Gayatri Sudhir Deshmukh

GRIZAL: Generative Prior-guided Zero-Shot Temporal Action Localization

Zero-shot temporal action localization (TAL) aims to temporally localize actions in videos without prior training examples. To address the challenges of TAL, we offer GRIZAL, a model that uses multimodal embeddings and dynamic motion cues to localize actions effectively. GRIZAL achieves sample diver…