Persistent-Transient Duality in Human Behavior Modeling

Hung Tran, Vuong Le, Svetha Venkatesh, Truyen Tran; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2022, pp. 2528-2531

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.

Related Material

[pdf] [arXiv]
[bibtex]
@InProceedings{Tran_2022_CVPR, author = {Tran, Hung and Le, Vuong and Venkatesh, Svetha and Tran, Truyen}, title = {Persistent-Transient Duality in Human Behavior Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {2528-2531} }