The DOI matches its Crossref record; 32 of the 32 references it cites were found in a registry or an index.
Realtime Multi-person 2D Pose Estimation Using Part Affinity Fields
Abstract
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 to associate body parts with individuals in the image. The architecture encodes global context, allowing a greedy bottom-up parsing step that maintains high accuracy while achieving realtime performance, irrespective of the number of people in the image. The architecture is designed to jointly learn part locations and their association via two branches of the same sequential prediction process. Our method placed first in the inaugural COCO 2016 keypoints challenge, and significantly exceeds the previous state-of-the-art result on the MPII Multi-Person benchmark, both in performance and efficiency.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“For a stream of 100 simple dynamics images from the JAAD data set, this knob reduces the median image size by up to 40%.”
From Mez: An Adaptive Messaging System for Latency-Sensitive Multi-Camera Machine Vision at the IoT Edge (2021) · cites this paper as [19]
In the citing paper
“We note that for video frames with complex scene dynamics, the ratio FIVE Lat /ONE Lat is 5.6x for the JAAD dataset, and 8.4x for the DukeMTMC dataset.”
From Mez: An Adaptive Messaging System for Latency-Sensitive Multi-Camera Machine Vision at the IoT Edge (2021) · cites this paper as [19]
In the citing paper
“Although top-down methods still dominate the leaderboard of public benchmark datasets like MS COCO 10 , they are usually slower than bottom-up methods [112].”
From Empowering things with intelligence: a survey of the progress, challenges, and opportunities in artificial intelligence of things (2021) · cites this paper as [112]
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 2×
“Insafutdinov et al. [15] built on [27] with a stronger part detectors based on ResNet [13] and image-dependent pairwise scores, and vastly improved the runtime with an incremental optimization approach, but the method still takes several minutes per image, with a limit of at most 150 part proposals.”
BackgroundMethodVery Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148 · cited 1×
“During training, we initialize the 10 layers from the VGG-19 [32].”
MethodMicrosoft COCO: Common Objects in Context
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., & Zitnick, C. L. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_48 · Cited by 45,460
(2016) · Cited by 31,590
The Hungarian method for the assignment problem
Kuhn, H. W. (1955) · Naval Research Logistics Quarterly · doi:10.1002/nav.3800020109 · Cited by 13,120
Stacked Hourglass Networks for Human Pose Estimation
Newell, A., Yang, K., & Deng, J. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46484-8_29 · Cited by 5,634 · cited 3×
“To obtain reliable local observations of body parts, Convolu-tional Neural Networks (CNNs) have been widely used, and have significantly boosted the accuracy on body pose estimation [23, 38, 24, 34, 35, 7, 36, 6].”
BackgroundMethodFields, J. (2001) · Cited by 4,044
DeepPose: Human Pose Estimation via Deep Neural Networks
Toshev, A., & Szegedy, C. (2014) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2014.214 · Cited by 3,395 · cited 1×
“To obtain reliable local observations of body parts, Convolu-tional Neural Networks (CNNs) have been widely used, and have significantly boosted the accuracy on body pose estimation [23, 38, 24, 34, 35, 7, 36, 6].”
MethodWei, S.-E., Ramakrishna, V., Kanade, T., & Sheikh, Y. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.511 · Cited by 2,966 · cited 7×
“…be capable of iteratively refining confidence maps by learning implicit spatial relationship between different body parts in the single person case [38]; we show the that sequential prediction architectures can also iteratively refine PAFs while capturing spatial relationship across different…”
BackgroundMethodInfluentialSelf-citation2D Human Pose Estimation: New Benchmark and State of the Art Analysis
Andriluka, M., Pishchulin, L., Gehler, P., & Schiele, B. (2014) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2014.471 · Cited by 2,699 · cited 1×
“We evaluate our method on two benchmarks for multi-person pose estimation: (1) the MPII human multi-person dataset [2] and (2) the MSCOCO 2016 keypoints challenge dataset [21].”
MethodPictorial Structures for Object Recognition
Felzenszwalb, P. F., & Huttenlocher, D. P. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000042934.15159.49 · Cited by 2,167 · cited 1×
“The spatial model for articulated pose is either based on tree-structured graphical models [10, 30, 4, 3, 26, 40, 17], which parametrically encode the spatial relationship between adjacent parts following a kinematic chain, or non-tree models [37, 31, 20, 18, 8] that augment the tree structure with…”
MethodEfficient object localization using Convolutional Networks
Tompson, J., Goroshin, R., Jain, A., LeCun, Y., & Bregler, C. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298664 · Cited by 1,365 · cited 1×
“These top-down approaches directly leverage existing techniques for single-person pose estimation [17, 31, 18, 28, 29, 7, 30, 5, 6, 20], but suffer from early commitment: if the person detector fails–as it is prone to do when people are in close proximity–there is no recourse to recovery.”
