发布求助
文献互助 智能选刊 最新文献

2020 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR)最新文献

筛选
英文 中文
Optimized Algorithm Of Human 3D Motion Recognition Based On HOG And LBP 基于HOG和LBP的人体三维运动识别优化算法
2020 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR) Pub Date : 2020-12-02 DOI: 10.1109/ICWAPR51924.2020.9494611
Xin Liang, Junpeng Yang, Tang-Tang Yi, Kaizhu Yang, Weile Zhang, Yiliang Fan, Peijie Li
{"title":"Optimized Algorithm Of Human 3D Motion Recognition Based On HOG And LBP","authors":"Xin Liang, Junpeng Yang, Tang-Tang Yi, Kaizhu Yang, Weile Zhang, Yiliang Fan, Peijie Li","doi":"10.1109/ICWAPR51924.2020.9494611","DOIUrl":"https://doi.org/10.1109/ICWAPR51924.2020.9494611","url":null,"abstract":"Recognizing the accurate position of each joint point of the human body helps the computer to understand the rich human body motion information. Recognizing the precise position of each joint point of the human body in 3D space helps the computer understand the rich human motion information. In order to avoid the defects of binocular vision combined with neural network method, we have designed an optimization algorithm for human body 3D pose recognition technology under binocular vision. The algorithm uses HOG and LBP feature operators to perform feature matching on the corresponding joint point areas of the left and right images, and seeks the optimal pixel position of the corresponding joints points. And the search window can adjust itself to the best size. This algorithm greatly reduces the randomness of neural network recognition, the generated 3D human pose is more stable, greatly reduces the problem of joint jitter offset, and the effect is more smooth and stable.","PeriodicalId":111814,"journal":{"name":"2020 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR)","volume":"2019 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133061684","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A Neural Network Prediction Model On Multiple Error Dimension Integration 多误差维积分的神经网络预测模型
2020 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR) Pub Date : 2020-12-02 DOI: 10.1109/ICWAPR51924.2020.9494622
Hao Yu, Ruixin Tang, R. Liu, Runbin Chen, Fangyuan Xu
{"title":"A Neural Network Prediction Model On Multiple Error Dimension Integration","authors":"Hao Yu, Ruixin Tang, R. Liu, Runbin Chen, Fangyuan Xu","doi":"10.1109/ICWAPR51924.2020.9494622","DOIUrl":"https://doi.org/10.1109/ICWAPR51924.2020.9494622","url":null,"abstract":"Forecasting technique is an important research area in machine learning, and average accuracy is usually recognized as the main target of prediction, such as 2-Norm error. However, this accuracy pursuing forecasting model may not always targets on the solution with optimal impact in further usage of prediction result. Facing this issue, this paper proposes a composite prediction structure model based on Long Short-Term Memory (LSTM), which considers both the mean deviation and the maximum positive bias error between the predicted value and the actual value. A numerical study with practical photovoltaic (PV) data is presented and the result shows that composite prediction structure model can reduce more total cost from prediction error than pure model on 2-Norm error only.","PeriodicalId":111814,"journal":{"name":"2020 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR)","volume":"459 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124259851","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Greetings from the General Chairs 各位主席的问候
2020 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR) Pub Date : 2020-12-02 DOI: 10.1109/icwapr51924.2020.9494380
{"title":"Greetings from the General Chairs","authors":"","doi":"10.1109/icwapr51924.2020.9494380","DOIUrl":"https://doi.org/10.1109/icwapr51924.2020.9494380","url":null,"abstract":"","PeriodicalId":111814,"journal":{"name":"2020 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125946204","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Image Colored-Pencil-Style Transformation Based on Generative Adversarial Network 基于生成对抗网络的图像彩色铅笔式变换
2020 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR) Pub Date : 2020-12-02 DOI: 10.1109/ICWAPR51924.2020.9494617
Haitao Chen, U. Kin Tak
{"title":"Image Colored-Pencil-Style Transformation Based on Generative Adversarial Network","authors":"Haitao Chen, U. Kin Tak","doi":"10.1109/ICWAPR51924.2020.9494617","DOIUrl":"https://doi.org/10.1109/ICWAPR51924.2020.9494617","url":null,"abstract":"Generative Adversarial Network (GAN) has an excellent performance in “ Image-to-Image Translation” field, this paper proposes an effective algorithm to solve the problem of image colored-pencil-style transformation based on Pix2Pix of GAN. The improved generator and discriminator are designed to be suitable for high resolution image generation. In the loss function, TV Loss is using for improving the smoothness of images and removing noise and overlapping shadows. In order to adapt to the practical application requirement of colored-pencil-style transformation, our data set comes from Flickr, the world's largest photo-sharing site, and includes high-resolution images of different types. The experimental results show that our proposed algorithm not only improves the resolution of images, but also makes the details clearer. Moreover, in all terms of objective indicators, our proposed algorithm is superior to Pix2Pix in different categories of data set. Therefore, through the comparison in visual subjectively and in indicators objectively, it is proved that the proposed algorithm has better performance than Pix2Pix.","PeriodicalId":111814,"journal":{"name":"2020 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR)","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124109903","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Matryoshka Attack: Research On An Attack Method Of Recommender System Based On Adversarial Learning And Optimization Solution 套娃攻击:一种基于对抗性学习的推荐系统攻击方法及优化解决方案研究
