Audio Classification On Vggsound
评估指标
Top 1 Accuracy
评测结果
各个模型在此基准测试上的表现结果
比较表格
| 模型名称 | Top 1 Accuracy |
|---|---|
| one-peace-exploring-one-general | 68.2 |
| mirasol3b-a-multimodal-autoregressive-model | 69.8 |
| multiscale-audio-spectrogram-transformer-for | 57.0 |
| audiovisual-masked-autoencoders | 57.2 |
| contrastive-audio-visual-masked-autoencoder | 65.9 |
| avt-audio-video-transformer-for-multimodal | 63.9 |
| play-it-back-iterative-attention-for-audio | 53.7 |
| audiovisual-masked-autoencoders | 65.0 |
| attention-bottlenecks-for-multimodal-fusion | - |
| avt-audio-video-transformer-for-multimodal | 53.2 |
| attention-bottlenecks-for-multimodal-fusion | 52.3 |
| contrastive-audio-visual-masked-autoencoder | 59.5 |
| multiscale-multimodal-transformer-for | 66.2 |
| 模型 14 | 67.1 |
| multiscale-multimodal-transformer-for | 56.1 |
| one-peace-exploring-one-general | 59.6 |
| uavm-a-unified-model-for-audio-visual | 65.8 |
| uavm-a-unified-model-for-audio-visual | 56.5 |
| uavm-a-unified-model-for-audio-visual | 49.9 |
| equiav-leveraging-equivariance-for-audio | 67.1 |
| attention-bottlenecks-for-multimodal-fusion | 51.2 |