Abstract
This paper proposes a novel few-shot action recognition framework that integrates the Transformer-based feature backbone into meta-learning. The proposed method includes pre-training the Video Transformer and utilizing metric-based meta-learning with the ProtoNet algorithm. Extensive experiments on benchmark datasets demonstrate that our approach achieves remarkable performance, surpassing baseline models and obtaining competitive results compared to state-of-the-art models. Additionally, we investigate the impact of supervised and self-supervised learning on video representation and evaluate the transferability of the learned representations in cross-domain scenarios. Our approach suggests a promising direction for exploring the combination of meta-learning with Video Transformer in the context of few-shot learning tasks, potentially contributing to the field of action recognition in various domains.