mmpose HRNet-w32 (w/ImageNet pretrained weights)

Reported on 4 benchmarks across 4 tasks · 1 paper · 4 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision2 results

Pose EstimationonHorse-10
Normalized Error (OOD)· uses extra data· 2022-03-14
0.179
best: 0.1091 (SuperAnimal-Quadruped HRNet-w32)
SOTA
SuperAnimal pretrained pose estimation models for behavioral analysis arXiv:2203.07436
Animal Pose EstimationonHorse-10
Normalized Error (OOD)· uses extra data· 2022-03-14
0.179
best: 0.1091 (SuperAnimal-Quadruped HRNet-w32)
SOTA
SuperAnimal pretrained pose estimation models for behavioral analysis arXiv:2203.07436

Methodology1 result

3DonHorse-10
Normalized Error (OOD)· uses extra data· 2022-03-14
0.179
best: 0.1091 (SuperAnimal-Quadruped HRNet-w32)
SOTA
SuperAnimal pretrained pose estimation models for behavioral analysis arXiv:2203.07436

Audio1 result

1 Image, 2*2 StitchionHorse-10
Normalized Error (OOD)· uses extra data· 2022-03-14
0.179
best: 0.1091 (SuperAnimal-Quadruped HRNet-w32)
SOTA
SuperAnimal pretrained pose estimation models for behavioral analysis arXiv:2203.07436