.png){kind=icon}
返回
Adversarial learning for modeling human motion
.png){kind=icon}
PRE
AI
DOI：10.1007/s00371-018-1594-7.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
We investigate how adversarial learning may be used for various animation tasks related to human motion synthesis. We propose a learning framework that we decline for building various models corresponding to various needs: a random synthesis generator that randomly produces realistic motion capture trajectories; conditional variants that allow controlling the synthesis by providing high-level features that the animation should match; a style transfer model that allows transforming an existing animation in the style of another one. Our work is built on the adversarial learning strategy that has been proposed in the machine learning field very recently (2014) for learning accurate generative models on complex data, and that has been shown to provide impressive results, mainly on image data. We report both objective and subjective evaluation results on motion capture data performed under emotion, the Emilya Dataset. Our results show the potential of our proposals for building models for a variety of motion synthesis tasks.
Keyword:
Adversarial learning
generative models
Recurrent neural networks
Motion capture data
Motion synthesis
Style transferring
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
2.9
论文数:
4.6K
被引数:
6.5K
机构
引用论文
α-Haloenolates of Esters; III.- A Novel High-Yield Preparation of α,α-Dichloroesters.png)
Synthesis
SynthesisIF0
PREAI
分享收藏
查看更多内容