Recently, Transformer-based methods have been utilized to improve the performance of human action recognition. However, most of these studies assume that multi-view data is complete, which may not always be the case in real-world scenarios. Therefore, this paper presents a novel Multi-view Knowledge Distillation Transformer (MKDT) framework that consists of a teacher network and a student network. This framework aims to handle incomplete human action problems in real-world applications. Specifically, the multi-view knowledge distillation transformer uses a hierarchical vision transformer with shifted windows to capture more spatial-temporal information. Experimental results demonstrate that our framework outperforms the CNN-based method on three public datasets.
@article{arxiv.2303.14358,
title = {Multi-view knowledge distillation transformer for human action recognition},
author = {Ying-Chen Lin and Vincent S. Tseng},
journal= {arXiv preprint arXiv:2303.14358},
year = {2023}
}