Audio Description Generation on MAD-eval-Named (test)
1.49OriginalityMM-Narrator
Evaluation results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| MM-NarratorLLM/LMM=GPT-4V, ExtCharBank integration=false2023.11 | 1.49 | 1.45 | 0.94 | 1.01 | 1.13 | 0.87 | 1.05 | 1.14 | |
| MM-NarratorLLM/LMM=GPT-4V, ExtCharBank integration=true2023.11 | 1.45 | 1.46 | 0.98 | 1.06 | 1.24 | 0.94 | 1.09 | 1.12 | |
| MM-NarratorLLM/LMM=GPT-4, ExtCharBank integration=false2023.11 | 1.05 | 1.03 | 0.52 | 0.7 | 0.66 | 0.57 | 0.7 | 0.61 | |
| VLogLLM/LMM=GPT-4, ExtCharBank integration=false2023.11 | 1.03 | 0.88 | 0.34 | 0.55 | 0.52 | 0.32 | 0.57 | 0.43 | |
| GTLLM/LMM=None2023.11 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | |
| MM-NarratorLLM/LMM=GPT-4, ExtCharBank integration=true2023.11 | 0.95 | 1.06 | 0.62 | 0.75 | 0.76 | 0.62 | 0.8 | 0.71 | |
| MM-VidLLM/LMM=GPT-4V, ExtCharBank integration=false2023.11 | 0.85 | 0.78 | 0.51 | 0.81 | 0.66 | 0.53 | 0.84 | 0.62 | |
| ClipCapLLM/LMM=GPT-2, ExtCharBank integration=false2023.11 | 0.43 | 0.42 | 0.26 | 0.35 | 0.35 | 0.26 | 0.42 | 0.33 |