检索结果-内蒙古大学图书馆

Modeling social interaction and intention for pedestrian trajectory prediction

PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS 2021年 570卷 125790-125790页

作者： Chen, Kai Song, Xiao Ren, Xiaoxiang Beihang Univ BUAA Beijing Peoples R China Nanan Primary Sch Nanan Shanxi Peoples R China

Future pedestrian trajectory prediction offers great prospects for many practical applications. Most existing methods focus on social interaction among pedestrians but ignore the fact that in addition to pedestrians there are other kinds of objects (cars, dogs, bicycles, motorcycles, etc.) with a great influence on the subject pedestrian's future trajectory. Most existing methods neglect the intentions of the pedestrian, which can be obtained by the key points of the subject pedestrian's face. Therefore, rich category information about the subject pedestrian's surroundings and face key points plays a great role in promoting the modeling of pedestrian movement. Motivated by this idea, this paper tries to predict a pedestrian's future trajectory by jointly using various categories and the relative positions of the subject pedestrian's surroundings and the key points in his face. We propose a data modeling method to effectively unify rich visual features about categories, interaction and face key points into a multi-channel tensor and build an end-to-end fully convolutional encoder-decoder attention model based on convolutional long-short-term memory utilizing this tensor. We evaluate and compare our method with several existing methods on 5 crowded video sequences from the public dataset multi-object tracking (MOT)-16. Experimental results show that our method outperforms state-of-the-art approaches, with less prediction error. (C) 2021 Elsevier B.V. All rights reserved.

关键词： Social-interaction Pedestrian intention Convolutional long-short-term memory encoder-decoder Attention

来源：评论

学校读者我要写书评

暂无评论

基于Attention模型的法律文书生成研究

引用

无线互联科技 2023年第1期20卷 111-115,129页

作者：徐惠苏同俞鹏飞江全胜朱咸军南京航空航天大学江苏南京210016 金陵科技学院江苏南京211169 东部战区总医院江苏南京210002 江苏省信息分析工程研究中心江苏南京211169

法律文书的自动生成可以有效缓解法律服务行业中人力资源不足的问题,让用户足不出户就可方便享受到法律咨询服务。适用于法律文书的自动生成技术的研究,在减轻法律工作者文书工作上和普通人叙述法律案件时更规范地描述法律内容具有重要... 详细信息

法律文书的自动生成可以有效缓解法律服务行业中人力资源不足的问题,让用户足不出户就可方便享受到法律咨询服务。适用于法律文书的自动生成技术的研究,在减轻法律工作者文书工作上和普通人叙述法律案件时更规范地描述法律内容具有重要的现实意义。文章提出一种筛选案件要素信息,在encoder-decoder模型中加入注意力机制的Attention模型,最终生成合格的法律文书。实验表明,该模型优化了LSTM模型对长文本的记忆效果,能够较好地完成生成法律文书任务。

关键词：法律文书 LSTM encoder-decoder Attention模型

来源：评论

学校读者我要写书评

暂无评论

Evolution of machine learning in environmental science-A perspective

引用

ENVIRONMENTAL DATA SCIENCE 2022年 1卷 e3-e3页

作者： Hsieh, William W. Univ British Columbia Dept Earth Ocean & Atmospher Sci Vancouver BC V6T IZ4 Canada 4028 Hopesmore Dr Victoria BC V8N 5S9 Canada

The growth of machine learning (ML) in environmental science can be divided into a slow phase lasting till the mid-2010s and a fast phase thereafter. The rapid transition was brought about by the emergence of powerful new ML methods, allowing ML to successfully tackle many problems where numerical models and statistical models have been hampered. Deep convolutional neural network models greatly advanced the use of ML on 2D or 3D data. Transfer learning has allowed ML to progress in climate science, where data records are generally short for ML. ML and physics are also merging in new areas, for example: (a) using ML for general circulation model parametrization, (b) adding physics constraints in ML models, and (c) using ML in data assimilation. Impact Statement This perspective paper reviews the evolution and growth of machine learning (ML) models in environmental science. The opaque nature of ML models led to decades of slow growth, but exponential growth commenced around the mid-2010s. Novel ML models which have contributed to this exponential growth (e.g., deep convolutional neural networks, encoder-decoder networks, and generative-adversarial networks) are reviewed, as well as approaches to merging ML models with physics-based models.

