the main pathway. Our novel multi-path architecture introduces a notion of an individual receptive field pathway, which is merged with other pathways at the bottom-most layer by concatenation and subsequent application of Layer Normalization and Spatial Dropout, which can improve generalization performance for small datasets. In general, our experiments show that the proposed multi-path architecture outperforms other state-of-the-art approaches that embark on similar ideas of pyramid structures, skip-connections, and encoder-decoder pathways. A significant improvement of the Dice similarity coefficient is attained at our proprietary colony-forming unit dataset, where a score of 0.809 was achieved for the foreground class.

关键词： U-Net skip-connections neural network encoder-decoder Layer Normalization

来源：评论

学校读者我要写书评

暂无评论

Segment boundary detection directed attention for online end-to-end speech recognition

引用

EURASIP JOURNAL ON AUDIO SPEECH AND MUSIC PROCESSING 2020年第1期2020卷 3-3页

作者： Hou, Junfeng Guo, Wu Song, Yan Dai, Li-Rong Univ Sci & Technol China Natl Engn Lab Speech & Language Informat Proc Hefei 230022 Peoples R China

Attention-based encoder-decoder models have recently shown competitive performance for automatic speech recognition (ASR) compared to conventional ASR systems. However, how to employ attention models for online speech recognition still needs to be explored. Different from conventional attention models wherein the soft alignment is obtained by a pass over the entire input sequence, attention models for online recognition must learn online alignment to attend part of input sequence monotonically when generating output symbols. Based on the fact that every output symbol is corresponding to a segment of input sequence, we propose a new attention mechanism for learning online alignment by decomposing the conventional alignment into two parts: segmentation-segment boundary detection with hard decision-and segment-directed attention-information aggregation within the segment with soft attention. The boundary detection is conducted along the time axis from left to right, and a decision is made for each input frame about whether it is a segment boundary or not. When a boundary is detected, the decoder generates an output symbol by attending the inputs within the corresponding segment. With the proposed attention mechanism, online speech recognition can be realized. The experimental results on TIMIT and WSJ dataset show that our proposed attention mechanism achieves comparable online performance with state-of-the-art models.

关键词： encoder-decoder Online recognition Boundary detection Attention mechanism Reinforcement learning Policy gradient

来源：评论

学校读者我要写书评

暂无评论

Pixel Voting decoder: A novel decoder that regresses pixel relationships for segmentation

引用

EXPERT SYSTEMS WITH APPLICATIONS 2022年第0期193卷 116438-116438页

作者： Xian, Pengfei Po, Lai-Man Xiong, Jingjing Zhou, Chang Zhao, Yuzhi Yu, Wing-Yin Ou, Weifeng Zhang, Yujia Zhang, Xiaori City Univ Hong Kong Hong Kong Peoples R China Fudan Univ Shanghai Peoples R China

With the rapid development of the convolutional neural network, both instance segmentation and semantic segmentation have achieved remarkable performances. Recently, many efforts have been made to use a unified encoder-decoder architecture to solve these two segmentation tasks simultaneously. The encoder extracts high-level features from the input images for both tasks. However, existing decoders cannot meet the performance requirements of these two tasks: the semantic segmentation decoder is not flexible enough for instance segmentation, and the instance segmentation decoder lacks the precision of semantic segmentation. Therefore, we introduce a novel Pixel Voting decoder to satisfy both precision and flexibility. The proposed decoder regresses the interlayer pixel relationships between the input and output feature maps across the convolutional layers. Then, the pixel relationships are regarded as the pixel votes for dynamically decoding the higher level information from the encoder. Finally, we propose the dynamic deconvolution to make full use of the votes for each pixel during the decoding process. Meanwhile, the matrix computation for the dynamic deconvolution is designed to boost the calculation. Experiments show that the proposed method can achieve better performance than the well-known methods on both instance segmentation on the COCO dataset and semantic segmentation on the Cityscapes dataset. The matrix implementation of the dynamic deconvolution also shows its high efficiency and feasibility.

