Datasets › OCHuman

OCHuman

Introduced by Song-Hai Zhang et al. in Pose2Seg: Detection Free Human Instance Segmentation archive 2025-07-28

This dataset focuses on heavily occluded human with comprehensive annotations including bounding-box, humans pose and instance mask. This dataset contains 13,360 elaborately annotated human instances within 5081 images. With average 0.573 MaxIoU of each person, OCHuman is the most complex and challenging dataset related to human.

Source: https://github.com/liruilong940607/OCHumanApi Image Source: https://github.com/liruilong940607/OCHumanApi

Benchmarks archive 2025-07-28

All 6 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

Papers archive 2025-07-28

papers with a benchmark row: 29 · with a code link: 24 · where Syntology ran a sample: 9 (9 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology

Show: all papers with a benchmark rowonly where code ran (9 of 29 with a benchmark row: 9 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 29 of 29 with a leaderboard row on this dataset's benchmarks, newest first by the archive's date (ties by slug; undated papers last).

The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset, not that list; the archive's count for this dataset is 66. The Syntology column is from Syntology's graph, stated per sample; it is not part of any archive number. A line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified” (C is a part of N, never taken away from it); the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. When the archive marks a repository official for the paper, the cell starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record.

PaperCodeResultsDateSamples run Syntology
PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation 1 1 23 May 2025 not harvested
Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle 1 6 2 Dec 2024 not harvested
Crowd-SAM: SAM as a Smart Annotator for Object Detection in Crowded Scenes 1 1 16 Jul 2024 not harvested
You Only Learn One Query: Learning Unified Human Query for Single-Stage Multi-Person Multi-Task Human-Centric Perception 1 3 9 Dec 2023 not harvested
Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity 1 1 13 Jun 2023 official (archive's flag): 4 ran · 4 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified
Object-Centric Multi-Task Learning for Human Instances 0 3 13 Mar 2023 not harvested
RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose 1 1 13 Mar 2023 not harvested
UniHCP: A Unified Model for Human-Centric Perceptions 1 1 6 Mar 2023 official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified (10 pointer-only for licence)
SEFD: Learning to Distill Complex Pose and Occlusion 1 1 1 Jan 2023 not harvested
Test-time Adaptation vs. Training-time Generalization: A Case Study in Human Instance Segmentation using Keypoints Estimation 0 1 12 Dec 2022 not harvested
Humans need not label more humans: Occlusion Copy & Paste for Occluded Human Instance Segmentation 1 1 7 Oct 2022 official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified
Occlusion-Aware Instance Segmentation via BiLayer Network Architectures 1 1 8 Aug 2022 not harvested
I^2R-Net: Intra- and Inter-Human Relation Network for Multi-Person Pose Estimation 1 1 22 Jun 2022 not harvested
ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation 6 1 26 Apr 2022 community repositories only · 18 ran (of which 8 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 8 where Syntology's instrument failed) · 13 unverified (6 pointer-only for licence)
Contextual Instance Decoupling for Robust Multi-Person Pose Estimation 1 1 1 Jan 2022 not harvested
HRFormer: High-Resolution Transformer for Dense Prediction 1 1 18 Oct 2021 official (archive's flag): 7 ran · 7 ran (of which 7 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 7 samples that ran constructed an object rather than computing a result
Real-time Human-Centric Segmentation for Complex Video Scenes 1 3 16 Aug 2021 not harvested
Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimation 1 7 27 Jan 2021 official (archive's flag): 1 ran · 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result
TransPose: Keypoint Localization via Transformer 1 2 28 Dec 2020 not harvested
Count- and Similarity-aware R-CNN for Pedestrian Detection 0 2 1 Aug 2020 not harvested
Differentiable Hierarchical Graph Grouping for Multi-Person Pose Estimation 0 3 23 Jul 2020 not harvested
PoSeg: Pose-Aware Refinement Network for Human Instance Segmentation 0 2 7 Jan 2020 not harvested
Single-Stage Multi-Person Pose Machines 1 1 24 Aug 2019 not harvested
CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark 4 1 2 Dec 2018 not harvested
Simple Baselines for Human Pose Estimation and Tracking 27 7 17 Apr 2018 not harvested
Pose2Seg: Detection Free Human Instance Segmentation 7 4 28 Mar 2018 official (archive's flag): 14 ran · 14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified
Mask R-CNN 179 1 20 Mar 2017 101 ran (of which 3 constructed an object rather than computing a result; 77 with no instrument failure: 2 honoured, 1 violated, 74 with no contract checked; 24 where Syntology's instrument failed) · 39 unverified (32 pointer-only for licence)
RMPE: Regional Multi-person Pose Estimation 14 3 1 Dec 2016 not harvested
Associative Embedding: End-to-End Learning for Joint Detection and Grouping 5 6 16 Nov 2016 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified

Dataset loaders archive 2025-07-28

2 loaders as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

License archive 2025-07-28

No licence recorded in the archive. Absence here is not a statement about the dataset's terms.

Modalities archive 2025-07-28

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • OCHuman

1 variant name, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections