SOTAVerified

Human Parsing

Human parsing is the task of segmenting a human image into different fine-grained semantic parts such as head, torso, arms and legs.

( Image credit: Multi-Human-Parsing (MHP) )

Papers

Showing 7180 of 125 papers

TitleStatusHype
Progressive One-shot Human ParsingCode1
Human Parsing Based Texture Transfer from Single Image to 3D Human via Cross-View ConsistencyCode1
Renovating Parsing R-CNN for Accurate Multiple Human ParsingCode1
Robust Person Re-Identification through Contextual Mutual Boosting0
Affinity-aware Compression and Expansion Network for Human Parsing0
Blended Grammar Network for Human Parsing0
Identity-Guided Human Semantic Parsing for Person Re-IdentificationCode1
From Real to Synthetic and Back: Synthesizing Training Data for Multi-Person Scene Understanding0
Part-Aware Context Network for Human Parsing0
Correlating Edge, Pose with ParsingCode1
Show:102550
← PrevPage 8 of 13Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Graphonomy_InnermAcc0.97Unverified
2CDGNet_InnermAcc0.92Unverified
3Graphonomy_OutermAcc0.92Unverified
4SCHP_InnermAcc0.91Unverified
5CDGNet_OutermAcc0.89Unverified
6SCHP_OutermAcc0.86Unverified
#ModelMetricClaimedVerifiedStatus
1InvPTmIoU67.61Unverified