Hantao Qi

Protect to Adapt: Orthogonal Subspace Control with Ranked Negative-Prompt Curriculum for Few-Shot Action Recognition

Adapting Vision-Language Models (VLMs) to few-shot action recognition (FSAR) often trades accuracy for stability: task-specific gains can trigger catastrophic forgetting of domain-general knowledge and reduce inter-class margins. In few-shot episodes, each query is contrasted with only one positive