Open Access

Automatic Generation of Cinematic Animated Characters and Their Behavioral Characterization Using Graph Generation Networks

Wei Peng

Wei Peng

  • Cheongju UniversitySouth Korea
  • Commerce Boustead College, Tianjin UniversityTianjin, China
Search for this author on
Sciendo|Google Scholar
Peng, Wei
 and 
Qingya Zhang

Qingya Zhang

Commerce Boustead College, Tianjin UniversityTianjin, China
Search for this author on
Sciendo|Google Scholar
Zhang, Qingya
  
Mar 17, 2025
Automatic Generation of Cinematic Animated Characters and Their Behavioral Characterization Using Graph Generation Networks's Cover Image
About this article
Previous Article
Next Article
Cite
Download Cover
Published Online: Mar 17, 2025
Received: Oct 16, 2024
Accepted: Jan 31, 2025
DOI: https://doi.org/10.2478/amns-2025-0268
Keywords
© 2025 Wei Peng et al., published by Sciendo
This work is licensed under the Creative Commons Attribution 4.0 International License.

Figure 1.

Animation design process evolution
Animation design process evolution

Figure 2.

The production and creation process of the artist
The production and creation process of the artist

Figure 3.

Comparison result(MMD)
Comparison result(MMD)

Figure 4.

Usability test results
Usability test results

Figure 5.

Training results
Training results

Figure 6.

Conventional score test results
Conventional score test results

Model test results

Model COKK
Degree Clustering Orbit
GAN 0.315 0.274 0.105
CGAN 0.275 0.244 0.078
ACGAN 0.189 0.201 0.065
Ours 0.178 0.185 0.076

The result of the abnormal behavior recognition of the artist

The action of the artist Video number Correct detection Error detection Accuracy(%)
M1 354 344 10 97.18
M2 546 527 19 96.52
M3 482 470 12 97.51
M4 337 323 14 95.85
Mean — 416 13.75 96.76
Language:
English
Publication timeframe:
1 times per year
Journal Subjects:
Life Sciences, Life Sciences, other, Mathematics, Applied Mathematics, General Mathematics, Physics, Physics, other
Journal RSS Feed