Text-Infused Attention and Foreground-Aware Modeling for Zero-Shot Temporal Action Detection
–Neural Information Processing Systems
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
Neural Information Processing Systems
Oct-9-2025, 18:59:02 GMT
- Country:
- Asia > South Korea > Seoul > Seoul (0.04)
- Genre:
- Research Report > Experimental Study (0.93)
- Industry:
- Information Technology (0.46)
- Technology: