HyperAIHyperAI超神经
首页算力平台文档资讯论文教程数据集百科SOTALLM 模型天梯GPU 天梯顶会
全站搜索
关于
HyperAIHyperAI超神经

Command Palette

Search for a command to run...

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

Paper TitleRepository
Mirasol3B69.8Mirasol3B: A Multimodal Autoregressive model for time-aligned and contextual modalities-
ONE-PEACE (Audio-Visual)68.2ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities
MAViL67.1--
EquiAV67.1EquiAV: Leveraging Equivariance for Audio-Visual Contrastive Learning
MMT (Audio-Visual)66.2Multiscale Multimodal Transformer for Multimodal Action Recognition-
CAV-MAE (Audio-Visual)65.9Contrastive Audio-Visual Masked Autoencoder
UAVM (Audio + Video)65.8UAVM: Towards Unifying Audio and Visual Models
Audiovisual Masked Autoencoder (Audiovisual, Single)65.0Audiovisual Masked Autoencoders
AVT (Audio-Visual)63.9AVT: Audio-Video Transformer for Multimodal Action Recognition-
ONE-PEACE (Audio-Only)59.6ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities
CAV-MAE (Audio-Only)59.5Contrastive Audio-Visual Masked Autoencoder
Audiovisual Masked Autoencoder (Audio-only, Single)57.2Audiovisual Masked Autoencoders
MAST (Audio Only)57.0Multiscale Audio Spectrogram Transformer for Efficient Audio Classification-
UAVM (Audio Only)56.5UAVM: Towards Unifying Audio and Visual Models
MMT (Video)56.1Multiscale Multimodal Transformer for Multimodal Action Recognition-
PlayItBackX353.7Play It Back: Iterative Attention for Audio Recognition
AVT (V)53.2AVT: Audio-Video Transformer for Multimodal Action Recognition-
MBT (A)52.3Attention Bottlenecks for Multimodal Fusion
MBT (V)51.2Attention Bottlenecks for Multimodal Fusion
UAVM (Video Only)49.9UAVM: Towards Unifying Audio and Visual Models
0 of 21 row(s) selected.