List your company

Image-to-Text Retrieval on COCO-CN

87.4R@1ObjEmbed
14.28833.26952.2571.231Feb 14, 2022Oct 13, 2022Jun 12, 2023Feb 8, 2024Oct 7, 2024Jun 5, 2025Feb 2, 2026

Evaluation results

MethodLinks
ObjEmbedParameters=4B2026.0287.4————
ObjEmbedParameters=2B2026.0286————
UME-R1Parameters=2B2026.0283.6————
FG-CLIP2Backbone=ViT-So/162026.0283.2————
Qwen3-VL-EmbeddingParameters=2B2026.0283————
GMEParameters=7B2026.0281.7————
M2-EncoderModel Size=10B, Protocol=Zero-shot2024.0180.996.599.191.7—
MetaCLIP2Backbone=ViT-H/142026.0280.1————
GMEParameters=2B2026.0279.7————
AltCLIPModel Size=0.8B, Protocol=Zero-shot2024.0177.894.497.585—
M2-EncoderModel Size=1B, Protocol=Zero-shot2024.0174.694.29889.3—
VLM2Vec-V2Parameters=2B2026.0274.4————
Wukong_ViT-LBackbone=ViT-L, Evaluation Protocol=Fine-tuned2022.0273.3949888.6—
SigLIP2Backbone=ViT-So/162026.0272————
M2-EncoderModel Size=0.4B, Protocol=Zero-shot2024.017193.797.987.8—
FILIP_ViT-LBackbone=ViT-L, Evaluation Protocol=Fine-tuned2022.0269.191.396.986.5—
ERNIE-ViL 2.0Setting=Zero-shot2022.0969.192.997.1—86.1
ERNIE-ViL 2.0Protocol=Zero-shot2024.0169.192.997.186.1—
CLIP_ViT-BBackbone=ViT-B, Evaluation Protocol=Fine-tuned2022.0268.793.697.586.6—
CLIP_ViT-LBackbone=ViT-L, Evaluation Protocol=Fine-tuned2022.0268.39397.386.2—
FILIP_Swin-LBackbone=Swin-L, Evaluation Protocol=Fine-tuned2022.0268.393.997.186.7—
CLIP_Swin-LBackbone=Swin-L, Evaluation Protocol=Fine-tuned2022.026892.897.385.4—
VLM2VecParameters=2B2026.0267.9————
Wukong_Swin-LBackbone=Swin-L, Evaluation Protocol=Fine-tuned2022.0267.492.497.585.5—
Wukong_ViT-BBackbone=ViT-B, Evaluation Protocol=Fine-tuned2022.0265.890.396.684.6—
R2D2Setting=Zero-shot2022.0963.389.395.7—80.5
R2D2Backbone=ViT-L, Zero-shot=true2022.0563.389.395.7——
R2D2Model Size=0.4B, Protocol=Zero-shot2024.0163.389.395.780.5—
CN-CLIPModel Size=1B, Protocol=Zero-shot2024.016386.692.983—
CN-CLIPModel Size=0.2B, Protocol=Zero-shot2024.0162.286.694.979.7—
FILIPBackbone=ViT-L, Zero-shot=true2022.0256.982.490.975.2—
FILIPBackbone=ViT-L, Zero-shot=true2022.0556.982.490.9——
WukongBackbone=ViT-L, Zero-shot=true2022.0255.28190.675.1—
WukongSetting=Zero-shot2022.0955.28190.6—75.1
WukongBackbone=ViT-L, Zero-shot=true2022.0555.28190.6——
WukongModel Size=0.4B, Protocol=Zero-shot2024.0155.28190.675.1—
CLIPBackbone=ViT-B, Zero-shot=true2022.0252.879.688.973—
FILIP_ViT-BBackbone=ViT-B, Evaluation Protocol=Fine-tuned2022.0252.781.388.376.6—
TaisuModel Size=0.2B, Protocol=Zero-shot2024.0152.581.591.475.9—
CLIPBackbone=ViT-L, Zero-shot=true2022.02518089.772.1—
CLIPBackbone=ViT-L, Zero-shot=true2022.05518089.7——
CLIPBackbone=Swin-L, Zero-shot=true2022.0250.579.288.271.7—
FILIPBackbone=Swin-L, Zero-shot=true2022.0248.677.388.372.1—
WukongBackbone=ViT-B, Zero-shot=true2022.0248.377.888.871.9—
WukongBackbone=Swin-L, Zero-shot=true2022.0247.37888.370.8—
FILIPBackbone=ViT-B, Zero-shot=true2022.0237.866.477.961.8—
BriVLBackbone=N/A, Zero-shot=true2022.0217.141.757.537.4—
BriVLModel Size=1B, Protocol=Zero-shot2024.0117.141.757.537.4—
EmbNEvaluation Protocol=Fine-tuned2022.02———73.2—
LightningDOTEvaluation Protocol=Fine-tuned2022.02———88.4—
M3PSetting=Zero-shot2022.09————32.3
M³PEvaluation Protocol=Fine-tuned2022.02———86.2—
PARALLEL-EmbNEvaluation Protocol=Fine-tuned2022.02———76—
S-LIWEEvaluation Protocol=Fine-tuned2022.02———73.6—
UC2Evaluation Protocol=Fine-tuned2022.02———89.8—
UNITEREvaluation Protocol=Fine-tuned2022.02———87.3—