关键词： Data assimilation encoder-decoder generative-adversarial network machine learning neural network

来源：评论

学校读者我要写书评

暂无评论

Attention-shift based deep neural network for fine-grained visual categorization

引用

PATTERN RECOGNITION 2021年 116卷 107947-107947页

作者： Niu, Yi Jiao, Yang Shi, Guangming Xidian Univ Sch Elect Engn 2 Taibai South Rd Xian Shaanxi Peoples R China Xidian Univ Sch Artificial Intelligence 2 Taibai South Rd Xian Shaanxi Peoples R China

Fine-grained visual categorization (FGVC) has attracted extensive attention in recent years. The general pipeline of current FGVC techniques is to 1) locate the discriminative regions;2) extract features from each region independently;and 3) feed the integrated features to a classifier. In this paper, we reinvestigate the pipeline from the view of human visual recognition mechanisms. The perceiving of discriminative regions is a temporal processing by the human visual system (HVS) via the attention-shift mechanism. However, the existing independent feature extracting and one-pass feeding strategy ignore the inherent semantic relationships among discriminative regions, and thus is improper to model the attention-shift process properly. Therefore, in this paper, we propose a novel end-to-end FGVC network structure named Attention-Shift based Deep Neural Network (AS-DNN) to locate the discriminative regions automatically and encode the semantic correlations iteratively. AS-DNN consists of two channels: 1) the global perception channel C-glb and 2) the attention-shift channel C-sft, simulating the global perception and the attention-shift mechanism, respectively. Experimental results show that AS-DNN achieves state-of-the-art performances by outperforming both the CNN-based weakly or strongly-supervised FGVC algorithms on several widely-used fine-grained datasets, and the visualization of attention regions exhibit that the proposed method can locate the discriminative regions robustly in complex backgrounds and postures. (C) 2021 Elsevier Ltd. All rights reserved.

关键词： Fine-grained visual categorization Deep neural network Human perception mechanism Attention-shift encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

A Deep Sequence-to-Sequence Method for Aircraft Landing Speed Prediction Based on QAR Data 21st

A Deep Sequence-to-Sequence Method for Aircraft Landing Spee...

引用

21st International Conference on Web Information Systems Engineering (WISE)

作者： Kang, Zongwei Shang, Jiaxing Feng, Yong Zheng, Linjiang Liu, Dajiang Qiang, Baohua Wei, Ran Chongqing Univ Coll Comp Sci Chongqing Peoples R China Chongqing Univ Key Lab Dependable Serv Comp Cyber Phys Soc Minist Educ Chongqing Peoples R China Guilin Univ Elect Technol Guangxi Key Lab Optoelect Informat Proc Guilin Peoples R China Guilin Univ Elect Technol Guangxi Key Lab Trusted Software Guilin Peoples R China Chongqing Med Data Informat Technol Co Ltd Chongqing Peoples R China

ISBN: (纸本)9783030620080;9783030620073

Runway overrun is one of the most typical landing incidents highly concerned by airlines in the aviation industry. Previous studies have shown that high landing speed is closely related to runway overrun risks, therefore the study of landing speed prediction based on flight data has drawn attention of many scholars in recent years. However, existing methods are mainly based on traditional machine learning models and handcrafted features, which not only rely heavily on flight experts' priori knowledge, but also provide unsatisfactory prediction accuracy. To solve this problem, in this paper we propose an innovative deep encoder-decoder model for aircraft landing speed prediction based on Quick Access Recorder (QAR) data. Specifically, we first preprocess the QAR dataset through a data cleaning, Lagrange interpolation and normalization procedure. Second, based on the preprocessed QAR dataset, we use gradient boosting decision trees to select features which are most closely related to landing speed. Finally, we employ the LSTM encoder-decoder architecture where the encoder captures the pattern underlying in the past sequences while the decoder generates predictions for the future speed sequences. We evaluate our method on a dataset of 44,176 A321 flight samples. The experimental results show that the prediction accuracy of the proposed method is significantly higher than the conventional methods.

