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 3140 of 125 papers

TitleStatusHype
Identity-Guided Human Semantic Parsing for Person Re-IdentificationCode1
Correlating Edge, Pose with ParsingCode1
Hierarchical Human Parsing with Typed Part-Relation ReasoningCode1
Learning Compositional Neural Information Fusion for Human ParsingCode1
Learning from Synthetic AnimalsCode1
Graphonomy: Universal Human Parsing via Graph Transfer LearningCode1
Parsing R-CNN for Instance-Level Human AnalysisCode1
Adept: Annotation-Denoising Auxiliary Tasks with Discrete Cosine Transform Map and Keypoint for Human-Centric Pretraining0
SCHNet: SAM Marries CLIP for Human Parsing0
Progressive Limb-Aware Virtual Try-OnCode0
Show:102550
← PrevPage 4 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