Occluded Human Pose Estimation based on Limb Joint Augmentation
Not on the map. Why?
Abstract (arXiv)
Human pose estimation aims at locating the specific joints of humans from the images or videos. While existing deep learning-based methods have achieved high positioning accuracy, they often struggle with generalization in occlusion scenarios. In this paper, we propose an occluded human pose estimation framework based on limb joint augmentation to enhance the generalization ability of the pose estimation model on the occluded human bodies. Specifically, the occlusion blocks are at first employed to randomly cover the limb joints of the human bodies from the training images, imitating the scene where the objects or other people partially occlude the human body. Trained by the augmented samples, the pose estimation model is encouraged to accurately locate the occluded keypoints based on the visible ones. To further enhance the localization ability of the model, this paper constructs a dynamic structure loss function based on limb graphs to explore the distribution of occluded joints by evaluating the dependence between adjacent joints. Extensive experimental evaluations on two occluded datasets, OCHuman and CrowdPose, demonstrate significant performance improvements without additional computation cost during inference.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 42 of its 49 references that are in the map. First posted on arXiv 13 Oct 2024.
Builds on
42 of 49 references.
References · 42
- 2014Microsoft COCO: Common Objects in Contextcited by 17,608
- 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
- 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,064
- 2016Stacked Hourglass Networks for Human Pose Estimationcited by 915
- 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
- 2022ViTPose: Simple Vision Transformer Baselines for Human Pose Estimationcited by 456
- 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
- 2016Convolutional Pose Machinescited by 325
- 2019HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimationcited by 247
- 2018CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmarkcited by 214
- 2020Deep Learning-Based Human Pose Estimation: A Surveycited by 207
- 2022RTMDet: An Empirical Study of Designing Real-Time Object Detectorscited by 195
30 more
- 2023RTMPose: Real-Time Multi-Person Pose Estimation based on MMPosecited by 175
- 2021HRFormer: High-Resolution Transformer for Dense Predictioncited by 149
- 2014Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimationcited by 129
- 2020TransPose: Keypoint Localization via Transformercited by 126
- 2015DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimationcited by 117
- 2021Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regressioncited by 112
- 2018Pose2Seg: Detection Free Human Instance Segmentationcited by 107
- 2021TokenPose: Learning Keypoint Tokens for Human Pose Estimationcited by 107
- 2020Cascaded deep monocular 3D human pose estimation with evolutionary training datacited by 80
- 2019The Devil is in the Details: Delving into Unbiased Data Processing for Human Pose Estimationcited by 79
- 2021SimCC: a Simple Coordinate Classification Perspective for Human Pose Estimationcited by 68
- 2017Multi-Context Attention for Human Pose Estimationcited by 66
- 2023Make-An-Animation: Large-Scale Text-conditional 3D Human Motion Generationcited by 56
- 2018Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimationcited by 44
- 2023ViPLO: Vision Transformer based Pose-Conditioned Self-Loop Graph for Human-Object Interaction Detectioncited by 41
- 2023GPGait: Generalized Pose-based Gait Recognitioncited by 40
- 2018Multi-Scale Structure-Aware Network for Human Pose Estimationcited by 37
- 2019Multi-Person Pose Estimation with Enhanced Channel-wise and Spatial Informationcited by 35
- 2021Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimationcited by 30
- 2022PPT: token-Pruned Pose Transformer for monocular and multi-view human pose estimationcited by 27
- 2021Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimationcited by 20
- 2016Multi-Person Pose Estimation with Local Joint-to-Person Associationscited by 18
- 2016Structured Feature Learning for Pose Estimationcited by 17
- 2022Lite Pose: Efficient Architecture Design for 2D Human Pose Estimationcited by 16
- 2021Six-channel Image Representation for Cross-domain Object Detectioncited by 8
- 2021A Domain Gap Aware Generative Adversarial Network for Multi-domain Image Translationcited by 8
- 2023Lightweight Super-Resolution Head for Human Pose Estimationcited by 7
- 2021AdaptivePose: Human Parts as Adaptive Pointscited by 6
- 2023Disentangled Representation Learning for Controllable Person Image Generationcited by 4
- 2023BoIR: Box-Supervised Instance Representation for Multi-Person Pose Estimationcited by 2
Built on by
Citing papers per year: 2025: 3.
3 papers.