Temporal Captioning on FineAction-CGR (test)
66B@4SlowFocus
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| SlowFocusLLM=Vicuna-7B, LoRA=true2026.02 | 66 | 41 | 70 | 3.27 | |
| LLaMA-VID†LLM=Vicuna-7B, LoRA=true, Re-trained on stage 3's data=true2026.02 | 23 | 20 | 37 | 1.03 | |
| LLaMA-VIDLLM=Vicuna-7B, LoRA=false2026.02 | 16 | 12 | 11 | 0.23 | |
| Video-ChatGPTLLM=Vicuna-7B, LoRA=false2026.02 | 15 | 12 | 10 | 0.21 | |
| VideoLLaMALLM=Vicuna-7B, LoRA=false2026.02 | 6 | 9 | 8 | 0.13 | |
| VTimeLLMLLM=Vicuna-7B, LoRA=true2026.02 | 5 | 9 | 8 | 0.12 |