TN-ZSTAD: Transferable Network for Zero-Shot Temporal Activity Detection

Abstract

TN-ZSTAD introduces a novel approach to zero-shot temporal activity detection (ZSTAD) in long untrimmed videos. By integrating an activity graph transformer with zero-shot detection techniques, it addresses the challenge of recognizing and localizing unseen activities. Experiments on THUMOS'14, Charades, and ActivityNet datasets validate its superior performance in detecting unseen activities.