We present a system for concurrent activity recognition. To extract features associated with different activities, we propose a feature-to-activity attention that maps the extracted global features to sub-features associated with individual activities. To model the temporal associations of individual activities, we propose a transformer-network encoder that models independent temporal associations for each activity. To make the concurrent activity prediction aware of the potential associations between activities, we propose self-attention with an association mask. Our system achieved state-of-the-art or comparable performance on three commonly used concurrent activity detection datasets. Our visualizations demonstrate that our system is able to locate the important spatial-temporal features for final decision making. We also showed that our system can be applied to general multilabel classification problems.
@article{arxiv.1812.02817,
title = {Tri-axial Self-Attention for Concurrent Activity Recognition},
author = {Yanyi Zhang and Xinyu Li and Kaixiang Huang and Yehan Wang and Shuhong Chen and Ivan Marsic},
journal= {arXiv preprint arXiv:1812.02817},
year = {2018}
}