BackgroundJoint Training of a Convolutional Network and a Graphical Model for Human Pose EstimationPreprint
Tompson, J., Jain, A., LeCun, Y., & Bregler, C. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1406.2984 · Cited by 1,317 · cited 2×
“Tompson et al. [35] used a deep architecture with a graphical model whose parameters are learned jointly with the network.”
BackgroundMethodDeeperCut: A Deeper, Stronger, and Faster Multi-person Pose Estimation Model
Insafutdinov, E., Pishchulin, L., Andres, B., Andriluka, M., & Schiele, B. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46466-4_3 · Cited by 1,210 · cited 12×
“We build a two-branch network upon CPMs [38] to iteratively refine both confidence maps and PAFs with global image and spatial contexts.”
BackgroundMethodInfluentialDeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation
Pishchulin, L., Insafutdinov, E., Tang, S., Andres, B., Andriluka, M., Gehler, P., & Schiele, B. (2016) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2016.533 · Cited by 1,090 · cited 8×
“Table 1 compares mAP performance between our method and other approaches on the same subset of 288 testing images as in [27], and the entire MPI testing set.”
BackgroundMethodInfluentialTowards Accurate Multi-person Pose Estimation in the Wild
Papandreou, G., Zhu, T., Kanazawa, N., Toshev, A., Tompson, J., Bregler, C., & Murphy, K. P. (2017) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2017.395 · Cited by 917
Clustered Pose and Nonlinear Appearance Models for Human Pose Estimation
Johnson, S., & Everingham, M. (2010) · British Machine Vision Conference (BMVC) · doi:10.5244/c.24.12 · Cited by 870 · cited 1×
“The spatial model for articulated pose is either based on tree-structured graphical models [10, 30, 4, 3, 26, 40, 17], which parametrically encode the spatial relationship between adjacent parts following a kinematic chain, or non-tree models [37, 31, 20, 18, 8] that augment the tree structure with…”
MethodArticulated Human Detection with Flexible Mixtures of Parts
Yang, Y., & Ramanan, D. (2012) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.261 · Cited by 843 · cited 1×
“Human 2D pose estimation—the problem of localizing anatomical keypoints or “parts”—has largely focused on finding body parts of individuals [8, 4, 3, 21, 33, 13, 25, 31, 6, 24].”
BackgroundPictorial structures revisited: People detection and articulated pose estimation
Andriluka, M., Roth, S., & Schiele, B. (2009) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2009.5206754 · Cited by 814 · cited 1×
“The spatial model for articulated pose is either based on tree-structured graphical models [10, 30, 4, 3, 26, 40, 17], which parametrically encode the spatial relationship between adjacent parts following a kinematic chain, or non-tree models [37, 31, 20, 18, 8] that augment the tree structure with…”
MethodHuman Pose Estimation via Convolutional Part Heatmap Regression
Bulat, A., & Tzimiropoulos, G. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46478-7_44 · Cited by 542
Flowing ConvNets for Human Pose Estimation in Videos
Pfister, T., Charles, J., & Zisserman, A. (2015) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.222 · Cited by 530 · cited 1×
“These top-down approaches directly leverage existing techniques for single-person pose estimation [17, 31, 18, 28, 29, 7, 30, 5, 6, 20], but suffer from early commitment: if the person detector fails–as it is prone to do when people are in close proximity–there is no recourse to recovery.”
BackgroundMonocular 3D pose estimation and tracking by detection
Andriluka, M., Roth, S., & Schiele, B. (2010) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2010.5540156 · Cited by 507 · cited 1×
“The spatial model for articulated pose is either based on tree-structured graphical models [10, 30, 4, 3, 26, 40, 17], which parametrically encode the spatial relationship between adjacent parts following a kinematic chain, or non-tree models [37, 31, 20, 18, 8] that augment the tree structure with…”
MethodPoselet Conditioned Pictorial Structures
Pishchulin, L., Andriluka, M., Gehler, P., & Schiele, B. (2013) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2013.82 · Cited by 375 · cited 1×
“Human 2D pose estimation—the problem of localizing anatomical keypoints or “parts”—has largely focused on finding body parts of individuals [8, 4, 3, 21, 33, 13, 25, 31, 6, 24].”
BackgroundArticulated Pose Estimation by a Graphical Model with Image Dependent Pairwise RelationsPreprint
Chen, X., & Yuille, A. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1407.3399 · Cited by 358 · cited 1×
“To obtain reliable local observations of body parts, Convolu-tional Neural Networks (CNNs) have been widely used, and have significantly boosted the accuracy on body pose estimation [23, 38, 24, 34, 35, 7, 36, 6].”
MethodRecurrent Human Pose Estimation
Belagiannis, V., & Zisserman, A. (2017) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/fg.2017.64 · Cited by 336 · cited 1×
“These top-down approaches directly leverage existing techniques for single-person pose estimation [17, 31, 18, 28, 29, 7, 30, 5, 6, 20], but suffer from early commitment: if the person detector fails–as it is prone to do when people are in close proximity–there is no recourse to recovery.”
