Motion Capture Synthesis with Adversarial Learning

Abstract : We propose a new statistical modeling approach that we call Sequential Adversarial Auto-encoder (SAAE) for learning a synthesis model for motion sequences. This model exploits the adversarial idea that has been popularized in the machine learning field for learning accurate generative models. We further propose a conditional variant of this model that takes as input an additional information such as the activity which is performed in a sequence, or the emotion with which it is performed, and which allows to perform synthesis in context.
Complete list of metadatas

Cited literature [8 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01691463
Contributor : Thierry Artières <>
Submitted on : Wednesday, January 24, 2018 - 8:30:01 AM
Last modification on : Thursday, September 19, 2019 - 2:17:45 PM
Long-term archiving on : Thursday, May 24, 2018 - 2:50:28 PM

File

104980470.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01691463, version 1

Collections

Citation

Qi Wang, Thierry Artières. Motion Capture Synthesis with Adversarial Learning. Intelligent Virtual Agents, Aug 2017, Stockholm, Sweden. ⟨hal-01691463⟩

Share

Metrics

Record views

348

Files downloads

239