List your company

Visual Grounding on RefPath 1.0 (test)

69.95AccuracyPKNet
55.275659.085362.89566.7047Feb 28, 2025

Evaluation results

MethodLinks
PKNetVisual/Text Encoder=RN50/BERT-B2025.0269.9563.49
D-MDETRVenue=TPAMI'24, Visual/Text Encoder=CLIP-B/CLIP-B2025.0264.9257.69
SimVGVenue=NeurIPS'24, Visual/Text Encoder=ViT-B/BERT-B2025.0263.9459.42
LLaVa-MedVenue=NeuIPS'23, Visual/Text Encoder=CLIP-L/LLaMa2025.0262.3257.96
TransCPVenue=TPAMI'24, Visual/Text Encoder=RN50/BERT-B2025.0261.7356.81
CLIPVGVenue=TMM'23, Visual/Text Encoder=CLIP-B/CLIP-B2025.0258.8953.97
TransVGVenue=ICCV'21, Visual/Text Encoder=RN50/BERT-B2025.0258.452.86
SeqTRVenue=ECCV'22, Visual/Text Encoder=DN53/BiGRU2025.0255.8451.96