Classification on VGGSound

Metric: Top 1 Accuracy (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide augmentations

#	Model↕	Top 1 Accuracy▼	Augmentations	Paper	Date↕	Code
1	Mirasol3B	69.8	No	Mirasol3B: A Multimodal Autoregressive model for...	2023-11-09	-
2	CA2ST(B/16)	68.3	No	CA^2ST: Cross-Attention in Audio, Space, and Tim...	2025-03-30	-
3	ONE-PEACE (Audio-Visual)	68.2	Yes	ONE-PEACE: Exploring One General Representation ...	2023-05-18	Code
4	CAVA(B/16)	68.2	No	CA^2ST: Cross-Attention in Audio, Space, and Tim...	2025-03-30	-
5	MAViL	67.1	Yes	-	-	-
6	EquiAV	67.1	Yes	EquiAV: Leveraging Equivariance for Audio-Visual...	2024-03-14	Code
7	MMT (Audio-Visual)	66.2	No	-	-	-
8	CAV-MAE (Audio-Visual)	65.9	Yes	Contrastive Audio-Visual Masked Autoencoder	2022-10-02	Code
9	UAVM (Audio + Video)	65.8	Yes	UAVM: Towards Unifying Audio and Visual Models	2022-07-29	Code
10	Audiovisual Masked Autoencoder (Audiovisual, Single)	65	No	Audiovisual Masked Autoencoders	2022-12-09	Code
11	AVT (Audio-Visual)	63.9	No	-	-	-
12	ONE-PEACE (Audio-Only)	59.6	Yes	ONE-PEACE: Exploring One General Representation ...	2023-05-18	Code
13	CAV-MAE (Audio-Only)	59.5	Yes	Contrastive Audio-Visual Masked Autoencoder	2022-10-02	Code
14	Audiovisual Masked Autoencoder (Audio-only, Single)	57.2	No	Audiovisual Masked Autoencoders	2022-12-09	Code
15	MAST (Audio Only)	57	No	Multiscale Audio Spectrogram Transformer for Eff...	2023-03-19	-
16	UAVM (Audio Only)	56.5	Yes	UAVM: Towards Unifying Audio and Visual Models	2022-07-29	Code
17	MMT (Video)	56.1	No	-	-	-
18	PlayItBackX3	53.7	No	Play It Back: Iterative Attention for Audio Reco...	2022-10-20	Code
19	AVT (V)	53.2	No	-	-	-
20	MBT (A)	52.3	No	Attention Bottlenecks for Multimodal Fusion	2021-06-30	Code
21	MBT (V)	51.2	No	Attention Bottlenecks for Multimodal Fusion	2021-06-30	Code
22	UAVM (Video Only)	49.9	Yes	UAVM: Towards Unifying Audio and Visual Models	2022-07-29	Code