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 1–10 of 125 papers

TitleStatusHype
Adept: Annotation-Denoising Auxiliary Tasks with Discrete Cosine Transform Map and Keypoint for Human-Centric Pretraining—0
SCHNet: SAM Marries CLIP for Human Parsing—0
Progressive Limb-Aware Virtual Try-OnCode0
TruePose: Human-Parsing-guided Attention Diffusion for Full-ID Preserving Pose Transfer—0
MC-VTON: Minimal Control Virtual Try-On Diffusion Transformer—0
Exploring More from Multiple Gait Modalities for Human IdentificationCode0
Improving analytical color and texture similarity estimation methods for dataset-agnostic person reidentification—0
It Takes Two: Accurate Gait Recognition in the Wild via Cross-granularity AlignmentCode0
Features Reconstruction Disentanglement Cloth-Changing Person Re-Identification—0
MTMamba: Enhancing Multi-Task Dense Scene Understanding by Mamba-Based DecodersCode1
Show:102550
← PrevPage 1 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