One-shot learning gesture recognition based on joint training of 3D ResNet and memory module

Li, Lianwei; Qin, Shiyin; Lu, Zhi; Xu, Kuanhong; Hu, Zhongying

doi:10.1007/s11042-019-08429-9

Cited by 16 publications

(6 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This can happen because the learning activities conducted by the students based on the activity in the module of science where it contains syntaxes of the DJP Model which gives impact on the attitude of students in learning that is able to empower and shape the character of students. This is similar to the research conducted (Alias & Siraj, 2012;Li, et al 2020).) which states that the modules are compiled and integrated with the model of learning to give effective impact and influence on learning styles and become appropriate to technology.…”

Section: Statistic Test Results Of Student Psychomotor Learning Outcomementioning

confidence: 55%

Effect of Dao Jiang Ping (DJP) Model Based Module on Learning Result of XI Class Students

Suciati

Maridi

Dewi

et al. 2020

jiecr

View full text Add to dashboard Cite

Learning outcomes are an evaluation mechanism in the curriculum to achieve graduates competency standards. Student learning outcomes include cognitive, affective, and psychomotor aspects. The purpose of this research is to know the effect of DJP Model based module to student learning result of class XI. The research used experimental method with pretest-posttest control group design. The research population is all of the XI MIA class of SMA Negeri 1 Geger with a total number of 192 students scattered into six classes. The sample which is taken by using simple random sampling technique resulted in two classes, namely XI MIA 3 class (experimental class using DJP Model module) which consist of 34 students and XI MIA 6 (control class using teaching material in school) which consist of 34 students. Data collection techniques are done through test (measuring cognitive learning outcomes) and non-tests (measuring affective and psychomotor learning outcomes). The research instruments used in this research were multiple choice questions, observation sheets, and documentation. The data were analyzed using SPSS 18 t-test with significance level of 0.05. The result of the analysis showed the experimental cognitive learning result of experimental class is higher (75,29 with 76,47% completeness) than control class (59,12 with 8,82% completeness) with significance level 0,000. The affective learning outcomes of experimental class were higher (89.78) than the control class (23.43) with significance level of 0.000. The experimental psychomotor learning outcomes of experimental class were higher (90.72) than control class (9,84) with a significance level of 0.000. Based on the results of the research can be concluded that the DJP Model-based Module gives positive effect on student learning outcomes of XI graders.

show abstract

Section: Statistic Test Results Of Student Psychomotor Learning Outcomementioning

confidence: 55%

Effect of Dao Jiang Ping (DJP) Model Based Module on Learning Result of XI Class Students

Suciati

Maridi

Dewi

et al. 2020

jiecr

View full text Add to dashboard Cite

show abstract

“…In this paper, considering the accuracy of defect detection and actual computing ability, the convolution part of ResNet-101 was selected as the feature extraction module, and the original VGG-16 was replaced to improve the accuracy of the final detection results. At present, ResNet is widely used due to its remarkable parameter optimization ability in training [27][28][29][30]. In this paper, considering the accuracy of defect detection and actual computing ability, the convolution part of ResNet-101 was selected as the feature extraction module, and the original VGG-16 was replaced to improve the accuracy of the final detection results.…”

Section: Transfer Learning With Resnet-101mentioning

confidence: 99%

Solder Joint Defect Detection in the Connectors Using Improved Faster-RCNN Algorithm

Zhang

Shen

2021

Applied Sciences

View full text Add to dashboard Cite

The miniaturization and high integration of electronic products have higher and higher requirements for welding of internal components of electronic products. A welding quality detection method has always been one of the important research contents in the industry, among which, the research on solder joint defect detection of a connector has gradually attracted people’s attention with the development of image detection algorithm. The traditional solder joint detection method of connector adopts manual detection or automatic detection methods, which is inefficient and not safe enough. With the development of deep learning, the application of a deep convolutional neural network to target detection has become a research hotspot. In this paper, a data set of connector solder joint samples was made and the number of image samples was expanded to more than 3 times of the original by using data augmentation. Clustering generates anchor boxes and transfer learning with ResNet-101 were fused, so an improved faster region-based convolutional neural networks (Faster RCNN) algorithm was proposed. The experiment verified that the improved algorithm proposed in this paper had a great improvement in all aspects compared with the original algorithm. The average detection accuracy of this method can reach 94%, and the detection rate of some defects can even reach 100%, which can completely meet the industrial requirements.

show abstract

“…The proposer of ResNet combined the residual representation concept with a CNN model to form a block structure with basic residual learning [75]. The core of this structure is the superposition of the residual function mapping layer on the basis of the shallow layer network, which can conduct residual learning to form jump connections, solve the problem of gradient disappearance, and further improve the accuracy of feature depth extraction [76]. The output of the function mapping layer can be expressed by the following formula: 𝑦 = 𝐻(𝑥, 𝑊 𝑖 ) + 𝑥 (1) where x and y are denoted as the input and output results of the subblock, respectively, and 𝐻(𝑥, 𝑊 𝑖 ) is the residual mapping parameter.…”

Section: Convolutional Neural Network (Cnns)mentioning

confidence: 99%

Landslide Detection Mapping Employing CNN, ResNet, and DenseNet in the Three Gorges Reservoir, China

Liu¹,

Chen²,

Niu³

2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Landslide detection mapping (LDM) is the basis of the field of landslide disaster prevention; however, it has faced certain difficulties. The Three Gorges Reservoir area of the Yangtze River has been one of the most intensively evaluated areas for landslide prevention in the world, due to the high frequency of landslide disasters here. In this study, we constructed an accurate LDM model based on convolutional neural networks (CNNs), residual neural networks (ResNets), and dense convolutional neural networks (DenseNets) that considers 'ZY-3' high spatial resolution (HSR) data and conditioning factors (CFs). In this work, nineteen factors based on remote sensing (RS) images, topographical and geological data associated with historical landslide locations were randomly divided into training (70% of total) and testing (30%) datasets. The experimental results show that the accuracy (ACC) of these three LDM models is above 0.95, indicating that the deep neural networks (DNNs) aimed at landslide detection performed well. Furthermore, DenseNet with RS images and CFs can accurately detect landslides. Specifically, DenseNet with RS images and CFs outperforms the other five models by considering the accuracy evaluation indexes, which exhibited Kappa coefficient improvements of 0.01-0.04 and ACC improvements of 0.02%-0.3%. Among all the factors, elevation factor has a high importance of 0.727, which is the most important factors found in this landslide model construction experiment.

show abstract

One-shot learning gesture recognition based on joint training of 3D ResNet and memory module

Cited by 16 publications

References 34 publications

Effect of Dao Jiang Ping (DJP) Model Based Module on Learning Result of XI Class Students

Effect of Dao Jiang Ping (DJP) Model Based Module on Learning Result of XI Class Students

Solder Joint Defect Detection in the Connectors Using Improved Faster-RCNN Algorithm

Landslide Detection Mapping Employing CNN, ResNet, and DenseNet in the Three Gorges Reservoir, China

Contact Info

Product

Resources

About