2020 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR) Pub Date : 2020-12-02 DOI: 10.1109/ICWAPR51924.2020.9494616
Huibin Wang, Junyan Zhong, Kin Tak U
{"title":"Matryoshka Attack: Research On An Attack Method Of Recommender System Based On Adversarial Learning And Optimization Solution","authors":"Huibin Wang, Junyan Zhong, Kin Tak U","doi":"10.1109/ICWAPR51924.2020.9494616","DOIUrl":"https://doi.org/10.1109/ICWAPR51924.2020.9494616","url":null,"abstract":"Currently, recommendation systems have been widely used in various fields, especially profitable ones. However, the research on the attack method of the recommendation system is not very common, and the analysis of the reaction of the system after the attack is also rare. At the same time, most of the existing research focuses on discussing a single theoretical level of attack without taking actual conditions into consideration. To this end, we propose an evaluation model based on minimum attack resource consumption, and innovatively propose a data injection attack method based on adversarial learning. In this article, we first introduced the principle of the recommendation system, explained the effectiveness of the data injection attack on the recommendation system, and then used the new \"Russian doll attack\" method to strengthen the common data injection attack and apply it to three realities. To verify the effectiveness and portability of our attack. In addition, we were also pleasantly surprised to find that the Russian doll attack is particularly destructive to the popular ITEMAE recommendation system.","PeriodicalId":111814,"journal":{"name":"2020 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR)","volume":"1996 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128210857","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Sparse Convolution Subspace Clustering 稀疏卷积子空间聚类
2020 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR) Pub Date : 2020-12-02 DOI: 10.1109/ICWAPR51924.2020.9494614
Chuan Luo, Linchang Zhao, Taiping Zhang
{"title":"Sparse Convolution Subspace Clustering","authors":"Chuan Luo, Linchang Zhao, Taiping Zhang","doi":"10.1109/ICWAPR51924.2020.9494614","DOIUrl":"https://doi.org/10.1109/ICWAPR51924.2020.9494614","url":null,"abstract":"The real-world high-dimensional data lie on low-dimensional manifolds embedded within the high-dimensional space. Therefore, clustering in high-dimensional spaces is a difficult problem. Subspace-based clustering methods are proposed to project the high dimensional data into a low-dimensional space, and then find clusters in this low-dimensional subspaces of the high dimensional data, instead of finding clusters in the entire feature space. In this work, we propose a subspace clustering method called Sparse Convolution Subspace Clustering (SCSC) which is inspired by Sparse Subspace Clustering (SSC). SSC is to find a sparse representations of a data point in terms of other points while SCSC tries to find a sparse convolutional representations of a data point in terms of other points. A group optimization method based alternating direction method of multipliers (ADMM) is used to solve the sparse convolutional representation problem. It should be pointed out that SSC is a special case of SCSC while the convolution kernel size is set as $1 times 1$. The experimental results on face data show the effectiveness of the proposed SCSC.","PeriodicalId":111814,"journal":{"name":"2020 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129918466","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Application Of Synchroqueezing Wavelet Transform In Bolt Anchorage Detection Signal Analysis 同步小波变换在锚杆锚固检测信号分析中的应用
2020 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR) Pub Date : 2020-12-02 DOI: 10.1109/ICWAPR51924.2020.9494624
Xiaoyan Sun, Jia-Qi Dong, Wenpeng Zhang, Hui Xing
{"title":"Application Of Synchroqueezing Wavelet Transform In Bolt Anchorage Detection Signal Analysis","authors":"Xiaoyan Sun, Jia-Qi Dong, Wenpeng Zhang, Hui Xing","doi":"10.1109/ICWAPR51924.2020.9494624","DOIUrl":"https://doi.org/10.1109/ICWAPR51924.2020.9494624","url":null,"abstract":"Time-frequency aggregation is an important criterion for evaluating the performance of time-frequency analysis methods, and traditional time-frequency analysis methods do not match the requirements of time-frequency aggregation. Synchroqueezing Wavelet Transform (SWT) method, as a new method proposed recently, can improve the time-frequency aggregation effectively by compressing the Wavelet coefficients in frequency domain. This paper applies the SWT method to extract the time-frequency characteristics of the analog