检索结果-内蒙古大学图书馆

Interspeech Conference

作者： Radfar, Martin Mouchtaris, Athanasios Kunzmann, Siegfried Rastrow, Ariya Amazon Alexa Machine Learning Seattle WA 98109 USA

ISBN: (纸本)9781713836902

Spoken language understanding (SLU) systems translate voice input commands to semantics which are encoded as an intent and pairs of slot tags and values. Most current SLU systems deploy a cascade of two neural models where the first one maps the input audio to a transcript (ASR) and the second predicts the intent and slots from the transcript (NLU). In this paper, we introduce FANS, a new end-to-end SLU model that fuses an ASR audio encoder to a multi-task NLU decoder to infer the intent, slot tags, and slot values directly from a given input audio, obviating the need for transcription. FANS consists of a shared audio encoder and three decoders, two of which are seq-to-seq decoders that predict non null slot tags and slot values in parallel and in an auto-regressive manner. FANS neural encoder and decoders architectures are flexible which allows us to leverage different combinations of LSTM, self-attention, and attenders. Our experiments show compared to the state-of-the-art end-to-end SLU models, FANS reduces ICER and IRER errors relatively by 30% and 7%, respectively, when tested on an in-house SLU dataset and by 0.86% and 2% absolute when tested on a public SLU dataset.

关键词： Spoken language understanding (SLU) Automatic speech recognition (ASR) Natural language understanding (NLU) sequence-to-sequence neural transformer encoder-decoder intent-slot

来源：评论

学校读者我要写书评

暂无评论

Research on Image Description Generation Method Based on G-AoANet 22

Research on Image Description Generation Method Based on G-A...

引用

Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition

作者： Pingan Qiao Ruixue Shen Yuan Li Xi'an University of Posts and Telecommunications China

ISBN: (纸本)9781450396899

Most of the image description generation methods in the attention-based encoder-decoder framework extract local features from images. Despite the relatively high semantic level of local features, it still has two problems to be solved, one is object loss, where some important objects may be lost when generating image descriptions, and the other is prediction error, as an object may be identified in the wrong class. In this paper, a G-AoANet model is proposed to solve the above problems. The model uses an attention mechanism to combine global features with local features. In this way, our model can selectively focus on both object and contextual information, improving the quality of the generated descriptions. Experimental results show that the model improves the initially reported best CIDEr-D and SPICE scores on the MS COCO dataset by 9.3% and 5.1% respectively.

关键词： encoder-decoder Global attention Image description

来源：评论

学校读者我要写书评

暂无评论

Multi-scale Strategy Based 3D Dual-encoder Brain Tumor Segmentation Network with Attention Mechanism

Multi-scale Strategy Based 3D Dual-Encoder Brain Tumor Segme...

引用

IEEE International Conference on Bioinformatics and Biomedicine (IEEE BIBM)

作者： Zhu, Yazhou Pan, Xiang Zhu, Jing Li, Lihua Jiangnan Univ Sch Artificial Intelligence & Comp Sci Wuxi Jiangsu Peoples R China Hangzhou Dianzi Univ Coll Life Informat Sci & Instrument Engn Hangzhou Peoples R China

ISBN: (纸本)9781728162157

Magnetic resonance imaging (MRI) is a widely used diagnostic technique in the initial evaluation of patients with primary brain tumor. Automatic segmentation algorithms for brain tumor plays an important role in diagnosis of tumor subregions and treatments for patients. In this paper, we propose a novel 3D convolutional neural network for segmentation of brain tumor, which is based on the traditional encoder-decoder architecture and inspired by multi-scale strategy. The proposed network employs multi-scale strategy with the designed dual-encoder structure which can be considered as two scales streams to extract features from two scales inputs respectively. To integrate the output features from two scales encoders, a multiscale attention is model designed to weight and integrated the multi-scale features. Moreover, with the purpose of modeling long-range feature dependencies more efficiently, hidden features from different positions of stream are also fused and then utilized by attention mechanism in each scale encoder. To validate the performance of the proposed network, we conduct experiments on the brain tumor segmentation dataset BraTS2019 against several state-of-art methods. The results show that proposed method has the effective and competitive performance in brain tumor segmentation.

关键词： Brain tumor segmentation Multi-scale model Attention model Deep learning encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

Image Steganography Scheme Using Dilated Convolutional Network 12

Image Steganography Scheme Using Dilated Convolutional Netwo...

