Audio Classification

Bestes Modell: MBT (AS-500K training + Video)

Bestes Modell: EAT

Bestes Modell: CrissCross (AudioSet)

Bestes Modell: Audiovisual Masked Autoencoder (Audiovisual, Single)

Bestes Modell: InternVideo2

Bestes Modell: BTS

Bestes Modell: animal2vec

Bestes Modell: SNN with Dilated Convolution with Learnable Spacings

Bestes Modell: EAT

Bestes Modell: Event-SSM

Bestes Modell: CDIL

Bestes Modell: ONE-PEACE (Audio-Visual)

Bestes Modell: VocalSound Baseline