Multi-Human Parsing 벤치마크
Multi-Human Parsing on PASCAL-Part
AP 0.5
- 2015-12-14 — MNC: AP 0.5 38.8
- 2017-09-11 — Holistic instance-level: AP 0.5 40.6
- 2018-04-10 — NAN: AP 0.5 59.7
| Rank | Model | AP 0.5 | Paper | Code | Year |
|---|---|---|---|---|---|
| 1 | NAN | 59.70% | Understanding Humans in Crowded Scenes: Deep Nested Adversarial Learning and A New Benchmark for Multi-Human Parsing | open-mmlab/mmpose · ZhaoJ9014/Multi-Human-Parsing | 2018 |
| 2 | Holistic instance-level | 40.60% | Holistic, Instance-Level Human Parsing | torrvision/caffe-tvg | 2017 |
| 3 | MNC | 38.80% | Instance-aware Semantic Segmentation via Multi-task Network Cascades | daijifeng001/MNC · jfc4050/detect-to-track | 2015 |