关键词： QAR data Landing speed prediction encoder-decoder Long short-term memory GBDT

来源：评论

学校读者我要写书评

暂无评论

Leveraging Linguistically-aware Object Relations and NASNet for Image Captioning 35

Leveraging Linguistically-aware Object Relations and NASNet ...

引用

35th International Conference on Image and Vision Computing New Zealand (IVCNZ)

作者： Sharif, Naeha Jalwana, Mohammad A. A. K. Bennamoun, Mohammed Liu, Wei Shah, Syed Afaq Ali Univ Western Australia Perth WA Australia Murdoch Univ Perth WA Australia

ISBN: (纸本)9781728185798

Image captioning is a challenging vision-to-language task, which has garnered a lot of attention over the past decade. The introduction of encoder-decoder based architectures expedited the research in this area and provided the backbone of the most recent systems. Moreover, leveraging relationships between objects for holistic scene understanding, which in turn improves captioning, has recently sparked interest among researchers. Our proposed model encodes the spatial and semantic proximity of object pairs into linguistically-aware relationship embeddings. Moreover, it captures the global semantics of the image using NASNet. This way, true semantic relations that are not apparent in visual content of an image can be learned, such that the decoder can attend to the most relevant object relations and visual features to generate more semantically-meaningful captions. Our experiments highlight the usefulness of linguistically-aware object relations as well as NASNet visual features for image captioning.

关键词： Image Captioning encoder-decoder Linguistically-aware object relationships NASNet

来源：评论

学校读者我要写书评

暂无评论

Sequence-level self-learning with multiple hypotheses 21

Sequence-level self-learning with multiple hypotheses

引用

Interspeech Conference

作者： Kumatani, Kenichi Dimitriadis, Dimitrios Gaur, Yashesh Gmyr, Robert Eskimez, Sefik Emre Li, Jinyu Zeng, Michael Microsoft Redmond WA 98052 USA

ISBN: (纸本)9781713820697

In this work, we develop new self-learning techniques with an attention-based sequence-to-sequence (seq2seq) model for automatic speech recognition (ASR). For untranscribed speech data, the hypothesis from an ASR system must be used as a label. However, the imperfect ASR result makes unsupervised learning difficult to consistently improve recognition performance especially in the case that multiple powerful teacher models are unavailable. In contrast to conventional unsupervised learning approaches, we adopt the multi-task learning (MTL) framework where the n-th best ASR hypothesis is used as the label of each task. The seq2seq network is updated through the MTL framework so as to find the common representation that can cover multiple hypotheses. By doing so, the effect of the hard-decision errors can be alleviated. We first demonstrate the effectiveness of our self-learning methods through ASR experiments in an accent adaptation task between the US and British English speech. Our experiment results show that our method can reduce the WER on the British speech data from 14.55% to 10.36% compared to the baseline model trained with the US English data only. Moreover, we investigate the effect of our proposed methods in a federated learning scenario.

关键词： unsupervised learning self-learning encoder-decoder multi-task learning end-to-end acoustic modeling

来源：评论

学校读者我要写书评

暂无评论

Denoising of Magnetic Resonance Images with Deep Neural Regularizer Driven by Image Prior 7

Denoising of Magnetic Resonance Images with Deep Neural Regu...

引用

7th IEEE International Conference on Data Science and Advanced Analytics (DSAA)

作者： Zhu, Yazhou Pan, Xiang Zhu, Jing Li, Lihua Liu, Yuan 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)9781728182063

