Audio Classification on Vocal Sound
92.4ScoreFull Model
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Full ModelModel=VideoLLaMA2, Sparsity ratio=0%2025.04 | 92.4 | 100 | |
| Full ModelBackbone=VideoLLaMA2, Sparsity=0%2025.04 | 92.4 | — | |
| Full ModelBackbone=VideoLLaMA2 (7B), Sparsity Ratio=0%, Evaluation Protocol=Zero-shot2026.04 | 92.4 | 100 | |
| WandaModel=VideoLLaMA2, Sparsity ratio=60%2025.04 | 92.1 | 91 | |
| ECOFLaPModel=VideoLLaMA2, Sparsity ratio=60%2025.04 | 92.1 | 93.8 | |
| TAMPModel=VideoLLaMA2, Sparsity ratio=60%2025.04 | 92.1 | 95 | |
| WandaBackbone=VideoLLaMA2 (7B), Sparsity Ratio=60%, Evaluation Protocol=Zero-shot2026.04 | 92.1 | 91 | |
| ECoFLaPBackbone=VideoLLaMA2 (7B), Sparsity Ratio=60%, Evaluation Protocol=Zero-shot2026.04 | 92.1 | 93.8 | |
| TAMPBackbone=VideoLLaMA2 (7B), Sparsity Ratio=60%, Evaluation Protocol=Zero-shot2026.04 | 92.1 | 95 | |
| SparseGPTModel=VideoLLaMA2, Sparsity ratio=60%2025.04 | 91.9 | 88.5 | |
| SparseGPTBackbone=VideoLLaMA2 (7B), Sparsity Ratio=60%, Evaluation Protocol=Zero-shot2026.04 | 91.9 | 88.5 | |
| TopoVLM (Ours)Backbone=VideoLLaMA2 (7B), Sparsity Ratio=60%, Evaluation Protocol=Zero-shot2026.04 | 91.5 | 96.7 | |
| OWLModel=VideoLLaMA2, Sparsity ratio=60%2025.04 | 91.3 | 89.4 | |
| OWLBackbone=VideoLLaMA2 (7B), Sparsity Ratio=60%, Evaluation Protocol=Zero-shot2026.04 | 91.3 | 89.4 | |
| LLM-StreamlineBackbone=VideoLLaMA2 (7B), Sparsity Ratio=60%, Evaluation Protocol=Zero-shot2026.04 | 89.5 | 86.5 | |
| LLM-PrunerBackbone=VideoLLaMA2 (7B), Sparsity Ratio=60%, Evaluation Protocol=Zero-shot2026.04 | 84.7 | 82.1 | |
| ShortGPTBackbone=VideoLLaMA2, Sparsity=25%2025.04 | 77.9 | — | |
| OWLBackbone=VideoLLaMA2, Sparsity=25%2025.04 | 73.9 | — | |
| DASBackbone=VideoLLaMA2, Sparsity=25%2025.04 | 53.2 | — | |
| ECOFLaPBackbone=VideoLLaMA2, Sparsity=25%2025.04 | 22.9 | — | |
| Shortened LLaMABackbone=VideoLLaMA2, Sparsity=25%2025.04 | 18.3 | — | |
| MagnitudeModel=VideoLLaMA2, Sparsity ratio=60%2025.04 | 0 | 12.6 | |
| MagnitudeBackbone=VideoLLaMA2 (7B), Sparsity Ratio=60%, Evaluation Protocol=Zero-shot2026.04 | 0 | 12.6 |