GSLTA-CDFSAR: Global Sequences and Local Tuples Alignment for Cross-Domain Few-Shot Action Recognition

Open Webpage

Fei Guo, Qi Han, Xuetao Zhang, Li Zhu, Jing Sun

Published: 2025, Last Modified: 09 Oct 2025Knowl. Based Syst. 2025EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•Our work focuses on the field of cross-domain few-shot action recognition.•Our work uses target domain frames to augment source domain videos.•Our work includes Domain Temporal Branch and the Local-Global Adapter Branch.