Search

Your search keyword '"Zhang, Yu-Xin"' showing total 1,028 results
Start Over Author "Zhang, Yu-Xin"
1,028 results on '"Zhang, Yu-Xin"'

1. A Comprehensive Survey and Taxonomy on Point Cloud Registration Based on Deep Learning

Author

Zhang, Yu-Xin, Gui, Jie, Cong, Xiaofeng, Gong, Xin, and Tao, Wenbing

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Point cloud registration (PCR) involves determining a rigid transformation that aligns one point cloud to another. Despite the plethora of outstanding deep learning (DL)-based registration methods proposed, comprehensive and systematic studies on DL-based PCR techniques are still lacking. In this paper, we present a comprehensive survey and taxonomy of recently proposed PCR methods. Firstly, we conduct a taxonomy of commonly utilized datasets and evaluation metrics. Secondly, we classify the existing research into two main categories: supervised and unsupervised registration, providing insights into the core concepts of various influential PCR models. Finally, we highlight open challenges and potential directions for future research. A curated collection of valuable resources is made available at https://github.com/yxzhang15/PCR., Comment: This paper is accepted by IJCAI 2024

Published
2024

21. Effects of Cold Rolling on the Corrosion Resistance of 2205 Duplex Stainless Steel in Artificial Seawater

Author

GUO Yu, ZHANG Yu-xin, SONG Hang, CHEN Ji, WANG Hong-chen, PENG Qi-qiang

Subjects
2205 duplex stainless steel, cold rolling reduction rate, artificial seawater, corrosion, Materials of engineering and construction. Mechanics of materials, TA401-492, Technology
Abstract

In order to clarify the change of the corrosion properties of 2205 duplex stainless steel in artificial seawater after cold rolling，2205 duplex stainless steel was cold-rolled at different reduction rates (PCRR ＝20%-80%)，and then the sample was studied by metallographic observation and hardness measurement.The corrosion resistance of cold-rolled 2205 duplex stainless steel in artificial seawater (3.5%NaCl)was investigated using dynamic potential polarization curve and electrochemical impedance spectroscopy.Results showed that the hardness and corrosion resistance of 2205 stainless steel presented non-monotonic variation with the increase of PCRR.In the interval from 0 to 40%，the corrosion resistance and hardness increased with the increase of the reduction rate，and the self-corrosion potential increased from -309 mV to-269 mV.In the interval from 40%to 80%，the corrosion resistance decreased with the increase of the reduction rate，and the self-corrosion potential decreased from -269 mV to -322 mV.Moreover，the corrosion resistance was highest at the reduction rate of 40%，and the Brinell hardness of the sample with the reduction rate of 60%was the highest，about 374 HBW.Suitable cold rolling could result in high-density dislocation and structure refinement，which was beneficial to the corrosion resistance of 2205 duplex stainless steel.However，an excessive reduction rate would result in the precipitation of σ-phase which was detrimental to corrosion resistance.

Published
2023
Full Text
View/download PDF

29. Driver Distraction Detection Based on Multi-scale Feature Fusion Network

Author

ZHANG Yu-xin, CHEN Yi-qiang

Subjects
driver distraction, unsupervised learning, multi-source, multi-scale fusion, encoder-decoder, Computer software, QA76.75-76.765, Technology (General), T1-995
Abstract

The occurrence of road traffic accidents has increased year by year.Driver inattention during driving is one of the major causes of traffic accidents.In this paper,we utilize multi-source data to detect driver distraction.However,the correlations derived from multi-source data will generate feature of high-dimensional entanglement.Existing methods perform similar processing for data of different sources or simply stick to concatenate multi-source features,which are not easy to catch the key feature of high-dimensional entanglement.And distracted driving can be affected by many factors.Supervised methods might cause misclassification when the type of driver distraction does not exist in the set of the known categories.Therefore,we propose a multi-dcale feature fusion network approach to tackle these challenges.Basically,it first learns low-dimensional representations from multi-source data through multiple embedding subnetworks,and then proposes a multi-scale feature Fusion method to aggregate these representations from the perspective of spatial-temporal correlation,thereby reducing the entanglement of feature.Finally,we utilize a ConvLSTM encoder-decoder model to detect driver distraction.Experimental results on a public loaded drive dataset show that the proposed method outperforms the existing methods.

Published
2022
Full Text
View/download PDF

44. Scopolamine for patients with motion sickness: a systematic review and meta-analysis with trial sequential analysis.

Author

Zhang, Yu-Xin, Niu, Xin-Ying, Xiao, Zhi-Yong, Wang, Meng-Ting, and Zheng, Hui

Subjects
*MOTION sickness, *SEQUENTIAL analysis, *SCOPOLAMINE, *CONFIDENCE intervals, *SAMPLE size (Statistics)
Abstract

AbstractBackgroundObjectivesMaterial and methodsResultsConclusionSignificanceScopolamine has been demonstrated to relieve motion sickness. However, repeated significance testing may increase false-positive results.Review the efficacy and safety of scopolamine in the prevention of motion sickness by performing a meta-analysis with Trial Sequential Analysis (TSA).Randomized controlled trials (RCTs) compared scopolamine with other medications or placebo were included. Primary outcomes were nausea reported and head movement time.Twenty studies with 753 participants were included. Scopolamine had a greater reported reduction in nausea than placebo (relative risk [RR] 0.35; 95% confidence interval [CI] 0.24 to 0.52; p<0.00001; I2 = 45%), while TSA showed the included sample size exceeded the required information size (RIS). There is no difference in head movement time between scopolamine and placebo (mean difference [MD] 2.02; 95% CI −1.2 to 5.25; p = 0.6; I2 = 0%), while the included sample size did not reach RIS.Scopolamine is effective for motion sickness nausea compared to placebo. The TSA recommends conducting more head movement trials to validate the objective efficacy of scopolamine.Clarifying the efficacy of scopolamine for motion sickness, the TSA highlights the need for more prospective studies using head movement as an outcome. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

45. A systematic review and meta-analysis on the prevalence of stigma in infectious diseases, including COVID-19: a call to action

Author

Yuan, Kai, Huang, Xiao-Lin, Yan, Wei, Zhang, Yu-Xin, Gong, Yi-Miao, Su, Si-Zhen, Huang, Yue-Tong, Zhong, Yi, Wang, Yi-Jie, Yuan, Ze, Tian, Shan-Shan, Zheng, Yong-Bo, Fan, Teng-Teng, Zhang, Ying-Jian, Meng, Shi-Qiu, Sun, Yan-Kun, Lin, Xiao, Zhang, Tian-Ming, Ran, Mao-Sheng, Wong, Samuel-Yeung-Shan, Rüsch, Nicolas, Shi, Le, Bao, Yan-Ping, and Lu, Lin

Published
2022
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results