Art

J-GLOBAL ID：202002282476285244   Reference number：20A0760208

Human Motion Generative Model using Wasserstein GAN

Wasserstein GANを用いた人体運動の生成モデル

Author (2)： SHIOBARA Ayumi (Toyo Univ., Saitama, JPN) ,  MURAKAMI Makoto (Toyo Univ., Saitama, JPN)
Material： 情報処理学会研究報告(Web)  (IPSJ Technical Report (Web))
Volume： 2020  Issue： CG-177  Page： Vol.2020-CG-177,No.4,1-6 (WEB ONLY)  Publication year： Mar. 10, 2020 
JST Material Number： U0451A  Document type： Proceedings
Article type： 原著論文  Country of issue： Japan (JPN)  Language： ENGLISH (EN)

Thesaurus term： neural network(biomodel) ,  machine learning ,  model ,  joint(animal) ,  loss function ,  least squares method ,  supervised learning ,  frame(structure) ,  *voluntary movement ,  *computer animation
Semi thesaurus term： skeleton ,  deep neural network ,  *Exertion ,  generation model

JST classification (1)： Graphic and image processing in general  (JE04010I)

Reference (11)：

• Wang, X. Chen, Q. and Wang. W. 3D human motion editing and synthesis : A survey. Computational and Mathematical Methods in Medicine. 2014.
• Holden, D. Saito, J. Komura, T. and Joyce, T. Learning motion manifolds with convolutional autoencoders. SIGGRAPH Asia 2015 Technical Briefs. 2015.
• Kingma, D. P. and Welling, M. Auto-encoding variational bayes. International Conference on Learning Representations. 2013.
• Kingma, D. P. Rezende, D. J. Mohamed, S. and Welling, M. Semi-supervised learning with deep generative models. Neural Information Processing Systems. 2014.
• Sabaththe, R. Coutinho, E. and Schuller, B. Deep recurrent music writer: Memory-enhanced variational autoencoder-based musical score composition and an objective measure. International Joint Conference on Neural Networks. 2017, pp. 3467-3474.

Terms in the title (3)： GaN ,  人体運動 ,  生成モデル