List your company

Audio Retrieval on Clotho

23.7R@1CLAP
-0.13686.051612.2418.4284Dec 15, 2022Jul 11, 2023Feb 4, 2024Aug 31, 2024Mar 27, 2025Oct 21, 2025May 18, 2026

Evaluation results

MethodLinks
CLAP2022.1223.759.948.9
MAViL2022.1223.363.649.5
OmniBind2026.0523.349.5—
MAViL2022.1217.253.541
LanguageBind2026.0516.752—
ML-ACTtrained without LAION-630K=true2022.1216.250.237.6
CLAP2022.1215.652.338.6
CyCLAPSsentence embedding training=unsupervised (Ls)2023.1014.935136.84
CyCLAP2023.1014.7448.5235.5
ML-ACTtrained without LAION-630K=true2022.1214.449.936.6
CLAP2023.1013.8848.934.16
FreeBind2026.0513.7——
CLAPSsentence embedding training=unsupervised (Ls)2023.1013.494935.6
ARNLQEmergent=false, Supervision=Supervised2023.0512.645.4—
LanguageBindAnchor Modality=Text2026.0412.144—
EmergentBridgeAnchor Modality=Text2026.0411.741.8—
EmergentBridgeAnchor Modality=Image, Evaluation Protocol=emergent zero-shot2026.041033.4—
CodeBind-VL2026.058.532.8—
AVFIC finetunedEmergent=false, Supervision=Supervised2023.058.438.6—
C-MCRAnchor Modality=–2026.048.3736.7—
ViT-LENS_Lanchor=I+T2023.118.131.2—
MMTtrained without LAION-630K=true2022.12734.622.7
CodeBind-IB2026.056.928.6—
ViT-LENS_Lanchor=I2023.116.829.6—
MMTtrained without LAION-630K=true2022.126.733.221.6
ImageBind-Hanchor=I2023.11628.4—
IMAGEBINDEmergent=true, Supervision=No audio and text supervision2023.05628.4—
ImageBindAnchor Modality=Image, Evaluation Protocol=emergent zero-shot2026.04628.4—
AudioCLIPAnchor Modality=–2026.043.220.3—
AVFIC2023.11317.5—
AVFICEmergent=false, Supervision=Uses audio and text loss2023.05317.5—
AVFICAnchor Modality=–2026.04317.5—
WAV2CLIPAnchor Modality=–2026.040.7812.1—