关键词： Convolutional neural network Dynamic deconvolution encoder-decoder Image segmentation Pixel voting Residual block

来源：评论

学校读者我要写书评

暂无评论

A traffic-weather generative adversarial network for traffic flow prediction for road networks under bad weather

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2024年 137卷

作者： Zhang, Wensong Yao, Ronghan Yuan, Ying Du, Xiaojing Wang, Libing Sun, Feng Hebei GEO Univ Sch Urban Geol & Engn Shijiazhuang Peoples R China Minist Nat Resources Key Lab Intelligent Detect & Equipment Underground Shijiazhuang Peoples R China Hebei Technol Innovat Ctr Intelligent Dev & Contro Shijiazhuang Peoples R China Shandong Univ Technol Sch Transportat & Vehicle Engn Zibo Peoples R China Dalian Univ Technol Sch Transportat & Logist Dalian Peoples R China

Traffic flow prediction is pivotal in providing reliable information for intelligent traffic systems. Unexpected events, such as bad weather, unavoidably impact the precision of traffic flow prediction. Therefore, to achieve accurate traffic flow prediction results in road networks under bad weather, a novel Traffic-Weather Generative Adversarial Network (TWeather-GAN model) is developed. This model comprises a Generator and a Discriminator. The Generator incorporates both the traffic and weather modules to extract the spatiotemporal patterns hidden in traffic flow and weather data. In the traffic and weather modules, the gated convolutional layer, encoder-decoder architecture, and attention mechanism are established. In the Discriminator, the gated convolutional layer and bidirectional long short-term memory neural network are introduced. Traffic flow data under fog, strong wind, and heavy rain are selected to test the seven baseline models and the proposed model, and the ablation experiments are conducted to analyze the mechanism of the proposed model. The experiments demonstrate that the TWeather-GAN model outperforms the baseline models under bad weather, and makes the prediction error have an average reduction of 0.20%-34.81%, 3.21%-35.22%, and 9.46%-39.10%, respectively, under one-step prediction, three-step prediction, and six-step prediction. Furthermore, establishing the gated convolutional layer and the weather module enhances the accuracy of traffic flow prediction under bad weather. Results show that traffic flow fluctuations and distributions differ under fog and strong wind, and heavy rain affects the trend of traffic flow over one day.

关键词： Traffic flow prediction Generative adversarial network Bad weather encoder-decoder Gated convolutional layer Bidirectional long short-term memory neural network

来源：评论

学校读者我要写书评

暂无评论

On the role of the architecture for spring discharge prediction with deep learning approaches

引用

HYDROLOGICAL PROCESSES 2022年第10期36卷 e14737-e14737页

作者： Zhou, Renjie Zhang, Yanyan Sam Houston State Univ Dept Environm & Geosci Huntsville TX 77340 USA Texas A&M Univ Dept Elect & Comp Engn College Stn TX 77840 USA

Understanding karst spring flow is important to accommodate the increasing water demand caused by the population growth and manage the freshwater water resource effectively. However, due to the spatial and temporal heterogeneity and complex hydrological processes in karst systems, predicting karst spring discharge remains challenging. In this study, three deep learning-based models, including long short-term memory (LSTM), gated recurrent unit (GRU) and simple recurrent neural network (RNN), are framed with an encoder-decoder architecture to provide multiple-step-ahead spring discharge prediction. The encoder-decoder architecture includes an encoder that reads and encodes the input sequence into a vector and decoder that deciphers the vector and outputs the predicted sequence. Three hybrid models called LSTM-ED, GRU-ED and simple RNN-ED are compared with single-step models and multiple-step models without the encoder-decoder architecture to investigate the role of the encoder-decoder architecture on multi-step-ahead prediction. The sensitivity of the selection of input time and lead time steps on the karst spring discharge prediction is evaluated. The predicted results are compared with the observed spring discharge. It implies that: (1) LSTM-ED, GRU-ED and RNN-ED models obtain similar results on predicting karst spring discharge multiple time steps ahead;(2) three hybrid multiple-step models outperform the single-step models in making consistent and accurate spring discharge predictions;(3) the multiple-step models framed with an encoder-decoder architecture obtain better spring discharge prediction results than the single-step models and multiple-step models without the encoder-decoder structure;(4) the LSTM-ED, GRU-ED and simple RNN-ED models are sensitive to the selection of lead time and insensitive to the selection of input time step. A short lead time typically yields a more accurate spring discharge prediction.

