[Docs] question about Multi-View 3D Visual Grounding metric

[Fan123456-c]

Branch

main branch https://mmdetection3d.readthedocs.io/en/latest/

📚 The doc issue

I am confused about the accuracy of the model(Multi-view 3D visual grounding) you submitted： In your paper, it shows: but in github web, it shows: So if I reproduce your 3D grounding-full model, which benchmark should the accuracy I obtain be compared to?

Suggest a potential alternative/fix

No response

[Tai-Wang]

You can directly refer to the latest results shown in the GitHub repo. We will consider updating the results in the paper during polishing the EmbodiedScan and MMScan benchmarks in the following months.