Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Datasets/OCHuman

OCHuman

Images

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

1 Image, 2*2 Stitchi/Test AP 1 Image, 2*2 Stitchi/Validation AP 1 Image, 2*2 Stitchi/AP50 1 Image, 2*2 Stitchi/AP75 2D Human Pose Estimation/Test AP 2D Human Pose Estimation/Validation AP 3D/Test AP 3D/Validation AP 3D/AP50 3D/AP75 Human Instance Segmentation/AP Instance Segmentation/AP Multi-Person Pose Estimation/AP50 Multi-Person Pose Estimation/AP75 Multi-Person Pose Estimation/Validation AP Pose Estimation/Test AP Pose Estimation/Validation AP Pose Estimation/AP50 Pose Estimation/AP75

Statistics

Papers: 66
Benchmarks: 19

Links

Tasks

1 Image, 2*2 Stitchi 2D Human Pose Estimation 3D Human Instance Segmentation Instance Segmentation Keypoint Detection Multi-Person Pose Estimation Pose Estimation Pose-Based Human Instance Segmentation