Audio-Visual Speaker Identification on AV-Speaker
47.1Original ScoreQwen2.5-Omni
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Qwen2.5-OmniLLM=Qwen2.5-7B, Use Audio=✓, Latency (s)=4.122025.09 | 47.1 | 50.5 | |
| UniMambaMiaLLM=Qwen2-7B, Use Audio=✓, Latency (s)=1.602025.09 | 46.6 | 47.3 | |
| LLaVA-VideoLLM=Qwen2-7B, Use Audio=×, Latency (s)=1.002025.09 | 43.5 | 43 | |
| Qwen2-VLLLM=Qwen2-7B, Use Audio=×, Latency (s)=1.632025.09 | 42.6 | 43.5 | |
| LLaVA-OneVisionLLM=Qwen2-7B, Use Audio=×, Latency (s)=0.972025.09 | 41.8 | 39.3 | |
| LLaVA-NeXT-Vid.LLM=Vicuna-7B, Use Audio=×, Latency (s)=0.242025.09 | 27.4 | 5.6 |