Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Sign Up
Cited by 1,884

The DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.

RMPE: Regional Multi-person Pose Estimation

Open access
Fang, Hao-Shu, Xie, Shuqin, Tai, Yu-Wing, Lu, Cewu·2017·2017 IEEE International Conference on Computer Vision (ICCV)
DOI 10.1109/iccv.2017.256
Open this paper in CoChat — free account

Abstract

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 76:7 mAP on the MPII (multi person) dataset[3]. Our model and source codes are made publicly available.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/iccv.2017.256

Cites

5 of 5 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 5 references

Research works printed but not linked: 35

  1. yao, 2012, Recognizing human-object interactions in still images by modeling the mutual context of objects and human poses, IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 34, 1691, 10.1109/TPAMI.2012.67 · DOI · Paper page
  2. 10.1109/CVPR.2016.511 · DOI · Paper page
  3. tompson, 2014, Joint training of a convolutional network and a graphical model for human pose estimation, Conference on Neural Information Processing Systems (NIPS), 1799
  4. sun, 2012, An efficient branch-and-bound algorithm for optimal human pose estimation, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 1616
  5. sun, 2012, Conditional regression forests for human pose estimation, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 3394
  6. sapp, 2010, Cascaded models for articulated pose estimation, European Conference on Computer Vision (ECCV), 406
  7. 10.1007/978-3-540-88690-7_53 · DOI
  8. 10.1109/CVPR.2013.83 · DOI
  9. umar iqbal, 2016, Multi-person pose estimation with local joint-to-person associations, European Conference on Computer Vision Workshops 2016 (ECCVW'16) — Workshop on Crowd Understanding (CUW'16)
  10. 10.1109/CVPR.2014.214 · DOI · Paper page
  11. 10.1109/CVPR.2017.206 · DOI
  12. zhang, 2009, Efficient human pose estimation via parsing a tree structure based human model, IEEE International Conference on Computer Vision (ICCV), 1349
  13. fan, 2015, Combining local appearance and holistic view: Dual-source deep neural networks for human pose estimation, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 1347
  14. gkioxari, 2014, Using k-poselets for detecting people and localizing their key-points, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 3582
  15. 10.1109/CVPR.2008.4587511 · doi:10.1109/cvpr.2008.4587511
  16. 10.1109/CVPR.2013.435 · DOI
  17. 10.1109/CVPR.2017.142 · DOI · Paper page
  18. insafutdinov, 2016, DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Model, European Conference on Computer Vision (ECCV)
  19. jaderberg, 2015, Spatial transformer networks, Conference on Neural Information Processing Systems (NIPS), 2017
  20. jain, 2013, Learning human pose estimation features with convolutional networks
  21. 10.1109/CVPR.2012.6248052 · DOI
  22. belagiannis, 2016, Recurrent human pose estimation
  23. 10.1109/CVPR.2016.533 · DOI · Paper page
  24. 10.1109/CVPR.2014.471 · DOI · Paper page
  25. 10.5244/C.27.58 · DOI
  26. 10.1109/CVPR.2013.391 · DOI · Paper page
  27. 10.1109/CVPR.2015.7299020 · DOI
  28. 10.1109/CVPR.2014.113 · doi:10.1109/cvpr.2014.113
  29. 2016, MSCOCO keypoint challenge
  30. 10.1007/978-3-319-10602-1_22 · DOI
  31. liu, 2016, SSD: Single Shot MultiBox Detector, European Conference on Computer Vision (ECCV)
  32. ladicky, 2013, Human pose estimation using a joint pixel-wise and part-wise formulation, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 3578
  33. 10.1109/CVPR.2014.299 · DOI · Paper page
  34. 10.1109/ICCV.2013.433 · DOI
  35. 10.1109/ICCV.2015.273 · DOI

Cited by

Metadata

Authors
Fang, H.-S., Xie, S., Tai, Y.-W., & Lu, C.
Venue
2017 IEEE International Conference on Computer Vision (ICCV)
Publisher
IEEE
Published
2017-10
Pages
2353-2362
DOI
10.1109/iccv.2017.256
OpenAlex
W2963781481
Cited by
1,884
References
5
FWCI
32.76
Type
conference paper
Language
en
Open access
green

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.