Submitted by Ozan √únal.

Submission data

Full nameDense 3D Visual Grounding Network
Publication titleThree Ways to Improve Verbo-visual Fusion for Dense 3D Visual Grounding
Publication authorsOzan Unal, Christos Sakaridis, Suman Saha, Fisher Yu, Luc Van Gool
Publication URLhttp://arxiv.org/abs/2309.04561
Input Data TypesUses XYZ coordinates,Uses RGB values
Programming language(s)Python
HardwareAMD EPYC 7742 64-Core CPU, GeForce RTX 3090, 526 GB RAM
Submission creation date20 Feb, 2023
Last edited12 Sep, 2023

Localization

Unique Unique Multiple Multiple Overall Overall
acc@0.25IoUacc@0.5IoUacc@0.25IoUacc@0.5IoUacc@0.25IoUacc@0.5IoU
0.86070.79230.47460.40910.56120.4950