Open-Vocabulary Audio-Visual Event Localization on OV-AVEBench (total)
67.1Accuracyfine-tuning baseline
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| fine-tuning baselinestrategy=fine-tuning2024.11 | 67.1 | 56.9 | 49.5 | 57.8 | |
| training-free baselinestrategy=training-free2024.11 | 59.2 | 46.7 | 34 | 46.6 | |
| AVEstrategy=fine-tuning2024.11 | 53.8 | 41.9 | 33.2 | 42.9 | |
| CLIP & CLAPstrategy=training-free2024.11 | 51.5 | 41.9 | 31.7 | 41.7 | |
| Video-LLaMA2strategy=training-free2024.11 | 48.9 | 39.1 | 29.8 | 39.3 | |
| MM-Pyramidstrategy=fine-tuning2024.11 | 48.4 | 40.2 | 35.2 | 41.2 | |
| PSPstrategy=fine-tuning2024.11 | 45.6 | 39.3 | 34.7 | 39.9 | |
| CMRAstrategy=fine-tuning2024.11 | 44.3 | 38.9 | 34.3 | 39.2 |