signal and compare the analysis results with that of the traditional methods. The bolt anchorage damage detection signals based on guided wave technology of magnetostrictive effect are analyzed as the measured data to verify the effect of SWT method. The results show that SWT method can accurately describe the frequency composition of signals and obtain a relatively concentrated time-frequency energy distribution, providing a new time-frequency analysis method for bolt anchoring quality NDT (Non Destructive Testing).","PeriodicalId":111814,"journal":{"name":"2020 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR)","volume":"256 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114364485","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Utilizing Contextualized Word Embeddings For Text Matching 利用语境化词嵌入进行文本匹配
2020 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR) Pub Date : 2020-12-02 DOI: 10.1109/ICWAPR51924.2020.9494608
Hao Yu, Xiaoyang Chen, Ying Zhou
{"title":"Utilizing Contextualized Word Embeddings For Text Matching","authors":"Hao Yu, Xiaoyang Chen, Ying Zhou","doi":"10.1109/ICWAPR51924.2020.9494608","DOIUrl":"https://doi.org/10.1109/ICWAPR51924.2020.9494608","url":null,"abstract":"Recent advances in information retrieval has shown a focus on developing neural ranking models based on pre-trained language models. Among them, the interaction-based neural retrieval models, despite the promising results, are mostly based on static word embedding techniques such as Word2Vec, without considering the dynamic nature of context. In this paper, we propose to utilize the recently emerged contextualized language models for improving the retrieval performance of interaction-based neural ranking models. Specifically, we incorporate the state-of-the-art DRMM and K-NRM models with the generalized autoregressive pre-trained language model based on Transformer-XL (XLNet) by taking individual query term occurrences within documents into account. Experimental results on two standard TREC collections demonstrate improved effectiveness brought by the contextualized word embeddings.","PeriodicalId":111814,"journal":{"name":"2020 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115882324","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Comparison Of RNA Secondary Structure Using Discrete Wavelet Transform And Fractal Dimension 用离散小波变换和分形维数比较RNA二级结构
2020 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR) Pub Date : 2020-12-02 DOI: 10.1109/ICWAPR51924.2020.9494386
Yang Liu, Lina Yang, Y. Tang, P. Wang
{"title":"Comparison Of RNA Secondary Structure Using Discrete Wavelet Transform And Fractal Dimension","authors":"Yang Liu, Lina Yang, Y. Tang, P. Wang","doi":"10.1109/ICWAPR51924.2020.9494386","DOIUrl":"https://doi.org/10.1109/ICWAPR51924.2020.9494386","url":null,"abstract":"As the role of RNA molecules was discovered more and more, the similarity between RNA sequences was studied widely. However, because RNA has a conserved secondary structure rather than a primary structure, it is important to consider structural information in RNA comparisons. In this paper, an RNA secondary structure comparison method based on fractal dimension and wavelet transform is proposed. First, the secondary structure of RNA was represented as TV-curve. Next, based on wavelet transform, the windowed fractal dimension is applied to calculate the similarity between sequences. RNA sequences from the RFAM database were selected for the experiment, and the results obtained were closer to the standard MEGA software compared with Li’s algorithm, with lower time complexity.","PeriodicalId":111814,"journal":{"name":"2020 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126920198","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Sensitivity Based Robust Learning With Sampling In Adversarial Environment 对抗环境下基于灵敏度的抽样鲁棒学习
2020 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR) Pub Date : 2020-12-02 DOI: 10.1109/ICWAPR51924.2020.9494387
Qing Lin, Wei Li, P. Chan
{"title":"Sensitivity Based Robust Learning With Sampling In Adversarial Environment","authors":"Qing Lin, Wei Li, P. Chan","doi":"10.1109/ICWAPR51924.2020.9494387","DOIUrl":"https://doi.org/10.1109/ICWAPR51924.2020.9494387","url":null,"abstract":"Although Deep Neural Networks achieve excellent results in many applications, their security issue is one of the concerns. Many studies suggest that Deep Neural Networks can be easily misled by adversarial attack. Sensitivity training method enhances the robustness of Deep Neural networks. However, injecting sensitivity samples for all training samples increases the training time significantly. This study investigates whether generating sensitivity samples for all training samples is necessary. A model trained by using sensitivity samples for selected training samples is proposed. The method is evaluated and compared with the traditional one and the adversarial learning method experimentally. The results suggest that the robustness of the models using sensitivity samples for the partial and full training sets is similar. The time complexity of sensitivity training methods can be reduced.","PeriodicalId":111814,"journal":{"name":"2020 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125880252","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信