List your company

Image-to-Text Retrieval on COCO (test)

76.2R@1Grounded Recaptioning
18.27233.31148.3563.389Dec 19, 2024Mar 7, 2025May 24, 2025Aug 11, 2025Oct 28, 2025Jan 14, 2026Apr 3, 2026

Evaluation results

MethodLinks
Grounded Recaptioning2024.1276.2———
CoMPGFLOPs=29.24±0.322026.0475.9692.54——
MADTPGFLOPs=30.04±0.442026.0474.3891.5——
TIPS2024.1274———
X-VLM2024.1271.6———
VeCLIP2024.1267.8———
GOAL fine-tuned with DOCCIBackbone=ViT-L/14, Zero-shot=true2025.0366.586.0496.7698.62
SigLIPZero-shot=true2025.0965.7———
GOAL fine-tuned with DCIBackbone=ViT-L/14, Zero-shot=true2025.0364.585.196.5298.62
CoCa2024.1263.8———
Long-CLIPBackbone=ViT-L/14, Zero-shot=true2025.0363.1684.5296.4698.66
NegCLIPZero-shot=true2025.0959.3———
GOAL fine-tuned with DOCCIBackbone=ViT-B/16, Zero-shot=true2025.0359.2881.0294.8497.76
CLIP2024.1258.4———
GOAL fine-tuned with DCIBackbone=ViT-B/16, Zero-shot=true2025.0357.7880.6294.998
CLIPBackbone=ViT-L/14, Zero-shot=true2025.0357.6880.294.5897.84
Long-CLIP2024.1257.6———
DreamLIPZero-shot=true2025.0957.6———
Long-CLIPBackbone=ViT-B/16, Zero-shot=true2025.0357.2480.4294.2497.6
LongCLIPZero-shot=true2025.0957.2———
LSSZero-shot=true2025.0957.2———
CE-CLIPZero-shot=true2025.0955.3———
CLIPBackbone=ViT-B/16, Zero-shot=true2025.0354.1477.7493.3297.36
CLIPZero-shot=true2025.0950.4———
DACLLMZero-shot=true2025.0933.7———
DCIP1Zero-shot=true2025.0920.5———