multi-person-pose-estimation

Semi-Supervised Human Pose Estimation

3260 papers • 126 benchmarks • 313 datasets

Semi-supervised human pose estimation aims to leverage the unlabelled data along with labeled data to improve the model performance.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in multi-person-pose-estimation

Trend

Dataset

Best Model

Actions

PoPArt

COCO 1% labeled data

Libraries

i

Use these libraries to find multi-person-pose-estimation models and implementations

Datasets

PoPArt

Subtasks

No subtasks available.

Most implemented papers

An Empirical Study of the Collapsing Problem in Semi-Supervised 2D Human Pose Estimation

Yizhou Wang, Chunyu Wang, Wenjun Zeng, Rongchang Xie•Tue Nov 24 2020

This work presents a surprisingly simple approach to drive the model to learn in the correct direction and applies it to the state-of-the-art pose estimators and it further improves their performance on three public datasets.

31

Content

0

Paper Graph

Semi-supervised Human Pose Estimation in Art-historical Images

R. Ewerth, Matthias Springstein, Stefanie Schneider, C. Althaus•Tue Jul 05 2022

This paper proposes a novel approach to estimate human poses in art-historical images that achieves significantly better results than methods that use pre-trained models or style transfer, and introduces a novel domain-specific art data set that includes both bounding box and keypoint annotations of human figures.

15 0

Paper Graph

Unsupervised domain adaptation for clinician pose estimation and instance segmentation in the OR

V. Srivastav, A. Gangi, Nicolas Padoy•Wed Aug 25 2021

A novel unsupervised domain adaptation method, called AdaptOR, to adapt a model from an in-the-wild labeled source domain to a statistically different unlabeled target domain, and disentangled feature normalization is proposed to handle the statistically different source and target domain data.

14 0

Paper Graph

Adding a benchmark result helps the community track progress.