paper-with-me

Semi-Supervised Human Pose Estimation

2개 벤치마크 · 논문 5편 · 이 태스크의 논문 보기 →

Benchmarks

PoPArt

결과 25개

COCO 1% labeled data

결과 5개

Most implemented

Papers

Denoising and Selecting Pseudo-Heatmaps for Semi-Supervised Human Pose Estimation

2023-09-29 · Zhuoran Yu, Manchen Wang, Yanbei Chen, Paolo Favaro 외

We propose a new semi-supervised learning design for human pose estimation that revisits the popular dual-student framework and enhances it two ways. First, we introduce a denoising scheme to generate reliable pseudo-hea…

DenoisingPose EstimationSemi-Supervised Human Pose Estimation

Semi-supervised Human Pose Estimation in Art-historical Images

2022-07-06 · Matthias Springstein, Stefanie Schneider, Christian Althaus, Ralph Ewerth

Gesture as language of non-verbal communication has been theoretically established since the 17th century. However, its relevance for the visual arts has been expressed only sporadically. This may be primarily due to the…

2D Human Pose EstimationKeypoint DetectionPose EstimationRetrieval+2

Pose-MUM : Reinforcing Key Points Relationship for Semi-Supervised Human Pose Estimation

2022-03-15 · Jongmok Kim, Hwijun Lee, Jaeseung Lim, Jongkeun Na 외

A well-designed strong-weak augmentation strategy and the stable teacher to generate reliable pseudo labels are essential in the teacher-student framework of semi-supervised learning (SSL). Considering these in mind, to …

Pose EstimationSemi-Supervised Human Pose Estimation

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

2021-08-26 · Vinkle Srivastav, Afshin Gangi, Nicolas Padoy

The fine-grained localization of clinicians in the operating room (OR) is a key component to design the new generation of OR support systems. Computer vision models for person pixel-based segmentation and body-keypoints …

2D Human Pose EstimationInstance SegmentationPrivacy PreservingSemi-Supervised Human Pose Estimation+3

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

2020-11-25 · ICCV 2021 10 · Rongchang Xie, Chunyu Wang, Wenjun Zeng, Yizhou Wang

Semi-supervised learning aims to boost the accuracy of a model by exploring unlabeled images. The state-of-the-art methods are consistency-based which learn about unlabeled images by encouraging the model to give consist…

2D Human Pose EstimationPose EstimationSemi-Supervised Human Pose Estimation