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 111120 of 125 papers

TitleStatusHype
Image Comes Dancing with Collaborative Parsing-Flow Video SynthesisCode0
Understanding Humans in Crowded Scenes: Deep Nested Adversarial Learning and A New Benchmark for Multi-Human ParsingCode0
CCNet: Criss-Cross Attention for Semantic SegmentationCode0
Part Representation Learning with Teacher-Student Decoder for Occluded Person Re-identificationCode0
Self-Correction for Human ParsingCode0
Identity-Sensitive Knowledge Propagation for Cloth-Changing Person Re-identificationCode0
Beyond Human Parts: Dual Part-Aligned Representations for Person Re-IdentificationCode0
Self-Supervised Learning via Conditional Motion PropagationCode0
Adaptive Temporal Encoding Network for Video Instance-level Human ParsingCode0
Progressive Limb-Aware Virtual Try-OnCode0
Show:102550
← PrevPage 12 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