English

Conditional Temporal Variational AutoEncoder for Action Video Prediction

Computer Vision and Pattern Recognition 2021-08-13 v1

Abstract

To synthesize a realistic action sequence based on a single human image, it is crucial to model both motion patterns and diversity in the action video. This paper proposes an Action Conditional Temporal Variational AutoEncoder (ACT-VAE) to improve motion prediction accuracy and capture movement diversity. ACT-VAE predicts pose sequences for an action clips from a single input image. It is implemented as a deep generative model that maintains temporal coherence according to the action category with a novel temporal modeling on latent space. Further, ACT-VAE is a general action sequence prediction framework. When connected with a plug-and-play Pose-to-Image (P2I) network, ACT-VAE can synthesize image sequences. Extensive experiments bear out our approach can predict accurate pose and synthesize realistic image sequences, surpassing state-of-the-art approaches. Compared to existing methods, ACT-VAE improves model accuracy and preserves diversity.

Keywords

Cite

@article{arxiv.2108.05658,
  title  = {Conditional Temporal Variational AutoEncoder for Action Video Prediction},
  author = {Xiaogang Xu and Yi Wang and Liwei Wang and Bei Yu and Jiaya Jia},
  journal= {arXiv preprint arXiv:2108.05658},
  year   = {2021}
}

Comments

under submission

R2 v1 2026-06-24T05:03:36.801Z