Zero-shot object recognition embedded in model?

Hello! Thank you SO much for sharing this awesome model and all it's training data.

In the Aria AR demo, the highlighted objects had a name tag to them. How was this achieved?

The issue references the Aria AR demo and its highlighted object name tags, but names no repository file or test. Start by tracing the demo and model documentation to determine how those labels are produced; done means documenting a clear explanation of that pipeline.

Written by the indexing model from the issue text.