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 41–50 of 125 papers

TitleStatusHype
Long-Term Person Re-identification with Dramatic Appearance Change: Algorithm and BenchmarkCode1
Google Coral-based edge computing person reidentification using human parsing combined with analytical method—0
RepParser: End-to-End Multiple Human Parsing with Representative Parts—0
Identity-Sensitive Knowledge Propagation for Cloth-Changing Person Re-identificationCode0
Combining human parsing with analytical feature extraction and ranking schemes for high-generalization person reidentification—0
AIParsing: Anchor-free Instance-level Human Parsing—0
Text2Human: Text-Driven Controllable Human Image GenerationCode2
Human-Centered Prior-Guided and Task-Dependent Multi-Task Representation Learning for Action Recognition Pre-Training—0
Versatile Multi-Modal Pre-Training for Human-Centric PerceptionCode1
InvPT: Inverted Pyramid Multi-task Transformer for Dense Scene UnderstandingCode2
Show:102550
← PrevPage 5 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