Pose Estimation On Mpii Human Pose
評価指標
PCKh-0.5
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
比較表
| モデル名 | PCKh-0.5 |
|---|---|
| human-pose-estimation-using-deep-consensus | 85.0 |
| human-pose-estimation-via-convolutional-part | 89.7 |
| deepcut-joint-subset-partition-and-labeling | 82.40 |
| unihcp-a-unified-model-for-human-centric | 93.2 |
| improved-training-of-binary-networks-for | 80.9 |
| learning-feature-pyramids-for-human-pose | 92.0 |
| quantized-densely-connected-u-nets-for | 91.2 |
| adversarial-posenet-a-structure-aware | 91.9 |
| distribution-aware-coordinate-representation | 90.6 |
| fast-human-pose-estimation | 91.1 |
| human-pose-estimation-via-convolutional-part | 89.7 |
| compositional-human-pose-regression | 86.4 |
| transpose-towards-explainable-human-pose | 93.5 |
| dite-hrnet-dynamic-lightweight-high | 87.6 |
| toward-fast-and-accurate-human-pose | 94.1 |
| deep-high-resolution-representation-learning | 92.3 |
| human-pose-as-compositional-tokens | 94.3 |
| deepercut-a-deeper-stronger-and-faster-multi | 88.52 |
| stacked-hourglass-networks-for-human-pose | 90.9 |
| unipose-unified-human-pose-estimation-in | 92.7 |
| human-pose-estimation-with-iterative-error | 81.3 |
| efficientpose-scalable-single-person-pose | 84.8 |
| bottom-up-and-top-down-reasoning-with | 82.4 |
| cu-net-coupled-u-nets | 89.4 |
| self-adversarial-training-for-human-pose | 91.8 |
| efficient-object-localization-using | 82.0 |
| convolutional-pose-machines | 88.52 |
| numerical-coordinate-regression-with | 89.5 |
| multi-context-attention-for-human-pose | 91.5 |
| matrix-and-tensor-decompositions-for-training | 82.5 |
| 2103-15320 | 90.4 |
| hierarchical-binary-cnns-for-landmark | 81.3 |
| knowledge-guided-deep-fractal-neural-networks | 91.2 |
| human-pose-estimation-with-spatial-contextual | 92.5 |
| improvement-multi-stage-model-for-human-pose | 93.9 |
| efficientpose-scalable-single-person-pose | 91.2 |
| multi-scale-structure-aware-network-for-human | 92.1 |
| learning-delicate-local-representations-for | 93.0 |
| deeply-learned-compositional-models-for-human | 92.3 |
| human-pose-as-compositional-tokens | 93.8 |
| bottom-up-and-top-down-reasoning-with | 81.1 |
| integral-human-pose-regression | 91.0 |
| jointly-optimize-data-augmentation-and | 91.5 |
| efficientpose-scalable-single-person-pose | 88.8 |
| rethinking-on-multi-stage-networks-for-human | 92.6 |
| t-net-parametrizing-fully-convolutional-nets | 87.5 |