关键词： encoder-decoder GRU karst LSTM RNN sequence-to-sequence spring discharge

来源：评论

学校读者我要写书评

暂无评论

MSLEFC: A low-frequency focused underwater acoustic signal classification and analysis system

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2023年第PartB期123卷

作者： Zhang, Yunqi Zeng, Qunfeng Xi An Jiao Tong Univ Key Lab Educ Minist Modern Design & Rotor Bearing Xian 710049 Peoples R China

Many feature extraction techniques are employed to study the classification of underwater acoustic, however, most of these techniques result in the loss of detailed information in this field. A Multi-scale short-time Fourier transform (MS-STFT) method was proposed to improve the low-frequency information and maintain the detailed information by increasing the number of channels. An effective data augmentation approach was proposed and a Ladder-like Encode (LE) architecture was built to increase the generalizability of the model and the classification accuracy for the features extracted. Finally, A Frequency-CAM (FC) method is proposed to analyze the frequency band locations that the neural network is interested in when conducting classification tasks on various classes of data. The integration of the above technologies is called MSLEFC. The performance of this system has been tested on two ship radiation noise datasets and obtained 82.94% and 96.06% accuracy, respectively. On the ShipsEar dataset, the proposed method increases the accuracy by 0.7% over the previous state-of-the-art method. The proposed model architecture has significant improvements in parameter size and computation compared to ResNet50.

关键词： Underwater acoustics encoder-decoder Multi-scale short-time fourier transform Frequency-CAM

来源：评论

学校读者我要写书评

暂无评论

MiniCrack: A simple but efficient convolutional neural network for pixel-level narrow crack detection

引用

COMPUTERS IN INDUSTRY 2022年 141卷

作者： Lan, Zhi-Xiong Dong, Xue-Mei Zhejiang Gongshang Univ Sch Stat & Math Hangzhou 310018 Peoples R China Zhejiang Gongshang Univ Collaborat Innovat Ctr Stat Data Engn Technol & Ap Hangzhou 310018 Peoples R China

With the advancement of deep learning, the newly proposed neural networks are growing increasingly complicated to achieve great performance. In this context, we propose a simple but effective neural network called MiniCrack for narrow crack detection. We also propose a lightweight version, MiniCrack-Light, to adapt to scenarios with limited computing resources. MiniCrack and MiniCrack-Light outperform the current state-of-the-art neural networks on all three challenging testing data sets with fewer parameters and achieving stronger robustness. PixelShuffle and PixelUnshuffle designed for image super-resolution are successfully used to the field of image segmentation, which effectively alleviates the problems caused by pooling.

关键词： Convolutional neural network encoder-decoder Narrow crack detection PixelShuffle PixelUnshuffle

来源：评论

学校读者我要写书评

暂无评论

Rethinking 1D convolution for lightweight semantic segmentation

引用

FRONTIERS IN NEUROROBOTICS 2023年 17卷 1119231页

作者： Zhang, Chunyu Xu, Fang Wu, Chengdong Xu, Chenglong Northeastern Univ Fac Robot Sci & Engn Shenyang Peoples R China Shenyang Siasun Robot & Automat Co Ltd Shenyang Peoples R China Harbin Engn Univ Coll Intelligent Syst Sci & Engn Harbin Peoples R China