BackgroundStrike a Pose: Tracking People by Finding Stylized Poses
Ramanan, D., Forsyth, D. A., & Zisserman, A. (2005) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2005.335 · Cited by 304 · cited 1×
“Human 2D pose estimation—the problem of localizing anatomical keypoints or “parts”—has largely focused on finding body parts of individuals [8, 4, 3, 21, 33, 13, 25, 31, 6, 24].”
BackgroundMulti-source Deep Learning for Human Pose Estimation
Ouyang, W., Chu, X., & Wang, X. (2014) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2014.299 · Cited by 273 · cited 1×
“To obtain reliable local observations of body parts, Convolu-tional Neural Networks (CNNs) have been widely used, and have significantly boosted the accuracy on body pose estimation [23, 38, 24, 34, 35, 7, 36, 6].”
MethodPose Machines: Articulated Pose Estimation via Inference Machines
Ramakrishna, V., Munoz, D., Hebert, M., Bagnell, J. A., & Sheikh, Y. A. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-10605-2_3 · Cited by 246 · cited 1×
“The convolutional pose machines architecture proposed by Wei et al. [38] used a multi-stage architecture based on a sequential prediction framework [29]; iteratively incorporating global context to refine part confi-dence maps and preserving multimodal uncertainty from previous iterations.”
MethodSelf-citationArticulated people detection and pose estimation: Reshaping the future
Pishchulin, L., Jain, A., Andriluka, M., Thormählen, T., & Schiele, B. (2012) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2012.6248052 · Cited by 228 · cited 2×
“A common approach [28, 11, 33, 16] is to divide and conquer the problem by employing a person detector and performing single-person pose estimation for each detection.”
BackgroundMethodArticulated part-based model for joint object detection and pose estimation
Sun, M., & Savarese, S. (2011) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2011.6126309 · Cited by 196 · cited 2×
“A common approach [28, 11, 33, 16] is to divide and conquer the problem by employing a person detector and performing single-person pose estimation for each detection.”
BackgroundMethodUsing k-Poselets for Detecting People and Localizing Their Keypoints
Gkioxari, G., Hariharan, B., Girshick, R., & Malik, J. (2014) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2014.458 · Cited by 175 · cited 2×
“A common approach [28, 11, 33, 16] is to divide and conquer the problem by employing a person detector and performing single-person pose estimation for each detection.”
BackgroundMethodMulti-person Pose Estimation with Local Joint-to-Person Associations
Iqbal, U., & Gall, J. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-48881-3_44 · Cited by 153 · cited 3×
“A common approach [28, 11, 33, 16] is to divide and conquer the problem by employing a person detector and performing single-person pose estimation for each detection.”
BackgroundMethodInfluential
Research works printed but not linked: 1
- 0, MSCOCO keypoint evaluation metric
Cited by
Sorted by citations
He, K., Gkioxari, G., Dollar, P., & Girshick, R. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.322 · Cited by 29,137
Deep High-Resolution Representation Learning for Human Pose Estimation
Sun, K., Xiao, B., Liu, D., & Wang, J. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00584 · Cited by 5,984
“This paper is interested in single-person pose estimation, which is the basis of other related problems, such as multiperson pose estimation [6, 26, 32, 38, 46, 55, 40, 45, 17, 69],”
BackgroundObject Detection With Deep Learning: A Review
Zhao, Z.-Q., Zheng, P., Xu, S.-T., & Wu, X. (2019) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2018.2876865 · Cited by 5,545
Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition
Yan, S., Xiong, Y., & Lin, D. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.12328 · Cited by 5,410
“Skeleton and joint trajectories of human bodies are robust to illumination change and scene variation, and they are easy to obtain owing to the highly accurate depth sensors or pose estimation algorithms (Shotton et al. 2011; Cao et al. 2017a).”
BackgroundMethodOpenPose: Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields
Cao, Z., Hidalgo, G., Simon, T., Wei, S.-E., & Sheikh, Y. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2929257 · Cited by 5,536
“An earlier version of this manuscript appeared in [3].”
BackgroundMethodInfluentialSelf-citation
Metadata
- Authors
- Cao, Z., Simon, T., Wei, S.-E., & Sheikh, Y.
- Affiliations
- Carnegie Mellon University (US)
- Venue
- 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2017-07
- Pages
- 1302-1310
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2559085405
- Cited by
- 7,539
- References
- 32
- Citations by year
- 2026: 384 · 2025: 774 · 2024: 968 · 2023: 1007 · 2022: 913 · 2021: 1016 · 2020: 1072 · 2019: 930 · 2018: 424 · 2017: 50
- FWCI
- 197.95
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- Funders
- Office of Naval Research
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Human Pose and Action Recognition
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face recognition and analysis
- Keywords
- multi-person pose estimation, part affinity fields, real-time pose estimation, bottom-up parsing, keypoint detection
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