Magnetic resonance imaging (MRI) is an important medical diagnosis technique in clinical diagnosis, while the quality of MR images is always damaged by the noise which is caused in the image acquisition process. In the classic image denoising methods, how to design an excellent regularizer with the prior knowledge of image is the key to solve the denoising problem. In this work, we introduce the deep neural regularizer for the MRI denoising tasks, the deep neural regularizer is made up of neural network structure and objective function, similar to the classic regularizer, both of these two parts are designed with the prior knowledge of image. The proposed neural network has three main parts: encoder network, decoder network and skip connections, the encoder network which consists of five down-sampling blocks is enforced to deeply extract low-resolution or highly-abstract MR image features, similar to the encoder network architecture, the decoder network is made up of five up-sampling blocks and is enforced to restore high-resolution MR image features. To generate more finer image features, we also use skip connections to transmit the abstract information from encoder to decoder directly. The objective function consists of data fidelity term and image quality penalty term, specifically, to enforce the capability of data fidelity term, we add the self-designed image structural consistency calculation to data fidelity term besides only calculating the image consistency over image pixels with mean squared error. Meanwhile, to guide the network generate more clearer image and reduce noise information, with the prior knowledge of image sharpness, an image quality penalty term which calculates the MR image sharpness is also added to the objective function. Experimental results over the simulated MRI data and real clinical data demonstrate the proposed network can achieve superior performance compared with other methods in terms of peak signal to noise ratio, structure simi

关键词： deep learning MRI denoising deep neural regularizer encoder-decoder objective function

来源：评论

学校读者我要写书评

暂无评论

Single headed attention based sequence-to-sequence model for state-of-the-art results on Switchboard 21

Single headed attention based sequence-to-sequence model for...

引用

Interspeech Conference

作者： Tuske, Zoltan Saon, George Audhkhasi, Kartik Kingsbury, Brian IBM Res AI Yorktown Hts NY 10598 USA Google Inc New York NY USA

ISBN: (纸本)9781713820697

It is generally believed that direct sequence-to-sequence (seq2seq) speech recognition models are competitive with hybrid models only when a large amount of data, at least a thousand hours, is available for training. In this paper, we show that state-of-the-art recognition performance can be achieved on the Switchboard-300 database using a single headed attention, LSTM based model. Using a cross-utterance language model, our single-pass speaker independent system reaches 6.4% and 12.5% word error rate (WER) on the Switchboard and CallHome subsets of Hub5'00, without a pronunciation lexicon. While careful regularization and data augmentation are crucial in achieving this level of performance, experiments on Switchboard-2000 show that nothing is more useful than more data. Overall, the combination of various regularizations and a simple but fairly large model results in a new state of the art, 4.8% and 8.3% WER on the Switchboard and CallHome sets, using SWB-2000 without any external data resources.

关键词： encoder-decoder attention speech recognition Switchboard

来源：评论

学校读者我要写书评

暂无评论

Cargo Segmentation in Stream of Commerce (SoC) X-Ray Images with Deep Learning Algorithms 5

Cargo Segmentation in Stream of Commerce (SoC) X-Ray Images ...

引用

Conference on Anomaly Detection and Imaging with X-Rays (ADIX) V

作者： Shen, Weicheng Tuszynski, Jaroslaw Leidos Inc Leidos Innovat Ctr Reston VA 20190 USA

ISBN: (纸本)9781510635869

Inspecting shipping containers using X-ray imagery is critical to safekeeping our borders. One of major tasks of inspecting shipping containers is manifest verification, which has two components: 1) determine what cargos are contained in a shipping container, which can be carried out in cargo segmentation, and 2) compare the cargos in the container with the cargos declared in the manifest. We focus our study on cargo segmentation. Cargo segmentation is the process of partitioning the cargo inside the container into regions with similar appearance. Assign a cargo class label to each pixel in the X-ray images. Our contribution is the development of a deep learning neural net based cargo segmentation algorithm that significantly improves the traditional ways of performing cargo segmentation. The cargo segmentation process is implemented by first partitioning the X-ray images into image tiles of certain sizes, and then train a deep learning (DL) model-based semantic segmentation algorithms using the annotated image tiles to partition the cargo into regions of similar appearance. The DL based semantic segmentation algorithm we used is an encoder-decoder structure often used for semantic segmentation. The DL network implementation chosen for our cargo segmentation is DeepLab v3+, which includes the atrous separable convolution composed of a depthwise convolution and pointwise convolution. Our X-ray cargo images used for development is a government-provided data set (GPD).

关键词： X-ray image cargo container deep learning semantic segmentation encoder-decoder atrous convolution

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：