List your company

Image-to-Text Retrieval on COCO 1K (5-fold average test)

86.6R@1Ours†
63.7269.6675.681.54Nov 30, 2022

Evaluation results

MethodLinks
Ours†Backbone=ResNeXt-101 + BERT, CA (Cross-Attention)=false, Ensemble=true2022.1186.698.299.4549.9
OursBackbone=ResNeXt-101 + BERT, CA (Cross-Attention)=false, Ensemble=false2022.1186.397.899.4547.5
VSE∞†Backbone=ResNeXt-101 + BERT, CA (Cross-Attention)=false, Ensemble=true2022.1185.69899.4548.1
VSE∞Backbone=ResNeXt-101 + BERT, CA (Cross-Attention)=false, Ensemble=false2022.1184.598.199.4545.4
Ours†Backbone=Faster R-CNN + Bi-GRU, CA (Cross-Attention)=false, Ensemble=true2022.1180.696.398.8528
NAAFBackbone=Faster R-CNN + Bi-GRU, CA (Cross-Attention)=true, Ensemble=true2022.1180.596.598.8527.2
OursBackbone=Faster R-CNN + Bi-GRU, CA (Cross-Attention)=false, Ensemble=false2022.1179.896.298.6524.6
SGRAFBackbone=Faster R-CNN + Bi-GRU, CA (Cross-Attention)=true, Ensemble=true2022.1179.696.298.5524.3
VSE∞Backbone=Faster R-CNN + Bi-GRU, CA (Cross-Attention)=false, Ensemble=false2022.1178.59698.7520.8
IMRAMBackbone=Faster R-CNN + Bi-GRU, CA (Cross-Attention)=true, Ensemble=true2022.1176.795.698.5516.6
VSRNBackbone=Faster R-CNN + Bi-GRU, CA (Cross-Attention)=false, Ensemble=true2022.1176.294.898.2516.8
CAANBackbone=Faster R-CNN + Bi-GRU, CA (Cross-Attention)=true, Ensemble=false2022.1175.595.498.5515.6
SCANBackbone=Faster R-CNN + Bi-GRU, CA (Cross-Attention)=true, Ensemble=true2022.1172.794.898.4507.9
OursBackbone=ResNet-152 + Bi-GRU, CA (Cross-Attention)=false, Ensemble=false2022.1170.391.596.3493.2
PVSEBackbone=ResNet-152 + Bi-GRU, CA (Cross-Attention)=false, Ensemble=false2022.1169.291.696.6492.8
PCMEBackbone=ResNet-152 + Bi-GRU, CA (Cross-Attention)=false, Ensemble=false2022.1168.8———
VSE++Backbone=ResNet-152 + Bi-GRU, CA (Cross-Attention)=false, Ensemble=false2022.1164.69095.7478.6