Skip to search formSkip to main contentSkip to account menu
DOI:10.1109/ICCV.2017.256 - Corpus ID: 6529517
@article{Fang2016RMPERM, title={RMPE: Regional Multi-person Pose Estimation}, author={Haoshu Fang and Shuqin Xie and Yu-Wing Tai and Cewu Lu}, journal={2017 IEEE International Conference on Computer Vision (ICCV)}, year={2016}, pages={2353-2362}, url={https://api.semanticscholar.org/CorpusID:6529517}}
- Haoshu Fang, Shuqin Xie, Cewu Lu
- Published in IEEE International Conference… 1 December 2016
- Computer Science, Engineering
This paper proposes a novel regional multi-person pose estimation (RMPE) framework to facilitate pose estimation in the presence of inaccurate human bounding boxes and can achieve 76:7 mAP on the MPII (multi person) dataset.
1,435 Citations
144
469
705
9
Figures and Tables from this paper
- figure 1
- table 1
- figure 2
- table 2
- figure 3
- figure 4
- figure 5
- figure 6
- figure 7
Topics
Regional Multi-person Pose Estimation (opens in a new tab)Symmetric Spatial Transformer Network (opens in a new tab)Single-person Pose Estimator (opens in a new tab)Pose-Guided Proposals Generator (opens in a new tab)Multi Person Pose Estimation (opens in a new tab)Single-person Pose Estimation (opens in a new tab)Max Planck Institute For Informatics (opens in a new tab)Human Bounding Boxes (opens in a new tab)Human Detectors (opens in a new tab)Human Proposals (opens in a new tab)
1,435 Citations
- Muhammed KocabasSalih KaragozEmre Akbas
- 2018
Computer Science
ECCV
On the COCO keypoints dataset, the pose estimation method outperforms all previous bottom-up methods both in accuracy and speed; it also performs on par with the best top-down methods while being at least 4x faster.
- Hengkai GuoTang TangGuozhong LuoRiwei ChenYongchen LuLinfu Wen
- 2018
Computer Science
ECCV Workshops
A simple network called Multi-Domain Pose Network (MDPN) is presented, which shows significant improvement over baselines and achieves the best performance on PoseTrack ECCV 2018 Challenge without additional datasets other than MPII and COCO.
- 32
- Highly Influenced[PDF]
- Chenyu TianR. YuXinyuan ZhaoWeihao XiaHaoqian WangYujiu Yang
- 2021
Computer Science
2021 16th IEEE International Conference on…
A novel framework PoseDet (Estimating Pose by Detection) to localize and associate body joints simultaneously at higher inference speed is presented and the keypoint-aware pose embedding to represent an object in terms of the locations of its keypoints is proposed.
- 2
- Highly Influenced[PDF]
- Huixiang QiaoYing XuZhongjie ZhaoJiahao TianJiahuan ZhangChengbin Peng
- 2019
Computer Science
2019 2nd International Conference on Artificial…
The results prove that the proposed method can more effectively distinguish ambiguous keypoints and estimate poses and introduce a channel-attention mechanism to enhance the predictive ability of heat map on keypoints.
- Highly Influenced
- Daiwei YuJun ZhangZhao JinGuanqun LiWenjin Zhang
- 2022
Computer Science
International Conference on Digital Image…
A multi-task model for human pose estimation and person detection simultaneously, named PersonPD (person pose and person Detection), which predicts keypoint heatmaps and regresses a 4D relative displacement vector which actually encodes the person bounding box and also acts as keypoints' grouping clues.
- Daxing ChenXinghao SongShixi FanHongpeng Wang
- 2019
Computer Science
2019 IEEE International Conference on Robotics…
This work proposes and attention module that could let the model get global receptive field at the shallow layer of the network and pay more attention to the key areas which is more important to pose estimation.
- Dahu ShiXing WeiLiangqi LiYe RenWenming Tan
- 2022
Computer Science
2022 IEEE/CVF Conference on Computer Vision and…
The proposed PETR method views pose estimation as a hierarchical set prediction problem and effectively removes the need for many hand-crafted modules like RoI cropping, NMS and grouping post-processing, and largely overcomes the feature misalignment difficulty in pose estimation and improves the performance considerably.
- 70
- PDF
- Yu-Feng ChengBo WangR. Tan
- 2023
Computer Science
IEEE Transactions on Pattern Analysis and Machine…
This work proposes the integration of top-down and bottom-up approaches to address the common gaps between training and testing data, and introduces a two-person pose discriminator that enforces natural two- person interactions.
