Pose Tracking on JHMDB
47PCK@0.1ToBo
Evaluation results
| Method | Links | ||
|---|---|---|---|
| ToBoPre-trained=Kinetics-400, Epochs=4002025.07 | 47 | 74.8 | |
| PhiNet v2Backbone=ViT-S/16, Pre-training=Kinetics-400, Pre-training Epochs=4002025.05 | 45 | 73.6 | |
| PhiNet v2Type=Non-contrastive, Architecture=ViT-S/16, Pre-training dataset=Kinetics-400, Pre-training epochs=4002025.05 | 45 | 73.6 | |
| RSPBackbone=ViT-S/16, Pre-training=Kinetics-400, Pre-training Epochs=4002025.05 | 44.8 | 73.3 | |
| RSPType=Autoencoder, Architecture=ViT-S/16, Pre-training dataset=Kinetics-400, Pre-training epochs=4002025.05 | 44.8 | 73.3 | |
| SiamMAEPre-trained=Kinetics-400, Epochs=4002025.07 | 44.7 | 73 | |
| JEPA-like methodBackbone=ViT-S/16, Pre-training=Kinetics-400, Pre-training Epochs=4002025.05 | 44.7 | 73 | |
| SiamMAEType=Autoencoder, Architecture=ViT-S/16, Pre-training dataset=Kinetics-400, Pre-training epochs=4002025.05 | 44.7 | 73 | |
| RSPPre-trained=Kinetics-400, Epochs=4002025.07 | 44.6 | 73.4 | |
| CropMAEBackbone=ViT-S/16, Pre-training=Kinetics-400, Pre-training Epochs=4002025.05 | 43.4 | 71.8 | |
| CropMAEType=Autoencoder, Architecture=ViT-S/16, Pre-training dataset=Kinetics-400, Pre-training epochs=4002025.05 | 43.4 | 71.8 | |
| MAEPre-trained=Kinetics-400, Epochs=4002025.07 | 43 | 71.3 | |
| MAEType=Autoencoder, Architecture=ViT-S/16, Pre-training dataset=Kinetics-400, Pre-training epochs=4002025.05 | 43 | 71.3 | |
| CropMAEPre-trained=Kinetics-400, Epochs=4002025.07 | 42.9 | 71.1 | |
| DINOPre-trained=Kinetics-400, Epochs=4002025.07 | 41.1 | 70.3 | |
| DinoType=Non-contrastive, Architecture=ViT-S/16, Pre-training dataset=Kinetics-400, Pre-training epochs=4002025.05 | 41.1 | 70.3 | |
| MoCo v3Pre-trained=Kinetics-400, Epochs=4002025.07 | 38.4 | 67.6 | |
| MoCo v3Type=Contrastive, Architecture=ViT-S/16, Pre-training dataset=Kinetics-400, Pre-training epochs=4002025.05 | 38.4 | 67.6 | |
| SimCLRPre-trained=Kinetics-400, Epochs=4002025.07 | 37.9 | 66.1 | |
| SimCLRType=Contrastive, Architecture=ViT-S/16, Pre-training dataset=Kinetics-400, Pre-training epochs=4002025.05 | 37.9 | 66.1 |