Social-MAE: Social Masked Autoencoder for Multi-person Motion Representation Learning

arXiv:2404.05578v1 Announce Type: new
Abstract: For a complete comprehension of multi-person scenes, it is essential to go beyond basic tasks like detection and tracking. Higher-level tasks, such as understanding the interactions and social activities among individuals, are also crucial. Progress towards models that can fully understand scenes involving multiple people is hindered by a lack of sufficient annotated data for such high-level tasks. To address this challenge, we introduce Social-MAE, a simple yet effective transformer-based masked autoencoder framework for multi-person …

abstract arxiv autoencoder basic beyond cs.cv detection interactions masked autoencoder multiple people person progress representation representation learning social tasks tracking type understanding