Spatial-Aware Regression for Keypoint Localization
Abstract
Regression-based keypoint localization shows advan-tages of high efficiency and better robustness to quantization errors than heatmap-based methods. However, existing regression-based methods discard the spatial location prior in input image with a global pooling, leading to in-ferior accuracy and are limited to single instance localization tasks. We study the regression-based keypoint localization from a new perspective by leveraging the spatiallocation prior. Instead of regressing on the pooled feature, the proposed Spatial-Aware Regression (SAR) maintains the spatial location map and outputs spatial coordinates and confidence score for each grid, which are optimized with a unified objective. Benefited by the location prior, these spatial-aware outputs can be efficiently optimized, resulting in better localization performance. Moreover, incorporating spatial prior makes SAR more general and can be applied into various keypoint localization tasks. We test the proposed method in 4 keypoint localization tasks including single/multi-person 2D/3D pose estimation, and the whole-body pose estimation. Extensive experiments demonstrate its promising performance, e.g., consistently outperforming recent regressions-based methods††project pagn: https://github.com/kennethwdk/SAR.
Integrity signals
Registry
Cites
Statistics
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?
When training with the SAR method, it is necessary to integrate spatial positional priors into the regression.
“When training with the SAR [19] method, it is necessary to integrate spatial positional priors into the regression.”
From Pose Estimation for Cross-Domain Non-Cooperative Spacecraft Based on Spatial-Aware Keypoints Regression (2024) · cites this paper as [19]
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 · see citing works
Microsoft 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 · see citing works
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 · see citing works
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 · see citing works
Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural Environments
Ionescu, C., Papava, D., Olaru, V., & Sminchisescu, C. (2014) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.248 · Cited by 3,653 · cited 1× · see citing works
“6M [6], a large-scale indoor benchmark for 3D human pose estimation.”
BackgroundDeepPose: 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 3,288 · see citing works
Simple Baselines for Human Pose Estimation and Tracking
Xiao, B., Wu, H., & Wei, Y. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01231-1_29 · Cited by 2,233 · see citing works
Joint 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 · see citing works
300 Faces in-the-Wild Challenge: The First Facial Landmark Localization Challenge
Sagonas, C., Tzimiropoulos, G., Zafeiriou, S. P., & Pantić, M. (2013) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2013.59 · Cited by 1,123 · see citing works
ViTPose: Simple Vision Transformer Baselines for Human Pose EstimationPreprint
Xu, Y.-F., Zhang, J., Zhang, Q., et al. (2022) · Neural Information Processing Systems · doi:10.48550/arxiv.2204.12484 · Cited by 1,118 · see citing works
Integral Human Pose Regression
Sun, X. N., Xiao, B., Wei, F., Liang, S., & Wei, Y. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01231-1_33 · Cited by 921 · see citing works
Towards 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 901 · see citing works
Human Pose Estimation with Iterative Error Feedback
Carreira, J., Agrawal, P., Fragkiadaki, K., & Malik, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.512 · Cited by 805 · see citing works
CrowdPose: Efficient Crowded Scenes Pose Estimation and a New Benchmark
Li, J., Wang, C., Zhu, H., Mao, Y., Fang, H.-S., & Lu, C. (2019) · 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.2019.01112 · Cited by 640 · see citing works
Distribution-Aware Coordinate Representation for Human Pose Estimation
Zhang, F., Zhu, X., Dai, H., Ye, M., & Zhu, C. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00712 · Cited by 588 · see citing works
Compositional Human Pose Regression
Sun, X. N., Shang, J., Liang, S., & Wei, Y. (2017) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.284 · Cited by 574 · see citing works
