Multi Human Parsing On Pascal Person Part
評価指標
AP 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
モデル名 | AP 0.5 | Paper Title | Repository |
|---|---|---|---|
| Holistic instance-level | 40.60% | Holistic, Instance-Level Human Parsing | - |
| NAN | 59.70% | Understanding Humans in Crowded Scenes: Deep Nested Adversarial Learning and A New Benchmark for Multi-Human Parsing | - |
| MNC | 38.80% | Instance-aware Semantic Segmentation via Multi-task Network Cascades | - |
0 of 3 row(s) selected.