# A comprehensive framework for occluded human pose estimation

arXiv: https://arxiv.org/abs/2401.00155 · HTML: https://mlsanity.com/paper/2401.00155/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 19 references that are in the map.
- First posted on arXiv 30 Dec 2023.

## Builds on (most cited first, 13 of 13)

- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [Simple Baselines for Human Pose Estimation and Tracking](https://mlsanity.com/paper/1804.06208/) (2018)
- [ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation](https://mlsanity.com/paper/2204.12484/) (2022)
- [CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark](https://mlsanity.com/paper/1812.00324/) (2018)
- [Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformer](https://mlsanity.com/paper/2106.04095/) (2021)
- [Pose2Seg: Detection Free Human Instance Segmentation](https://mlsanity.com/paper/1803.10683/) (2018)
- [SimCC: a Simple Coordinate Classification Perspective for Human Pose Estimation](https://mlsanity.com/paper/2107.03332/) (2021)
- [Devil in the Details: Towards Accurate Single and Multiple Human Parsing](https://mlsanity.com/paper/1809.05996/) (2018)
- [Poseur: Direct Human Pose Regression with Transformers](https://mlsanity.com/paper/2201.07412/) (2022)
- [Multi-Scale Structure-Aware Network for Human Pose Estimation](https://mlsanity.com/paper/1803.09894/) (2018)
- [Peeking into occluded joints: A novel framework for crowd pose estimation](https://mlsanity.com/paper/2003.10506/) (2020)
- [PoseTrans: A Simple Yet Effective Pose Transformation Augmentation for Human Pose Estimation](https://mlsanity.com/paper/2208.07755/) (2022)

## Abstract (arXiv)

Occlusion presents a significant challenge in human pose estimation. The challenges posed by occlusion can be attributed to the following factors: 1) Data: The collection and annotation of occluded human pose samples are relatively challenging. 2) Feature: Occlusion can cause feature confusion due to the high similarity between the target person and interfering individuals. 3) Inference: Robust inference becomes challenging due to the loss of complete body structural information. The existing methods designed for occluded human pose estimation usually focus on addressing only one of these factors. In this paper, we propose a comprehensive framework DAG (Data, Attention, Graph) to address the performance degradation caused by occlusion. Specifically, we introduce the mask joints with instance paste data augmentation technique to simulate occlusion scenarios. Additionally, an Adaptive Discriminative Attention Module (ADAM) is proposed to effectively enhance the features of target individuals. Furthermore, we present the Feature-Guided Multi-Hop GCN (FGMP-GCN) to fully explore the prior knowledge of body structure and improve pose estimation results. Through extensive experiments conducted on three benchmark datasets for occluded human pose estimation, we demonstrate that the proposed method outperforms existing methods. Code and data will be publicly available.