ST-CLIP: Learning SpatioTemporal CLIP with GraphTransformer for Action Recognition
Year: 2024
Type: conference-paper
Authors: Zhenxing Zheng, Jing Lyu, Junlong Gong, Gaoyun An
Institution: Xi’an University of Posts and Telecommunications
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: closed
OpenAlex ID: W4406754280