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 5160 of 125 papers

TitleStatusHype
C-DLinkNet: considering multi-level semantic features for human parsingCode0
Macro-Micro Adversarial Network for Human ParsingCode0
Look into Person: Joint Body Parsing & Pose Estimation Network and A New BenchmarkCode0
CCNet: Criss-Cross Attention for Semantic SegmentationCode0
DROP: Decouple Re-Identification and Human Parsing with Task-specific Features for Occluded Person Re-identificationCode0
Instance-level Human Parsing via Part Grouping NetworkCode0
Devil in the Details: Towards Accurate Single and Multiple Human ParsingCode0
Image Comes Dancing with Collaborative Parsing-Flow Video SynthesisCode0
Progressive Limb-Aware Virtual Try-OnCode0
Weakly and Semi Supervised Human Body Part Parsing via Pose-Guided Knowledge TransferCode0
Show:102550
← PrevPage 6 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