The reviewed record of science sign in
Pith

arxiv: 2205.09710 · v1 · pith:KNQN43TL · submitted 2022-05-19 · cs.CL · cs.AI· cs.CV

Voxel-informed Language Grounding

Rodolfo Corona , Shizhan Zhu , Dan Klein , Trevor Darrell This is my paper

Reviewed by Pithpith:KNQN43TLopen to challenge →

classification cs.CL cs.AIcs.CV
keywords languagegroundingmodelnaturalsnarevoxel-informedabsoluteaccuracy
0
0 comments X
read the original abstract

Natural language applied to natural 2D images describes a fundamentally 3D world. We present the Voxel-informed Language Grounder (VLG), a language grounding model that leverages 3D geometric information in the form of voxel maps derived from the visual input using a volumetric reconstruction model. We show that VLG significantly improves grounding accuracy on SNARE, an object reference game task. At the time of writing, VLG holds the top place on the SNARE leaderboard, achieving SOTA results with a 2.0% absolute improvement.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.