Audio Classification On Esc 50
المقاييس
Top-1 Accuracy
النتائج
نتائج أداء النماذج المختلفة على هذا المعيار القياسي
جدول المقارنة
| اسم النموذج | Top-1 Accuracy |
|---|---|
| audio-visual-instance-discrimination-with | 89.2 |
| efficient-large-scale-audio-tagging-via | 97.45 |
| masked-modeling-duo-towards-a-universal-audio | 96.0 |
| m2d-clap-masked-modeling-duo-meets-clap-for | 97.4 |
| beats-audio-pre-training-with-acoustic | 98.1 |
| omnivec2-a-novel-transformer-based-network | 99.1 |
| lhgnn-local-higher-order-graph-neural | 96.2 |
| self-supervised-learning-by-cross-modal-audio | 84.8 |
| eranns-efficient-residual-audio-neural | 96.1 |
| environmental-sound-classification-on-the | 87.1 |
| omnivec-learning-robust-representations-with | 98.4 |
| النموذج 12 | 89.5 |
| ast-audio-spectrogram-transformer | 95.7 |
| cooperative-learning-of-audio-and-video | 82.3 |
| lerac-learning-rate-curriculum | 91.58 |
| self-supervised-learning-by-cross-modal-audio | 85.4 |
| look-listen-and-learn | 79.3 |
| multi-format-contrastive-learning-of-audio | 90.5 |
| internvideo2-scaling-video-foundation-models | 98.6 |
| dynamic-convolutional-neural-networks-as | 97.4 |
| end-to-end-audio-strikes-back-boosting | 95.25 |
| end-to-end-audio-strikes-back-boosting | 96.3 |
| end-to-end-audio-strikes-back-boosting | 92.15 |
| septr-separable-transformer-for-audio | 91.13 |
| masked-modeling-duo-towards-a-universal-audio | 97.2 |
| hts-at-a-hierarchical-token-semantic-audio | 97.0 |
| eat-self-supervised-pre-training-with | 96.0 |