List your company

Image-Text Retrieval on MSCOCO 5K

69.78I-T ScoreHarmoCLIP
0.744818.667436.5954.5126Aug 28, 2023Feb 3, 2024Jul 11, 2024Dec 18, 2024May 26, 2025Nov 1, 2025Apr 10, 2026

Evaluation results

MethodLinks
HarmoCLIPBackbone=ViT-B/16, Extra data / VLM augmentation=false2025.1169.78———
HarmoCLIPBackbone=ViT-B/16, Data Enhancement=false2025.1169.78———
Fully-FTArchitecture=VSE∞2023.0864.251.2468.9—
Fully-FTParams. (M)=201.2, Mem. (G)=176.82026.0464.251.2468.9—
Fully-FTParams. (M)=201.2, Mem. (G)=176.82026.0464.251.2468.9—
FG-CLIPBackbone=ViT-B/16, Extra data / VLM augmentation=true2025.1164.1———
FG-CLIPBackbone=ViT-B/16, Data Enhancement=true2025.1164.1———
Ours‡Params. (M)=11.8, Mem. (G)=25.42026.0463.448.7453.8—
Ours♠Params. (M)=11.4, Mem. (G)=25.2, QPS=14.832026.0463.248452.3—
SHERLParams. (M)=11.3, Mem. (G)=24.4, QPS=10.242026.0462.547.3450.8—
SHERLParams. (M)=11.3, Mem. (G)=24.42026.0462.547.3450.8—
Ours†Params. (M)=12.9, Mem. (G)=25.52026.0462.247.1449.1—
Ours♡Params. (M)=12.4, Mem. (G)=25.1, QPS=14.712026.0461.946.8448.1—
UniPTArchitecture=VSE∞2023.0861.145.9445.3—
UniPTParams. (M)=12.4, Mem. (G)=24.4, QPS=8.612026.0461.145.9445.3—
UniPTParams. (M)=12.4, Mem. (G)=24.42026.0461.145.9445.3—
LSTArchitecture=VSE∞2023.0857.843.1434.5—
LSTParams. (M)=9.7, Mem. (G)=24.42026.0457.843.1434.5—
LSTParams. (M)=9.7, Mem. (G)=24.42026.0457.843.1434.5—
EVA-CLIPBackbone=ViT-B/16, Extra data / VLM augmentation=false2025.1157.32———
EVA-CLIPBackbone=ViT-B/16, Data Enhancement=false2025.1157.32———
FineCLIPBackbone=ViT-B/16, Extra data / VLM augmentation=true2025.1154.5———
FineCLIPBackbone=ViT-B/16, Data Enhancement=true2025.1154.5———
CLIPBackbone=ViT-B/16, Extra data / VLM augmentation=false2025.1151.8———
CLIPBackbone=ViT-B/16, Data Enhancement=false2025.1151.8———
Partially⇓Architecture=VSE∞2023.0851.237.6401.7—
CLIPSelfBackbone=ViT-B/16, Extra data / VLM augmentation=false2025.1118.8———
CLIPSelfBackbone=ViT-B/16, Data Enhancement=false2025.1118.8———
RegionCLIPBackbone=ViT-B/16, Extra data / VLM augmentation=false2025.113.4———
RegionCLIPBackbone=RN50, Data Enhancement=false2025.113.4———
CHANVisual Backbone=Faster R-CNN, Text Encoder=BERT, Ensemble=false2026.03——443.9—
CLIPBackbone=ViT-B/16, Data Enhancement=false2025.11———37.6
CLIPSelfBackbone=ViT-B/16, Data Enhancement=false2025.11———16.1
CMSFVisual Backbone=Fast R-CNN, Text Encoder=BiGRU, Ensemble=false2026.03——432—
CMSFVisual Backbone=Faster R-CNN, Text Encoder=BERT, Ensemble=false2026.03——445.8—
EVA-CLIPBackbone=ViT-B/16, Data Enhancement=false2025.11———40.47
FG-CLIPBackbone=ViT-B/16, Data Enhancement=true2025.11———45.4
FineCLIPBackbone=ViT-B/16, Data Enhancement=true2025.11———40.2
HarmoCLIPBackbone=ViT-B/16, Data Enhancement=false2025.11———53.44
HREMVisual Backbone=Faster R-CNN, Text Encoder=BERT, Ensemble=false2026.03——444.1—
MaxMatchVisual Backbone=Faster R-CNN, Text Encoder=BERT, Ensemble=false2026.03——446.5—
MMCAVisual Backbone=Faster R-CNN, Text Encoder=BERT, Ensemble=false2026.03——416.4—
NAAFVisual Backbone=Fast R-CNN, Text Encoder=BiGRU, Ensemble=false2026.03——430.9—
RegionCLIPBackbone=RN50, Data Enhancement=false2025.11———2
SCANVisual Backbone=Fast R-CNN, Text Encoder=BiGRU, Ensemble=true2026.03——410.9—
TERANVisual Backbone=Faster R-CNN, Text Encoder=BERT, Ensemble=true2026.03——443.4—
USERVisual Backbone=Faster R-CNN, Text Encoder=BERT, Ensemble=false2026.03——445.5—
VSE∞Visual Backbone=Fast R-CNN, Text Encoder=BiGRU, Ensemble=false2026.03——421.9—
VSE∞Visual Backbone=Faster R-CNN, Text Encoder=BERT, Ensemble=false2026.03——434.2—
VSRNVisual Backbone=Fast R-CNN, Text Encoder=BiGRU, Ensemble=true2026.03——415.7—
VSRN++Visual Backbone=Faster R-CNN, Text Encoder=BERT, Ensemble=true2026.03——425.4—