Transflower: probabilistic autoregressive dance generation with multimodal attention

Guillermo Valle Perez (1) , Jonas Beskow (2) , Gustav Eje Henter (2) , Andre Holzapfel (2) , Pierre-Yves Oudeyer (1) , Simon Alexanderson (2)

1 Flowers - Flowing Epigenetic Robots and Systems
2 KTH - KTH Royal Institute of Technology [Stockholm]

Mots clés: Neural networks; Motion capture; machine learning; normalising flows; Glow; transformers; dance; Generative models

Domaines: Intelligence artificielle [cs.AI]

Guillermo Valle Perez, Jonas Beskow, Gustav Eje Henter, Andre Holzapfel, Pierre-Yves Oudeyer, et al.. Transflower: probabilistic autoregressive dance generation with multimodal attention. SIGGRAPH Asia 2021 - 14th ACM SIGGRAPH Conference and Exhibition on Computer Graphics and Interactive Techniques, Dec 2021, Tokyo, Japan. ⟨10.1145/3478513.3480570⟩. ⟨hal-03449915⟩