1 code implementation • 3 Dec 2023 • Wenjie Pei, Qizhong Tan, Guangming Lu, Jiandong Tian
In particular, we devise the anisotropic Deformable Spatio-Temporal Attention module as the core component of D$^2$ST-Adapter, which can be tailored with anisotropic sampling densities along spatial and temporal domains to learn spatial and temporal features specifically in corresponding pathways, allowing our D$^2$ST-Adapter to encode features in a global view in 3D spatio-temporal space while maintaining a lightweight design.