Multi-modal Joint Retrieval on NYU
77.4Top-1 AccuracyLanguageBind
Evaluation Results
| Method | Links | |
|---|---|---|
| LanguageBindTask=Depth + RGB to Text2023.10 | 77.4 | |
| LanguageBindTask=RGB to Text2023.10 | 76 | |
| LanguageBindTask=Depth to Text2023.10 | 65.1 | |
| ImageBindTask=Depth to Text2023.10 | 54 |