List your company
ResearchFormerly WizWand

2D Pose Estimation on AIC (test)

37.1mAPHulk-FT
31.69233.09634.535.904Dec 4, 2023
Updated 8mo ago

Evaluation results

MethodLinks
Hulk-FTBackbone=ViT-L, Model Category=Generalist, Input Resolution=256×192, Evaluation Protocol=Fine-tuned2023.1237.1
Hulk-FTBackbone=ViT-L, Input Resolution=256x192, Fine-tuned=true2023.1237.1
PATHBackbone=ViT-L, Model Category=Pretraining, Input Resolution=256×1922023.1236.3
HulkBackbone=ViT-L, Model Category=Generalist, Input Resolution=256×192, Evaluation Protocol=Direct2023.1236.3
PATHBackbone=ViT-L, Input Resolution=256x1922023.1236.3
HulkBackbone=ViT-L, Input Resolution=256x192, Fine-tuned=false2023.1236.3
Hulk-FTBackbone=ViT-B, Model Category=Generalist, Input Resolution=256×192, Evaluation Protocol=Fine-tuned2023.1235.6
Hulk-FTBackbone=ViT-B, Input Resolution=256x192, Fine-tuned=true2023.1235.6
PATHBackbone=ViT-B, Model Category=Pretraining, Input Resolution=256×1922023.1235
PATHBackbone=ViT-B, Input Resolution=256x1922023.1235
ViTPose-LBackbone=ViT-L, Model Category=Specialist, Input Resolution=256×192, Evaluation Protocol=Our implementation2023.1234.5
HulkBackbone=ViT-B, Model Category=Generalist, Input Resolution=256×192, Evaluation Protocol=Direct2023.1234.5
ViTPose-LBackbone=ViT-L, Input Resolution=256x192, Implementation=Our implementation2023.1234.5
HulkBackbone=ViT-B, Input Resolution=256x192, Fine-tuned=false2023.1234.5
ViTPose++-LBackbone=ViT-L, Input Resolution=256x192, Multiple Datasets=true2023.1234.3
UniHCP-FTBackbone=ViT-B, Model Category=Generalist, Input Resolution=256×192, Evaluation Protocol=Fine-tuned2023.1233.6
UniHCP-FTBackbone=ViT-B, Input Resolution=256x192, Fine-tuned=true2023.1233.6
UniHCPBackbone=ViT-B, Model Category=Generalist, Input Resolution=256×192, Evaluation Protocol=Direct2023.1232.5
UniHCPBackbone=ViT-B, Input Resolution=256x192, Fine-tuned=false2023.1232.5
HAPBackbone=ViT-B, Model Category=Pretraining, Input Resolution=256×1922023.1232.3
HAPBackbone=ViT-B, Input Resolution=256x1922023.1232.3
ViTPose-BBackbone=ViT-B, Model Category=Specialist, Input Resolution=256×192, Evaluation Protocol=Our implementation2023.1232
ViTPose-BBackbone=ViT-B, Input Resolution=256x192, Implementation=Our implementation2023.1232
ViTPose++-BBackbone=ViT-B, Input Resolution=256x192, Multiple Datasets=true2023.1231.9