PifPaf: Composite Fields for Human Pose Estimation
Kreiss, S., Bertoni, L., & Alahi, A. (2019) · 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.2019.01225 · Cited by 574 · see citing works
TokenPose: Learning Keypoint Tokens for Human Pose Estimation
Li, Y., Zhang, S., Wang, Z., Yang, S., Yang, W., Xia, S., & Zhou, E. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01112 · Cited by 442 · see citing works
Self-citationBottom-Up Human Pose Estimation Via Disentangled Keypoint Regression
Geng, Z., Sun, K., Xiao, B., Zhang, Z., & Wang, J. (2021) · 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/cvpr46437.2021.01444 · Cited by 418 · see citing works
Camera Distance-Aware Top-Down Approach for 3D Multi-Person Pose Estimation From a Single RGB Image
Moon, G., Chang, J. Y., & Lee, K. M. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.01023 · Cited by 349 · see citing works
The Devil Is in the Details: Delving Into Unbiased Data Processing for Human Pose Estimation
Huang, J., Zhu, Z. D., Guo, F., & Huang, G. (2020) · 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/cvpr42600.2020.00574 · Cited by 299 · see citing works
Whole-Body Human Pose Estimation in the Wild
Jin, S., Xu, L., Xu, J., Wang, C., Liu, W., Qian, C., Ouyang, W., & Luo, P. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58545-7_12 · Cited by 275 · see citing works
SimCC: A Simple Coordinate Classification Perspective for Human Pose Estimation
Li, Y., Yang, S., Liu, P., Zhang, S., Wang, Y., Wang, Z., Yang, W., & Xia, S. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20068-7_6 · Cited by 267 · see citing works
Self-citationHuman Pose Regression with Residual Log-likelihood Estimation
Li, J., Bian, S., Zeng, A., Wang, C., Pang, B., Liu, W., & Lu, C. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01084 · Cited by 266 · see citing works
Pose2Seg: Detection Free Human Instance Segmentation
Zhang, S., Li, R., Dong, X., Rosin, P. L., Cai, Z., Xi, H., Yang, D., Huang, H., & Hu, S. (2019) · 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.2019.00098 · Cited by 235 · see citing works
Self-citationEnd-to-End Multi-Person Pose Estimation with Transformers
Shi, D., Wei, X., Li, L., Ren, Y. T., & Tan, W. (2022) · 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/cvpr52688.2022.01079 · Cited by 170 · see citing works
ZoomNAS: Searching for Whole-body Human Pose Estimation in the Wild
Xu, L., Jin, S., Liu, W., Qian, C., Ouyang, W., Luo, P., & Wang, X. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3197352 · Cited by 47 · see citing works
Mutual Supervision for Dense Object Detection
Gao, Z., Wang, L., & Wu, G. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00362 · Cited by 46 · see citing works
Contextual Instance Decoupling for Instance-Level Human Analysis
Wang, D., & Zhang, S. S. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3243223 · Cited by 14 · see citing works
Self-citation3D Human Mesh Recovery with Sequentially Global Rotation Estimation
Wang, D., & Zhang, S. S. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01373 · Cited by 11 · see citing works
Self-citationPink: Unveiling the Power of Referential Comprehension for Multi-modal LLMsPreprint
Xuan, S., Guo, Q., Yang, M., et al. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2310.00582 · Cited by 4 · see citing works
HumVis: Human-Centric Visual Analysis System
Wang, D., Zhang, S. S., Wang, Y., et al. (2023) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3581783.3612663 · Cited by 3 · see citing works
Self-citation
Flagged first, then by citations
Cited by
Sorted by citations
Wang, Z., Liu, Y., & Zhang, E. (2024) · Aerospace · doi:10.3390/aerospace11110948 · Cited by 5 · see citing works
- Authors
- Wang, D., & Zhang, S.
- Affiliations
- Peking University (CN)
- Venue
- 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2024-06-16
- Pages
- 624-633
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W4402753275
- Cited by
- 12
- References
- 32
- Citations by year
- 2026: 8 · 2025: 3 · 2024: 1
- FWCI
- 2.49
- 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)
- 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 › Advanced Image and Video Retrieval Techniques
- Keywords
- keypoint detection, 2D pose estimation, 3D pose estimation, multi-person pose estimation
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
