CMU, Oxford & Facebook Cross-Lingual Vision-Language Model Achieves New SOTA in Zero-Shot Setting | CMU, Oxford & Facebook Cross-Lingual Vision-Language Model Achieves New SOTA in Zero-Shot SettingSynced
A research team from CMU, Oxford and Facebook AI proposes a vision-language model that, when trained on a source language, can be applied to different languages without additional annotated trainin...
Source: Synced | AI Technology & Industry Review
A research team from CMU, Oxford and Facebook AI proposes a vision-language model that, when trained on a source language, can be applied to different languages without additional annotated training data.