Social Diffusion: Long-term Multiple Human Motion Anticipation

Julian Tanke, Linguang Zhang, Amy Zhao, Chengcheng Tang, Yujun Cai, Lezi Wang, Po-Chen Wu, Juergen Gall, Cem Keskin

Abstract

We propose Social Diffusion, a novel method for short-term and long-term forecasting of the motion of multiple persons as well as their social interactions. Jointly forecasting motions for multiple persons involved in social activities is inherently a challenging problem due to the interdependencies between individuals. In this work, we leverage a diffusion model conditioned on motion histories and causal temporal convolutional networks to forecast individually and contextually plausible motions for all participants. The contextual plausibility is achieved via an order-invariant aggregation function. As a second contribution, we design a new evaluation protocol that measures the plausibility of social interactions which we evaluate on the Haggling dataset, which features a challenging social activity where people are actively taking turns to talk and switching their attention. We evaluate our approach on four datasets for multi-person forecasting where our approach outperforms the state-of-the-art in terms of motion realism and contextual plausibility.
BibTeX
@inproceedings{tanke2023social,
  author = {Julian Tanke and Linguang Zhang and Amy Zhao and Chengcheng Tang and Yujun Cai and Lezi Wang and Po-Chen Wu and Juergen Gall and Cem Keskin},
  title = {{Social Diffusion: Long-term Multiple Human Motion Anticipation}},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year = {2023},
  doi = {10.1109/iccv51070.2023.00880},
}

Loading related content...

Figure