mlsanityData to 7 Oct 2026

Towards High Performance One-Stage Human Pose Estimation

arXiv 2301.04842 ↗First posted 12 Jan 2023cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Making top-down human pose estimation method present both good performance and high efficiency is appealing. Mask RCNN can largely improve the efficiency by conducting person detection and pose estimation in a single framework, as the features provided by the backbone are able to be shared by the two tasks. However, the performance is not as good as traditional two-stage methods. In this paper, we aim to largely advance the human pose estimation results of Mask-RCNN and still keep the efficiency. Specifically, we make improvements on the whole process of pose estimation, which contains feature extraction and keypoint detection. The part of feature extraction is ensured to get enough and valuable information of pose. Then, we introduce a Global Context Module into the keypoints detection branch to enlarge the receptive field, as it is crucial to successful human pose estimation. On the COCO val2017 set, our model using the ResNet-50 backbone achieves an AP of 68.1, which is 2.6 higher than Mask RCNN (AP of 65.5). Compared to the classic two-stage top-down method SimpleBaseline, our model largely narrows the performance gap (68.1 AP vs. 68.9 AP) with a much faster inference speed (77 ms vs. 168 ms), demonstrating the effectiveness of the proposed method. Code is available at: https://github.com/lingl_space/maskrcnn_keypoint_refined.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 30 of its 44 references that are in the map. First posted on arXiv 12 Jan 2023.

Builds on

30 of 44 references.

References · 30

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2017Mask R-CNNcited by 7,259
  4. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  5. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  6. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  7. 2019Objects as Pointscited by 1,172
  8. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,061
  9. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  10. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  11. 2022ViTPose: Simple Vision Transformer Baselines for Human Pose Estimationcited by 450
  12. 2021Bottleneck Transformers for Visual Recognitioncited by 364
18 more
  1. 2016RMPE: Regional Multi-person Pose Estimationcited by 340
  2. 2019HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimationcited by 247
  3. 2016Associative Embedding: End-to-End Learning for Joint Detection and Groupingcited by 211
  4. 2018PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Modelcited by 133
  5. 2017Towards Accurate Multi-person Pose Estimation in the Wildcited by 131
  6. 2019PifPaf: Composite Fields for Human Pose Estimationcited by 120
  7. 2015DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimationcited by 117
  8. 2021Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regressioncited by 112
  9. 2019Single-Stage Multi-Person Pose Machinescited by 95
  10. 2020Rethinking the Heatmap Regression for Bottom-up Human Pose Estimationcited by 69
  11. 2017Benchmarking and Error Diagnosis in Multi-Instance Pose Estimationcited by 48
  12. 2019Multi-task Deep Learning for Real-Time 3D Human Pose Estimation and Action Recognitioncited by 35
  13. 2021FCPose: Fully Convolutional Multi-Person Pose Estimation with Dynamic Instance-Aware Convolutionscited by 34
  14. 2018Glimpse Clouds: Human Activity Recognition from Unstructured Feature Pointscited by 33
  15. 2018Weakly and Semi Supervised Human Body Part Parsing via Pose-Guided Knowledge Transfercited by 27
  16. 2019Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimationcited by 27
  17. 2020AnimePose: Multi-person 3D pose estimation and animationcited by 10
  18. 2019State-aware Re-identification Feature for Multi-target Multi-camera Trackingcited by 7

Built on by

Not cited yet.