Text-Infused Attention and Foreground-Aware Modeling for Zero-Shot Temporal Action Detection

Ti-FAD outperforms the state-of-the-art methods on ZST AD benchmarks by a large margin: 41.2% (+ 11.0%) on THUMOS14 and 32.0% (+ 5.4%) on ActivityNet v1.3. Code is available at: https://github.com/Y