Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment
2024-01-16
· ICLR 2024 poster ·
anchor
Findings
IC-981
ImageBind's indirect alignment through images degrades zero-shot performance on non-visual modalities and prevents emergent cross-modal retrieval