Lightweight semantic segmentation promotes the application of semantic segmentation in tiny devices. The existing lightweight semantic segmentation network (LSNet) has the problems of low precision and a large number of parameters. In response to the above problems, we designed a full 1D convolutional LSNet. The tremendous success of this network is attributed to the following three modules: 1D multi-layer space module (1D-MS), 1D multi-layer channel module (1D-MC), and flow alignment module (FA). The 1D-MS and the 1D-MC add global feature extraction operations based on the multi-layer perceptron (MLP) idea. This module uses 1D convolutional coding, which is more flexible than MLP. It increases the global information operation, improving features' coding ability. The FA module fuses high-level and low-level semantic information, which solves the problem of precision loss caused by the misalignment of features. We designed a 1D-mixer encoder based on the transformer structure. It performed fusion encoding of the feature space information extracted by the 1D-MS module and the channel information extracted by the 1D-MC module. 1D-mixer obtains high-quality encoded features with very few parameters, which is the key to the network's success. The attention pyramid with FA (AP-FA) uses an AP to decode features and adds a FA module to solve the problem of feature misalignment. Our network requires no pre-training and only needs a 1080Ti GPU for training. It achieved 72.6 mIoU and 95.6 FPS on the Cityscapes dataset and 70.5 mIoU and 122 FPS on the CamVid dataset. We ported the network trained on the ADE2K dataset to mobile devices, and the latency of 224 ms proves the application value of the network on mobile devices. The results on the three datasets prove that the network generalization ability we designed is powerful. Compared to state-of-the-art lightweight semantic segmentation algorithms, our designed network achieves the best balance between segmentation accuracy an

关键词： semantic segmentation lightweight network 1D convolution encoder-decoder feature alignment

来源：评论

学校读者我要写书评

暂无评论

ERV-Net: An efficient 3D residual neural network for brain tumor segmentation

引用

EXPERT SYSTEMS WITH APPLICATIONS 2021年 170卷 114566-114566页

作者： Zhou, Xinyu Li, Xuanya Hu, Kai Zhang, Yuan Chen, Zhineng Gao, Xieping Xiangtan Univ Minist Educ Key Lab Intelligent Comp & Informat Proc Xiangtan 411105 Peoples R China Baidu Inc Beijing 100085 Peoples R China Chinese Acad Sci Inst Automat Beijing 100190 Peoples R China Xiangnan Univ Coll Med Imaging & Inspect Chenzhou Peoples R China

Brain tumors are the most aggressive and mortal cancers, which lead to short life expectancy. A reliable and efficient automatic or semi-automatic segmentation method is significant for clinical practice. In recent years, deep learning-based methods achieve great success in brain tumor segmentation. However, due to the limitation of parameters and computational complexity, there is still much room for improvement in these methods. In this paper, we propose an efficient 3D residual neural network (ERV-Net) for brain tumor segmentation, which has less computational complexity and GPU memory consumption. In ERV-Net, a computation-efficient network, 3D ShuffleNetV2, is firstly utilized as encoder to reduce GPU memory and improve the efficiency of ERV-Net, and then the decoder with residual blocks (Res-decoder) is introduced to avoid degradation. Furthermore, a fusion loss function, which is composed of Dice loss and Cross-entropy loss, is developed to solve the problems of network convergence and data imbalance. Moreover, a concise and effective post-processing method is proposed to refine the coarse segmentation result of ERV-Net. The experimental results on the dataset of multimodal brain tumor segmentation challenge 2018 (BRATS 2018) demonstrate that ERV-Net achieves the best performance with Dice of 81.8%, 91.21% and 86.62% and Hausdorff distance of 2.70 mm, 3.88 mm and 6.79 mm for enhancing tumor, whole tumor and tumor core, respectively. Besides, ERV-Net also achieves high efficiency compared to the state-of-the-art methods.

关键词： Brain tumor segmentation 3D convolutional neural network encoder-decoder Efficiency Lightweight Residual block

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：