Cross-Modal Action Recognition in Egocentric Video Using Mamba: Integrating RGB and Hand Skeleton Streams via CLS Token Fusion Strategies 文章

ArXiv CS.CV2026-05-26NEWSen作者: Juan Ignacio Bustos Gorostegui, Maria Elena Buemi
查看原文 →
关系图谱

Cross-Modal Action Recognition in Egocentric Video Using Mamba: Integrating RGB and Hand Skeleton Streams via CLS Token Fusion Strategies · 相关人物

暂无数据