- 17 [PDF]
- Haoshu FangJiefeng Li Cewu Lu
- 2023
Computer Science
IEEE Transactions on Pattern Analysis and Machine…
This article presents AlphaPose, a system that can perform accurate whole-body pose estimation and tracking jointly while running in realtime, and proposes several new techniques: Symmetric Integral Keypoint Regression (SIKR) for fast and fine localization, Parametric Pose Non-Maximum-Suppression (P-NMS) for eliminating redundant human detections and Pose Aware Identity Embedding for jointly posing and tracking.
- 207
- Highly Influenced[PDF]
- Xiao ChenGen-ke Yang
- 2018
Computer Science
2018 25th IEEE International Conference on Image…
A generic bottom-up approach for multi-person pose estimation is presented, which introduces limb detection heatmaps as a representation of body joint pairs association, which are simultaneously learned with joint detections.
- 7
...
...
55 References
- Umar IqbalJuergen Gall
- 2016
Computer Science
ECCV Workshops
This work proposes a method that estimates the poses of multiple persons in an image in which a person can be occluded by another person or might be truncated, and considers multi-person pose estimation as a joint-to-person association problem.
- 138
- Highly Influential[PDF]
- L. PishchulinEldar Insafutdinov B. Schiele
- 2016
Computer Science
2016 IEEE Conference on Computer Vision and…
An approach that jointly solves the tasks of detection and pose estimation: it infers the number of persons in a scene, identifies occluded body parts, and disambiguates body parts between people in close proximity of each other is proposed.
- 903 [PDF]
- Eldar InsafutdinovL. PishchulinBjoern AndresMykhaylo AndrilukaB. Schiele
- 2016
Computer Science
ECCV
The goal of this paper is to advance the state-of-the-art of articulated pose estimation in scenes with multiple people. To that end we contribute on three fronts. We propose (1) improved body part…
- 1,051 [PDF]
- G. PapandreouTyler Lixuan Zhu K. Murphy
- 2017
Computer Science
2017 IEEE Conference on Computer Vision and…
This work proposes a method for multi-person detection and 2-D pose estimation that achieves state-of-art results on the challenging COCO keypoints task by using a novel form of keypoint-based Non-Maximum-Suppression (NMS), instead of the cruder box-level NMS, and by introducing a novel aggregation procedure to obtain highly localized keypoint predictions.
- 756 [PDF]
- L. PishchulinArjun JainMykhaylo AndrilukaThorsten ThormählenB. Schiele
- 2012
Computer Science
2012 IEEE Conference on Computer Vision and…
This work proposes a new technique to extend an existing training set that allows to explicitly control pose and shape variations and defines a new challenge of combined articulated human detection and pose estimation in real-world scenes.
- 248
- PDF
- M. EichnerV. Ferrari
- 2010
Computer Science
ECCV
A novel multi-person pose estimation framework, which extends pictorial structures (PS) to explicitly model interactions between people and to estimate their poses jointly, resulting in better pose estimates in group photos, where several persons stand nearby and occlude each other.
- 121
- PDF
- Zhe CaoT. SimonS. WeiYaser Sheikh
- 2017
Computer Science
2017 IEEE Conference on Computer Vision and…
We present an approach to efficiently detect the 2D pose of multiple people in an image. The approach uses a nonparametric representation, which we refer to as Part Affinity Fields (PAFs), to learn…
- 5,827 [PDF]
- Eldar InsafutdinovMykhaylo Andriluka B. Schiele
- 2017
Computer Science
2017 IEEE Conference on Computer Vision and…
This paper uses a model that resembles existing architectures for single-frame pose estimation but is substantially faster to generate proposals for body joint locations and forms articulated tracking as spatio-temporal grouping of such proposals.
- 255 [PDF]
- Mykhaylo AndrilukaL. PishchulinPeter GehlerB. Schiele
- 2014
Computer Science, Engineering
2014 IEEE Conference on Computer Vision and…
A novel benchmark "MPII Human Pose" is introduced that makes a significant advance in terms of diversity and difficulty, a contribution that is required for future developments in human body models.
- 2,254
- PDF
- Yilun ChenZhicheng WangYuxiang PengZhiqiang ZhangGang YuJian Sun
- 2018
Computer Science
2018 IEEE/CVF Conference on Computer Vision and…
A novel network structure called Cascaded Pyramid Network (CPN) is presented which targets to relieve the problem from these "hard" keypoints, with state-of-art results on the COCO keypoint benchmark, with average precision at 73.0.
- 1,229 [PDF]
...
...
Related Papers
Showing 1 through 3 of 0 Related Papers