D$^2$ST-Adapter: Disentangled-and-Deformable Spatio-Temporal Adapter for Few-shot Action Recognition

arXiv:2312.01431v2 Announce Type: replace
Abstract: Adapting large pre-trained image models to few-shot action recognition has proven to be an effective and efficient strategy for learning robust feature extractors, which is essential for few-shot learning. Typical fine-tuning based adaptation paradigm is prone to overfitting in the few-shot learning scenarios and offers little modeling flexibility for learning temporal features in video data. In this work we present the Disentangled-and-Deformable Spatio-Temporal Adapter (D$^2$ST-Adapter), which is a novel adapter tuning framework well-suited for few-shot …

abstract action recognition adapter arxiv cs.cv feature few-shot few-shot learning fine-tuning image modeling overfitting paradigm recognition robust strategy temporal type