Our new X account is live! Follow @wizwand_team for updates

Home/Benchmarks

Visual Grounding on RefCOCO

9.62Acc@0.5

LG-VQ

Updated 2d ago

Evaluation Results

Method	Links
LG-VQ 2024.05		9.62
VQCT 2024.05		9.46
VQ-GAN 2024.05		9.14

SOTA Paper

LG-VQ

LG-VQ: Language-Guided Codebook Learning

Dataset

RefCOCO

Follow for update

@wizwand_team Discord

Related Benchmarks

Text-to-image synthesis on CelebA-HQ Semantic Synthesis on CelebA-HQ Image Captioning on CUB-200 Unconditional Image Generation on CelebA-HQ Image Reconstruction on TextCaps (test)

© 2026 wizwand

Blog Contact Changelog

Privacy Policy Terms of Service FAQs