Crowd Instance-level Human Parsing
The Crowd Instance-level Human Parsing (CIHP) dataset has 38,280 diverse human images. Each image in CIHP is labeled with pixel-wise annotations on 20 categories and instance-level identification. The dataset can be used for the human part segmentation task.
Source: Parsing R-CNN for Instance-Level Human Analysis
Image Source: https://arxiv.org/abs/1808.00157
Variants: CIHP
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Human Part Segmentation | Hulk(Finetune, ViT-L) | Hulk: A Universal Knowledge Translator … | 2023-12-04 |
| Human Part Segmentation | Hulk(Finetune, ViT-B) | Hulk: A Universal Knowledge Translator … | 2023-12-04 |
| Human Part Segmentation | UniHCP (finetune) | UniHCP: A Unified Model for … | 2023-03-06 |
| Human Part Segmentation | ResNet101 | Self-Correction for Human Parsing | 2019-10-22 |
| Human Part Segmentation | Parsing R-CNN + ResNext101 | Parsing R-CNN for Instance-Level Human … | 2018-11-30 |
| Human Part Segmentation | PGN + ResNet101 | Instance-level Human Parsing via Part … | 2018-08-01 |
Recent papers with results on this dataset: