2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML)最新文献_第4页

Parking-Lot Vehicles Detection from a Low-Angle Camera Perspective Based on Improved Mask R-CNN 基于改进掩模R-CNN的低角度摄像机视角停车场车辆检测

2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/CACML55074.2022.00102

Yiliang Wu, Yu Sun, Yulin Jia, Fengshun Liao

引用次数: 0

Experimental Teaching Reform of Angle Measuring Method in Digital Signal Processing Course 数字信号处理课程角度测量方法实验教学改革

2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/CACML55074.2022.00070

Shaoming Wei, Yuxiang Liu, Jun Wang

{"title":"Experimental Teaching Reform of Angle Measuring Method in Digital Signal Processing Course","authors":"Shaoming Wei, Yuxiang Liu, Jun Wang","doi":"10.1109/CACML55074.2022.00070","DOIUrl":"https://doi.org/10.1109/CACML55074.2022.00070","url":null,"abstract":"The angle measurement experiment is an innovative experiment in the digital signal processing course. This experiment combines engineering practice to allow students to comprehensively master the basic knowledge of circular convolution and window function. Aiming at the problems of the traditional amplitude ratio monopulse angle measurement method, due to the coupling of the azimuth angle and the pitch angle, the normalized error curve is not unique and the angle measurement results are uncertain. In this paper, a new monopulse angle measurement method based on sinusoidal coordinate system is designed. Through the transformation of the sinusoidal coordinate system, the coupling of the azimuth angle and the pitch angle in the angle measurement process is solved, thus realizing the uniqueness of the angle measurement result. On the premise of paying attention to the foundation, professionalism and practicability, this paper introduces innovative experimental methods and updates the teaching content. Through this experiment, students' innovative thinking and problem-solving ability are cultivated.","PeriodicalId":137505,"journal":{"name":"2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML)","volume":"207 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124553713","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

Semantic and Visual Enrichment Hierarchical Network for Medical Image Report Generation 基于语义和视觉丰富层次网络的医学图像报告生成

2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/CACML55074.2022.00128

Qian Tang, Yongbin Yu, Xiao Feng, Chenhui Peng

引用次数: 0

Quantitative Trading Method based on Neural Network Machine Learning 基于神经网络机器学习的定量交易方法

2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/CACML55074.2022.00107

W.-S. Weng

引用次数: 0

Learning 3D Face Representation with Vision Transformer for Masked Face Recognition 用视觉变压器学习三维人脸表示，用于蒙面人脸识别

2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/CACML55074.2022.00092

Yuan Wang, Zhen Yang, Zhiqiang Zhang, Huaijuan Zang, Qiang Zhu, Shu Zhan

{"title":"Learning 3D Face Representation with Vision Transformer for Masked Face Recognition","authors":"Yuan Wang, Zhen Yang, Zhiqiang Zhang, Huaijuan Zang, Qiang Zhu, Shu Zhan","doi":"10.1109/CACML55074.2022.00092","DOIUrl":"https://doi.org/10.1109/CACML55074.2022.00092","url":null,"abstract":"Masked face recognition, a non-contact biometric technology, has attracted much attention and developed rapidly during the coronavirus disease 2019 (COVID-19) outbreak. The existing work trains the masked face recognition model based on a large number of 2D masked face images. However, in practical application scenarios, it is difficult to obtain a large number of masked face images in a short period of time. Therefore, combined with 3D face recognition technology, this paper proposes a masked face recognition model trained with non-masked face images. In this paper, we locate and segment the complete face region and the face region not occluded by masks from the face point clouds. The geometric features of the 3D face surface, namely depth, azimuth, and elevation, are extracted from the above two regions to generate training data. The proposed masked face recognition model based on vision Transformer divides the complete faces and part of the faces into sequence images, and then captures the relationship between the image slices to compensate for the impact caused by the lack of face information, thereby improving the recognition performance. Comparative experiments with the state-of-the-art masked face recognition work are carried out on four databases. The experimental results show that the recognition accuracy of the proposed model is improved by 9.86% on Bosphorus database, 16.77% on CASIA-3D FaceV1 database, 2.32% on StirlingESRC database, and 34.81% on Ajmal main database, respectively, which verifies the effectiveness and stability of the proposed model.","PeriodicalId":137505,"journal":{"name":"2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114865978","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

Analysis of range anxiety using NEV monitoring big data 利用新能源汽车监测大数据分析里程焦虑

2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/CACML55074.2022.00032

Lina Xia, Chuan Chen, Huanhuan Ren, Zejun Kang

引用次数: 0

Research on Complexity Change of Stock Market Based on Approximate Entropy 基于近似熵的股票市场复杂性变化研究

2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/CACML55074.2022.00113

Xuemei Yang, Yuting Zhou, Shiqi Liu, Junping Yin

引用次数: 0

Asymmetric Generative Adversarial Networks with a New Attention Mechanism 一种新的注意机制的非对称生成对抗网络

2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/CACML55074.2022.00038

Jian Chen, Gang Liu, Aihua Ke

引用次数: 0

Experimental Teaching Reform of Window Function Design in Digital Signal Processing Course 数字信号处理课程窗函数设计实验教学改革

2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/CACML55074.2022.00071

Shaoming Wei, Xin Ma, Jun Wang

引用次数: 0

Face alignment by learning from small real datasets and large synthetic datasets 从小型真实数据集和大型合成数据集学习人脸对齐

2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML) Pub Date : 2022-03-01 DOI: 10.1109/CACML55074.2022.00073

Haoqi Gao, K. Ogawara

引用次数: 1