Year: 2023
Type: preprint
Abstract: 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.
Source: arXiv (Cornell University)
Authors: Lin, Ying-Chen, Tseng, Vincent S.
Institution: National Yang Ming Chiao Tung University
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4361193049