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 1–25 of 125 papers

TitleStatusHype
Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual TasksCode3
Text2Human: Text-Driven Controllable Human Image GenerationCode2
HumanBench: Towards General Human-centric Perception with Projector Assisted PretrainingCode2
InvPT: Inverted Pyramid Multi-task Transformer for Dense Scene UnderstandingCode2
Body Part-Based Representation Learning for Occluded Person Re-IdentificationCode2
4D-DRESS: A 4D Dataset of Real-world Human Clothing with Semantic AnnotationsCode2
Long-Term Person Re-identification with Dramatic Appearance Change: Algorithm and BenchmarkCode1
Hierarchical Human Parsing with Typed Part-Relation ReasoningCode1
milliFlow: Scene Flow Estimation on mmWave Radar Point Cloud for Human Motion SensingCode1
IntegratedPIFu: Integrated Pixel Aligned Implicit Function for Single-view Human ReconstructionCode1
Graphonomy: Universal Image Parsing via Graph Reasoning and TransferCode1
Identity-Guided Human Semantic Parsing for Person Re-IdentificationCode1
Learning Compositional Neural Information Fusion for Human ParsingCode1
Learning from Synthetic AnimalsCode1
Integrating Human Parsing and Pose Network for Human Action RecognitionCode1
Graphonomy: Universal Human Parsing via Graph Transfer LearningCode1
Deep Learning Technique for Human Parsing: A Survey and OutlookCode1
Human Co-Parsing Guided Alignment for Occluded Person Re-identificationCode1
CDGNet: Class Distribution Guided Network for Human ParsingCode1
DM-VTON: Distilled Mobile Real-time Virtual Try-OnCode1
Explore Human Parsing Modality for Action RecognitionCode1
End-to-end One-shot Human ParsingCode1
Correlating Edge, Pose with ParsingCode1
Differentiable Multi-Granularity Human Representation Learning for Instance-Aware Human Semantic ParsingCode1
Human Parsing Based Texture Transfer from Single Image to 3D Human via Cross-View ConsistencyCode1
Show:102550
← PrevPage 1 of 5Next →
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