List your company

Cross-modal retrieval on AudioCaps (test)

59.1R@1OmniBind
-0.90814.67130.2545.829Apr 1, 2022Sep 2, 2022Feb 4, 2023Jul 8, 2023Dec 10, 2023May 12, 2024Oct 14, 2024

Evaluation results

MethodLinks
OmniBindmultimodal query=true2024.1059.183.8————
OmniBind2024.105680.8————
CART2024.0649.879.886.862——
Laion-CLAPmultimodal query=true2024.1045.380.3————
Laion-CLAP2024.104479.5————
AVRPretraining=VideoCC3M, Modality=Audio+Visual, Zero-shot=false2022.0443.2—88.9———
ONE-PEACETraining Status=Pretrained2024.0642.577.588.4———
HTSAT-BERT2024.0642.276.587.1———
AVRPretraining=None, Modality=Audio+Visual, Zero-shot=false2022.0441.4—85.3———
Multi-TTAAudio Encoder=PANNs (ResNet38), Text Encoder=BERT, Data Augmentation=PairMix, Test-Time Augmentation=Multi-TTA2022.1040.27487.2—97.66.3
VALORVariant=B2024.0640.173.983.1———
PairMixAudio Encoder=PANNs (ResNet38), Text Encoder=BERT, Data Augmentation=PairMix2022.104073.186.8—97.36.6
BaselineAudio Encoder=PANNs (ResNet38), Text Encoder=BERT2022.1037.97182.7—97.48.8
CLAP-HTSAT2024.0636.171.883.9———
AVRPretraining=VideoCC3M, Modality=Audio, Zero-shot=false2022.0435.5—84.5———
AVRPretraining=HowTo100M, Modality=Audio, Zero-shot=false2022.0433.7—83.2———
AVRPretraining=None, Modality=Audio, Zero-shot=false2022.0432—82.3———
SOTAPretraining=None, Modality=Audio+Visual, Zero-shot=false2022.0428.1—79———
SOTAPretraining=None, Modality=Audio, Zero-shot=false2022.0424.3—72.1———
LanguageBindModality=Audio2024.0615.249.867.629.8——
AVRPretraining=VideoCC3M, Modality=Audio+Visual, Zero-shot=true2022.0410.6—45.2———
AVRPretraining=VideoCC3M, Modality=Audio, Zero-shot=true2022.048.7—37.7———
AVRPretraining=HowTo100M, Modality=Audio, Zero-shot=true2022.041.4—6.5———