Persistent-Transient Duality in Human Behavior Modeling

Hung Tran, Vuong Le, Svetha Venkatesh, Truyen Tran

CVPRW 2022 pp. 2527-2530

doi:10.1109/CVPRW56347.2022.00283 /cvprw/2022/tran2022cvprw-persistenttransient/

Abstract

We propose to model the persistent-transient duality in human behavior using a parent-child multi-channel neural network, which features a parent persistent channel that manages the global dynamics and children transient channels that are initiated and terminated on-demand to handle detailed interactive actions. The short-lived transient sessions are managed by a proposed Transient Switch. The neural framework is trained to discover the structure of the duality automatically. Our model shows superior performances in human-object interaction motion prediction.

PDF CVPRW Semantic Scholar

Cite

Text

Tran et al. "Persistent-Transient Duality in Human Behavior Modeling." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2022. doi:10.1109/CVPRW56347.2022.00283

Markdown

[Tran et al. "Persistent-Transient Duality in Human Behavior Modeling." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2022.](https://mlanthology.org/cvprw/2022/tran2022cvprw-persistenttransient/) doi:10.1109/CVPRW56347.2022.00283

BibTeX

@inproceedings{tran2022cvprw-persistenttransient,
  title     = {{Persistent-Transient Duality in Human Behavior Modeling}},
  author    = {Tran, Hung and Le, Vuong and Venkatesh, Svetha and Tran, Truyen},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2022},
  pages     = {2527-2530},
  doi       = {10.1109/CVPRW56347.2022.00283},
  url       = {https://mlanthology.org/cvprw/2022/tran2022cvprw-persistenttransient/}
}