List your company

Sentence-to-Image Retrieval on Flickr30k zero-shot generalization from MS-COCO (test)

55.8R@13SHNet
39.26443.55747.8552.143Apr 26, 2024

Evaluation results

MethodLinks
3SHNetVisual Representation=Region+Grid, Ensemble=false2024.0455.881.488.5490
3SHNetVisual Representation=Region, Ensemble=true2024.0454.579.586.8478.6
DIMEEnsemble=true, Source=derived from released pre-trained model2024.0453.779.286.5471.4
3SHNetVisual Representation=Grid, Ensemble=false2024.0453.779.687477.8
ESAEnsemble=false2024.0451.577.985.7467.4
VSE∞Ensemble=false, Source=derived from released pre-trained model2024.04507784.9462.8
DIMEEnsemble=false, Source=derived from released pre-trained model2024.0449.776.183.9453.2
SGRAFEnsemble=true2024.0448.173.981.9450.2
SGREnsemble=false2024.0440.568.677.7404.6
CVSEEnsemble=false2024.0439.968.677.2414.1