Data to 14 Oct 2026

RMPE: Regional Multi-person Pose Estimation

arXiv 1612.00137 ↗First posted 1 Dec 2016cs.CVcited by 340

Not on the map. Why?

Abstract (arXiv)

Multi-person pose estimation in the wild is challenging. Although state-of-the-art human detectors have demonstrated good performance, small errors in localization and recognition are inevitable. These errors can cause failures for a single-person pose estimator (SPPE), especially for methods that solely depend on human detection results. In this paper, we propose a novel regional multi-person pose estimation (RMPE) framework to facilitate pose estimation in the presence of inaccurate human bounding boxes. Our framework consists of three components: Symmetric Spatial Transformer Network (SSTN), Parametric Pose Non-Maximum-Suppression (NMS), and Pose-Guided Proposals Generator (PGPG). Our method is able to handle inaccurate bounding boxes and redundant detections, allowing it to achieve a 17% increase in mAP over the state-of-the-art methods on the MPII (multi person) dataset.Our model and source codes are publicly available.

Key facts. Cited by 340 papers in the map (data through 14 Oct 2026). First posted on arXiv 1 Dec 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 103; 2022: 94; 2023: 69; 2024: 42; 2025: 23; 2026: 9.

340 papers.

Sort:

By area:

2022DiffusionDet: Diffusion Model for Object Detectioncited by 354
2023Humans in 4D: Reconstructing and Tracking Humans with Transformerscited by 350
20213D Human Pose Estimation with Spatial and Temporal Transformerscited by 272
2021Exploring Cross-Image Pixel Contrast for Semantic Segmentationcited by 242
2024Sapiens: Foundation for Human Vision Modelscited by 229
2024STAR: A Benchmark for Situated Reasoning in Real-World Videoscited by 213
2022AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Timecited by 200
2021Human Pose Regression with Residual Log-likelihood Estimationcited by 131
2021Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regressioncited by 112
2021TokenPose: Learning Keypoint Tokens for Human Pose Estimationcited by 107
2022Recovering 3D Human Mesh from Monocular Images: A Surveycited by 103
2021UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehiclescited by 96

38 more

2021Lite-HRNet: A Lightweight High-Resolution Networkcited by 91
2021Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognitioncited by 90
2023Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregationcited by 82
2022P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimationcited by 80
2021SimCC: a Simple Coordinate Classification Perspective for Human Pose Estimationcited by 68
2021Pose-guided Feature Disentangling for Occluded Person Re-identification Based on Transformercited by 68
2022ViTPose++: Vision Transformer for Generic Body Pose Estimationcited by 65
2022Towards a Deeper Understanding of Skeleton-based Gait Recognitioncited by 56
2021OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Associationcited by 55
2022TransCG: A Large-Scale Real-World Dataset for Transparent Object Depth Completion and a Grasping Baselinecited by 55
2021Deep Gait Recognition: A Surveycited by 54
2021GroupFormer: Group Activity Recognition with Clustered Spatial-Temporal Transformercited by 54
2021Deep Dual Consecutive Network for Human Pose Estimationcited by 51
2021Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspectivecited by 50
2021Three Steps to Multimodal Trajectory Prediction: Modality Clustering, Classification and Synthesiscited by 46
2023Human Pose as Compositional Tokenscited by 45
2021Spatio-Temporal Dynamic Inference Network for Group Activity Recognitioncited by 42
2021When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarkscited by 41
2023Masked Motion Predictors are Strong 3D Action Representation Learnerscited by 41
2021RGB Matters: Learning 7-DoF Grasp Poses on Monocular RGBD Imagescited by 39
2022Faster VoxelPose: Real-time 3D Human Pose Estimation by Orthographic Projectioncited by 39
2022CMD: Self-supervised 3D Action Representation Learning with Cross-modal Mutual Distillationcited by 38
2021Learning Dynamics via Graph Neural Networks for Human Pose Estimation and Trackingcited by 37
2023Music-Driven Group Choreographycited by 37
2022TSA-Net: Tube Self-Attention Network for Action Quality Assessmentcited by 36
2023DiffPose: SpatioTemporal Diffusion Model for Video-Based Human Pose Estimationcited by 36
2021VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Livingcited by 35
2021UNIK: A Unified Framework for Real-world Skeleton-based Action Recognitioncited by 35
2021FCPose: Fully Convolutional Multi-Person Pose Estimation with Dynamic Instance-Aware Convolutionscited by 34
2022Signature Methods in Machine Learningcited by 34
2022Mining Cross-Person Cues for Body-Part Interactiveness Learning in HOI Detectioncited by 34
2021Lightweight Multi-person Total Motion Capture Using Sparse Multi-view Camerascited by 33
2021AdaptPose: Cross-Dataset Adaptation for 3D Human Pose Estimation by Learnable Motion Generationcited by 32
2023On the Benefits of 3D Pose and Tracking for Human Action Recognitioncited by 32
2021Differentiable Multi-Granularity Human Representation Learning for Instance-Aware Human Semantic Parsingcited by 31
2022Neural MoCon: Neural Motion Control for Physically Plausible Human Motion Capturecited by 31
2023UnionDet: Union-Level Detector Towards Real-Time Human-Object Interaction Detectioncited by 31
2021Supervision by Registration and Triangulation for Landmark Detectioncited by 30

50 most cited of 340 All 340 (JSON)