mlsanityData to 7 Oct 2026

Greedy Offset-Guided Keypoint Grouping for Human Pose Estimation

arXiv 2107.03098 ↗First posted 7 Jul 2021cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

We propose a simple yet reliable bottom-up approach with a good trade-off between accuracy and efficiency for the problem of multi-person pose estimation. Given an image, we employ an Hourglass Network to infer all the keypoints from different persons indiscriminately as well as the guiding offsets connecting the adjacent keypoints belonging to the same persons. Then, we greedily group the candidate keypoints into multiple human poses (if any), utilizing the predicted guiding offsets. And we refer to this process as greedy offset-guided keypoint grouping (GOG). Moreover, we revisit the encoding-decoding method for the multi-person keypoint coordinates and reveal some important facts affecting accuracy. Experiments have demonstrated the obvious performance improvements brought by the introduced components. Our approach is comparable to the state of the art on the challenging COCO dataset under fair conditions. The source code and our pre-trained model are publicly available online.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 19 of its 20 references that are in the map. First posted on arXiv 7 Jul 2021.

Builds on

19 of 20 references.

References · 19

  1. 2017Mask R-CNNcited by 7,259
  2. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  3. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  4. 2019Objects as Pointscited by 1,172
  5. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,061
  6. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  7. 2018CornerNet: Detecting Objects as Paired Keypointscited by 763
  8. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  9. 2013DeepPose: Human Pose Estimation via Deep Neural Networkscited by 305
  10. 2019HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimationcited by 247
  11. 2016Associative Embedding: End-to-End Learning for Joint Detection and Groupingcited by 211
  12. 2019Distribution-Aware Coordinate Representation for Human Pose Estimationcited by 165
7 more
  1. 2018PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Modelcited by 133
  2. 2017Towards Accurate Multi-person Pose Estimation in the Wildcited by 131
  3. 2014Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimationcited by 129
  4. 2019PifPaf: Composite Fields for Human Pose Estimationcited by 120
  5. 2016DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Modelcited by 96
  6. 2017Benchmarking and Error Diagnosis in Multi-Instance Pose Estimationcited by 48
  7. 2019Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimationcited by 27

Built on by

Not cited yet.