引用

12th International Conference on Information and Communication Systems (ICICS)

作者： Kich, Ismail Ameur, El Bachir Taouil, Youssef Benhfid, Amine Ibn Tofail Univ Fac Sci Comp Sci Res Lab Kenitra Morocco

ISBN: (纸本)9781665433518

Nowadays, Convolutional Neural Networks (CNN) have allowed us to solve many problems, difficult to solve with classical methods, in different fields of applications. The use of this technique in the field of modern steganography has improved the performance of steganographic schemes in terms of concealability and invisibility. In this article, we propose a system based on CNN in order to hide a color image in another color image of the same size. The proposed system is based on Auto-encoder network and U-net architecture. The network is subdivided into two sub-networks, the first is for the concealment of the image secret by the sender, the second is for its extraction by the receiver. The network is end to end trained to ensure the integrity of the concealment and extraction process. The tests were performed on challenging images dataset publicly available, such as ImageNet, LFW, PASCAL-VOC12. The results show that the proposed steganographic scheme can hide a color image in another one of the same sizes, i.e. a capacity of 24 bpp, with acceptable PSNR and SSIM values compared to other previous work.

关键词： Information security Image steganography Deep Neural Network CNN encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

Keyword-guided abstractive code summarization via incorporating structural and contextual information

引用

INFORMATION AND SOFTWARE TECHNOLOGY 2022年第0期150卷

作者： Cheng, Wuyan Hu, Po Wei, Shaozhi Mo, Ran Cent China Normal Univ Hubei Prov Key Lab Artificial Intelligence & Smart Wuhan Hubei Peoples R China Cent China Normal Univ Sch Comp Wuhan Hubei Peoples R China Cent China Normal Univ Natl Language Resources Monitoring & Res Ctr Netwo Wuhan Hubei Peoples R China

Context: Source code summarization is a crucial yet far from settled task for describing structured code snippets in natural language. High-quality code summaries could effectively facilitate program comprehension and software maintenance. A good code summary is supposed to have the following characteristics: complete information, correct meaning, and consistent description. In recent years, numerous approaches have been proposed for code summarization, but it is still very challenging for developers to automatically learn the complex semantics from the source code and generate complete, correct and consistent code summaries. Objective: In this paper, we propose KGCodeSum, a novel keyword-guided abstractive code summarization approach that incorporates structural and contextual ***: To improve summaries' quality, we leverage both the structural information embedded in code itself and the contextual information from related code snippets. Meanwhile, we make use of keywords to guide summaries' generation to guarantee the code summaries contain key information. Finally, we propose a new dynamic vocabulary strategy which can effectively resolve the UNK problems in code ***: Through our evaluation on the large-scale benchmark datasets with 2.1 million java method-comment pairs and 1.1 million C/C++ function-summary pairs, We have observed that our approach could generate better code summaries than existing state-of-the-art approaches in terms of completeness, correctness and consistency. In addition, we also find that incorporating the dynamic vocabulary strategy into our approach could significantly save time and space in the model training ***: Our KGCodeSum approach could effectively generate code summaries.

关键词： Source code summarization encoder-decoder Information incorporation Dynamic vocabulary Deep learning

来源：评论

学校读者我要写书评

暂无评论

Translating medical image to radiological report: Adaptive multilevel multi-attention approach

引用

COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2022年 221卷 106853-106853页

作者： Gajbhiye, Gaurav O. V. Nandedkar, Abhijeet Faye, Ibrahima SGGS Inst Engn & Technol CVPR Lab Nanded India Univ Teknol PETRONAS CISIR Seri Iskandar Malaysia

Acknowledgment This research work was supported by joint collaboration of Computer Vision and Pattern Vision (CVPR) Lab, Shri Guru Gobind Singhji Institute of Engineering and Technology, Nanded, India and Center for Intelligent Signal and Imaging Research (CISIR), Universiti Teknologi PETRONAS (UTP), Seri Iskandar, Malaysia under International Grant 015ME0-018.

关键词： Radiology report generation X-ray encoder-decoder Residual attention module Multilevel multi-attention mechanism Radiology-trained word embedding

来源：评论

学校读者我要写书评

暂无评论

Radar Echo Image Prediction Algorithm Based on Multi-scale Encoding-Decoding Network 22nd

Radar Echo Image Prediction Algorithm Based on Multi-scale E...

