2020
DOI: 10.1016/j.jnca.2020.102636
|View full text |Cite
|
Sign up to set email alerts
|

A novel syntax-aware automatic graphics code generation with attention-based deep neural network

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
4
0
2

Year Published

2020
2020
2023
2023

Publication Types

Select...
7
2

Relationship

0
9

Authors

Journals

citations
Cited by 14 publications
(7 citation statements)
references
References 1 publication
0
4
0
2
Order By: Relevance
“…Action spacing is a comprehensive description of human motion amplitude, with motion amplitude referring to the amount of space spanned by human joint movements [19]. In this paper, the action distance is computed based on the moving distance of each node position in the action segment, whereas the moving distance of joint points is determined by calculating the distance between each joint point and its central position in the action segment.…”
Section: Feature Analysis and Extractionmentioning
confidence: 99%
“…Action spacing is a comprehensive description of human motion amplitude, with motion amplitude referring to the amount of space spanned by human joint movements [19]. In this paper, the action distance is computed based on the moving distance of each node position in the action segment, whereas the moving distance of joint points is determined by calculating the distance between each joint point and its central position in the action segment.…”
Section: Feature Analysis and Extractionmentioning
confidence: 99%
“…rough the network, which is the HGui2Code model as an attention-based deep neural code, the DSL code may be aligned with the relevant GUI pixel by using a hybrid attention approach. Comprehensive empirical findings indicate that the NAT model surpasses the newest techniques in online datasets, with the HGui2Code model enhancing accuracy by 5.5 percent and the SGui2Code model increasing accuracy by 1.5 percent, respectively [18].…”
Section: Related Workmentioning
confidence: 99%
“…However, in the automatic code generation field, the text is code (structured text) instead of natural language text [38]. Convolutional neural network (CNN) and recurrent neural network (RNN) have been used in this type of studies which are well-known deep neural networks [38][39][40].…”
Section: Automated Testingmentioning
confidence: 99%