The MHP dataset contains multiple persons captured in real-world scenes with pixel-level fine-grained semantic annotations in an instance-aware setting.
Source: Multiple-Human Parsing in the WildBenchmarks
| Trend | Task | Dataset Variant | Best Model | Paper | Code |
|---|---|---|---|---|---|
|
MHP v2.0
|
UniParser
|
|||
|
MHP v1.0
|
NAN
|
|||
|
MHP v2.0
|
Parsing R-CNN + ResNext101
|
Papers
| Paper | Code | Results | Date | Stars |
|---|
