Knowledge is Power: Advancing Few-shot Action Recognition with Multimodal Semantics from MLLMs
Crossref DOI link: https://doi.org/10.1007/s11263-026-02895-z
Published Online: 2026-05-27
Published Print: 2026-06
Update policy: https://doi.org/10.1007/springer_crossmark_policy
Xing, Jiazheng https://orcid.org/0000-0001-7280-249X
Xu, Chao
Yuan, Hangjie
Wang, Mengmeng
Dan, Jun
Qian, Hangwei
Liu, Yong
Text and Data Mining valid from 2026-05-27
Version of Record valid from 2026-05-27
Article History
Received: 22 September 2025
Accepted: 13 May 2026
First Online: 27 May 2026