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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 81–90 of 125 papers

TitleStatusHype
Towards Rich Feature Discovery With Class Activation Maps Augmentation for Person Re-Identification—0
Mutual Learning to Adapt for Joint Human Parsing and Pose Estimation—0
Capture Dense: Markerless Motion Capture Meets Dense Pose Estimation—0
Nondiscriminatory Treatment: a straightforward framework for multi-human parsing—0
C+1 Loss: Learn to Classify C Classes of Interest and the Background Class Differentially—0
Parsing is All You Need for Accurate Gait Recognition in the Wild—0
Blended Grammar Network for Human Parsing—0
Part-Attention Based Model Make Occluded Person Re-Identification Stronger—0
Part-Aware Context Network for Human Parsing—0
Towards Unified Human Parsing and Pose Estimation—0
Show:102550
← PrevPage 9 of 13Next →
All datasets4D-DRESSPASCAL Context

Benchmark Results

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