Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Contribute
Light
Dark
Valor
Report a problem with this record
text, image, audio · discriminative ·
anchor
Findings
IC-390
The parallelotope volume of modality embeddings from LanguageBind, VAST, and Valor on MSR-VTT is strongly correlated with their downstream R@1 retrieval performance