引用

22nd International Conference on Intelligent Data Engineering and Automated Learning

作者： Mou, Xingang Liu, Chang Zhou, Xiao Wuhan Univ Technol Mech & Elect Engn Wuhan Peoples R China

ISBN: (纸本)9783030916077;9783030916084

The traditional technology of radar echo image extrapolation for rainfall nowcasting faces such problems as insufficiently high accuracy, the incomplete analysis of the data on radar echo images, and the image blurring from the stacked LSTM(Long Short-Term Memory). In order to more accurately and clearly predict the radar echo image at a future moment, an adversarial prediction network based on multi-scale U-shaped encoder-decoder is proposed. To overcome the problem of insufficient details of the predicted image, the generator of the network adopts a U-shaped encoder-decoder structure with jump-layer connection. At the same time, in order to capture the echo movement at different scales, multi-scale convolution kernels is introduced to the encoder-decoder units. Then the conventional discriminator structure is improved and stacked ConvLSTM(Convolutional Long Short-Term Memory) layers were proposed to classify sequence. Based on the prediction of next ten frames from the given ten frames of images, this paper tests the network on the SRAD(Standardized Radar Dataset), and compares the prediction results of different networks. The test results show that the proposed model reduces image blurring, enhances the prediction accuracy while retaining sufficient prediction details.

关键词： encoder-decoder Multi-scale Prediction Rainfall nowcasting

来源：评论

学校读者我要写书评

暂无评论

面向稠密NRSfM的神经网络模型的研究

面向稠密NRSfM的神经网络模型的研究

引用

作者：王敏洁浙江理工大学

学位级别：硕士

稠密非刚性运动恢复结构用于对具有非刚性运动的物体进行精确的三维重建,是非刚性运动恢复结构(Non-rigid Structure from Motion,NRSf M)的一个特殊分支。与标准的NRSf M算法相比,稠密NRSf M可以在更高的精度下还原非刚性物体的形状和... 详细信息

稠密非刚性运动恢复结构用于对具有非刚性运动的物体进行精确的三维重建,是非刚性运动恢复结构(Non-rigid Structure from Motion,NRSf M)的一个特殊分支。与标准的NRSf M算法相比,稠密NRSf M可以在更高的精度下还原非刚性物体的形状和表面细节,并生成更为精细的三维模型,因此在计算机视觉和真实世界应用等方面具有重要的研究意义。然而,由于稠密NRSf M在解决问题时需要处理大规模的、具有非刚性结构的图像数据,且对精度和效率具有极高的要求,故研究进展相对缓慢。2020年,神经网络技术第一次被应用于稠密NRSf M领域,并取得了优于传统方法的性能,因此开始受到关注。但现存基于神经网络的稠密NRSf M方案多适用于半稠密数据集,且由于该研究兴起不久,神经网络技术在稠密NRSf M领域并没有得到充分的研究与应用。因此,本文开展了以下两方面的研究工作:(1)受到基于模板的三维重建(Shape from Template,Sf T)方法启发,本文将传统刚性运动恢复结构(Rigid Structure from Motion,RSf M)方法与神经网络技术相结合,提出基于自建模板的稠密NRSf M神经网络模型(T-NRSf M)。该模型首先采用刚性因式分解方法获得重建对象的稠密三维模板,再使用神经网络技术拟合目标物体的形变特征,从而实现稠密非刚性物体的三维重建。其中,为防止重建效果过于依赖初始模板质量,引入Auto encoder架构在网络训练过程中对模板进行微调。此外,由于神经网络技术在重建形变特征时,所需参数数量与重建对象形变复杂度密切相关,本文引入Res Net结构适当调节网络的参数数量,以提高网络对非刚性物体复杂形变的拟合能力,并避免由于网络加深加宽而带来的梯度消失和收敛缓慢等问题。实验结果表明,与大多数竞争算法相比,T-NRSf M在重建精度方面表现更优,并具有良好的鲁棒性。(2)针对现有的基于神经网络的稠密NRSf M方法忽略了时空数据的重要性,以及引入传统RSf M算法限制了神经网络模型重建具有较大形变的物体的能力等缺点,本文采用encoder-decoder架构设计了一个端到端的深度时空稠密NRSf M网络模型(DST-NRSf M),并引入新型的加权空间约束进一步优化三维重建结果。此外,本文巧妙地将层归一化引入到稠密NRSf M任务中,以解决梯度消失问题,并加速神经网络的收敛速度。实验结果表明,无论是在常用的合成数据集上还是真实的基准数据集上,DST-NRSf M模型均体现出了最先进的性能,且在重建形变较大的目标时,表现依旧优异。综上,针对神经网络技术在稠密NRSf M领域尚未得到充分研究与应用的现状,本文从不同的重建思路出发,提出了两个面向稠密NRSf M的神经网络模型。实验结果表明,相比于现有算法,本文提出的两个模型均可实现更高精度的稠密非刚体三维重建。

关键词：稠密NRSfM 自建模板 ResNet encoder-decoder 加权空间约束

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

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

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：