List your company

Sentence Retrieval on Flickr30K 1K (test)

418.5R SumSCO
413.652446.376479.1511.824Apr 26, 2024

Evaluation results

MethodLinks
SCOImage Representation=grid-based, Ensemble=true2024.04418.5———
CRGNImage Representation=region- and grid-based, Ensemble=false2024.04469.8———
IMRAMImage Representation=region-based, Ensemble=true2024.04484.2———
MLSLImage Representation=region- and grid-based, Ensemble=false2024.04494.2———
RAANImage Representation=region- and grid-based, Ensemble=true2024.04495.5———
CMCANImage Representation=region- and grid-based, Ensemble=false2024.04507.8———
VSRN++Image Representation=region-based, Ensemble=true2024.04508.9———
KIDRRImage Representation=region-based, Ensemble=true2024.04509.2———
RCTRNImage Representation=region-based, Ensemble=true2024.04509.6———
NAAFImage Representation=region-based, Ensemble=true2024.04513.2———
VSE∞Image Representation=region-based, Ensemble=false2024.04513.5———
EKDMImage Representation=region-based, Ensemble=true2024.04515.7———
HGANImage Representation=region- and grid-based, Ensemble=false2024.04518.3———
CHANImage Representation=region-based, Ensemble=false2024.04518.5———
DIMEImage Representation=region-based, Ensemble=true2024.04520———
CMSEIImage Representation=region-based, Ensemble=true2024.04521.3———
3SHNetImage Representation=region-based, Ensemble=false2024.04521.4———
VSE∞Image Representation=grid-based, Ensemble=false2024.04522.3———
AMEImage Representation=region-based, Ensemble=true2024.04522.8———
3SHNetImage Representation=grid-based, Ensemble=false2024.04525.5———
3SHNetImage Representation=region-based, Ensemble=true2024.04527.8———
3SHNetImage Representation=grid-based, Ensemble=true2024.04531.3———
Imp.Image Representation=region- and grid-based, Ensemble=true2024.04531.6———
VSE∞Image Representation=region- and grid-based, Ensemble=false2024.04532———
3SHNetImage Representation=region- and grid-based, Ensemble=false2024.04535.6———
3SHNetImage Representation=region- and grid-based, Ensemble=true2024.04539.7———
CAANBackbone=ResNet-101 BUTD [5]2023.03—70.191.697.2
GPOBackbone=ResNet-101 BUTD [5], Warm-up=true, Text Size Augmentation=true2023.03—7894.697.8
GPOBackbone=ResNet-101 BUTD [5], Warm-up=true, Text Size Augmentation=true, Ensemble=true, High Resolution Input=true2023.03—80.796.498.3
GSMNBackbone=ResNet-101 BUTD [5]2023.03—76.494.397.3
IMRAMBackbone=ResNet-101 BUTD [5]2023.03—74.19396.6
MMCABackbone=ResNet-101 BUTD [5]2023.03—74.292.896.4
RCARBackbone=ResNet-101 BUTD [5], Model Variant=T2I2023.03—77.893.696.9
RCARBackbone=ResNet-101 BUTD [5], Model Variant=I2T2023.03—74.79397.1
RCARBackbone=ResNet-101 BUTD [5], Model Variant=All2023.03—78.794.697.6
RCARBackbone=ResNet-101 BUTD [5], Warm-up=true, Text Size Augmentation=true, Model Variant=T2I2023.03—79.79597.4
RCARBackbone=ResNet-101 BUTD [5], Warm-up=true, Text Size Augmentation=true, Model Variant=I2T2023.03—76.995.598
RCARBackbone=ResNet-101 BUTD [5], Warm-up=true, Text Size Augmentation=true, Model Variant=All2023.03—82.39698.4
SCANBackbone=ResNet-101 BUTD [5], Warm-up=false2023.03—67.490.395.8
SCANBackbone=ResNet-101 BUTD [5], Warm-up=true, Text Size Augmentation=true2023.03—72.292.496.5
SGRAFBackbone=ResNet-101 BUTD [5]2023.03—77.894.197.4
SHANBackbone=ResNet-101 BUTD [5]2023.03—74.693.596.9
VSRNBackbone=ResNet-101 BUTD [5]2023.03—71.390.696
WCGLBackbone=ResNet-101 BUTD [5]2023.03—74.893.396.8