Audio-Visual Question Answering on AVSD 1 (test)
152.9CIDErPAVE-7B (w/ audio)
Evaluation Results
| Method | Links | |
|---|---|---|
| PAVE-7B (w/ audio)Evaluation Protocol=Task-specific fine-tuning, TFLOPS=98.63, Total/Trainable Params=8.2B / 170.5M2025.03 | 152.9 | |
| LLaVA-OV-7B-FTEvaluation Protocol=Task-specific fine-tuning, TFLOPS=98.53, Total/Trainable Params=8.2B / 161.5M2025.03 | 124.9 | |
| COSTEvaluation Protocol=Task-specific fine-tuning2025.03 | 108.5 | |
| MTNEvaluation Protocol=Task-specific fine-tuning2025.03 | 98.5 | |
| CAT-7BEvaluation Protocol=Zero-shot2025.03 | 79 | |
| LLaVA-OV-7BEvaluation Protocol=Zero-shot, TFLOPS=98.53, Total/Trainable Params=8.2B / -2025.03 | 70.6 |