MPII

The MPII dataset is a benchmark for human pose estimation that contains annotated images of people in various activities and is used to evaluate the accuracy of pose estimation methods.

Papers using MPII (8)

Dite-HRNet: Dynamic Lightweight High-Resolution Network for Human Pose Estimation2022 · 63 citesLAPX: Lightweight Hourglass Network with Global Context2025Associative Embedding: End-to-End Learning for Joint Detection and Grouping2016 · 418 citesRMPE: Regional Multi-person Pose Estimation2016 · 61 citesTFPose: Direct Human Pose Estimation with Transformers2021 · 57 citesPPT: token-Pruned Pose Transformer for monocular and multi-view human pose estimation2022 · 2 citesPoseur: Direct Human Pose Regression with Transformers2022Improved TokenPose with Sparsity2023