Deep High-Resolution Representation Learning for Visual Recognition
The DOI matches its Crossref record; 190 of the 190 references it cites were found in a registry or an index.
Abstract
High-resolution representations are essential for position-sensitive vision problems, such as human pose estimation, semantic segmentation, and object detection. Existing state-of-the-art frameworks first encode the input image as a low-resolution representation through a subnetwork that is formed by connecting high-to-low resolution convolutions in series (e.g., ResNet, VGGNet), and then recover the high-resolution representation from the encoded low-resolution representation. Instead, our proposed network, named as High-Resolution Network (HRNet), maintains high-resolution representations through the whole process. There are two key characteristics: (i) Connect the high-to-low resolution convolution streams in parallel and (ii) repeatedly exchange the information across resolutions. The benefit is that the resulting representation is semantically richer and spatially more precise. We show the superiority of the proposed HRNet in a wide range of applications, including human pose estimation, semantic segmentation, and object detection, suggesting that the HRNet is a stronger backbone for computer vision problems. All the codes are available at https://github.com/HRNet.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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?
The cited source says what the claim attributes to it.
In the citing paper
“Alternatively, high-resolution representations are maintained during the entire process using a novel network, referred to as a High-Resolution Network (HRNet) [143, 144].”
From Review of deep learning: concepts, CNN architectures, challenges, applications, future directions (2021) · cites this paper as [143]
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“On the other hand ,DMA [59] focuses on open-vocabulary 3D scene understanding, aligning dense correspondences between 3D points, 2D images, and text, utilizing vision-language models to generalize across diverse indoor and outdoor scenarios.”
From Multimodal fusion and vision–language models: A survey for robot vision (2026) · cites this paper as [59]
Experimental — accuracy not yet measuredThe check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“Therefore, Weston University proposed an effective architecture called PeleeNet [132], which was constructed by conventional convolution.”
From A survey of model compression strategies for object detection (2023) · cites this paper as [132]
Experimental — accuracy not yet measured
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
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
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
U-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1506.01497 · Cited by 70,812
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805
Densely Connected Convolutional Networks
Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.243 · Cited by 48,566
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
Self-citation
Research works printed but not linked: 35
- [45] G. Ghiasi and C. C. Fowlkes. Occlusion coherence: Localizing occluded faces with a hierarchical deformable part model. In CVPR , pages 1899-1906, 2014. 20 -
- [48] R. A. G¨ uler, G. Trigeorgis, E. Antonakos, P. Snape, S. Zafeiriou, and I. Kokkinos. Densereg: Fully convolutional dense shape regression in-the-wild. In CVPR , pages 2614-2623, 2017. 21 -
- [34] X. Dong, Y. Yan, W. Ouyang, and Y. Yang. Style aggregated network for facial landmark detection. In CVPR , pages 379-388, 2018. 20, 21 -
- [35] X. Dong, S. Yu, X. Weng, S. Wei, Y. Yang, and Y. Sheikh. Supervision-by-registration: An unsupervised approach to improve the precision of facial landmark detectors. In CVPR , pages 360-368, 2018. 20, 21 -
- [39] Z. Feng, G. Hu, J. Kittler, W. J. Christmas, and X. Wu. Cascaded collaborative regression for robust facial landmark detection trained using a mixture of synthetic and real images with dynamic weighting. IEEE Trans. Image Processing , 24(11):3425-3440, 2015. 20 -
- [40] Z. Feng, J. Kittler, M. Awais, P. Huber, and X. Wu. Wing loss for robust facial landmark localisation with convolutional neural networks. In CVPR , pages 2235-2245, 2018. 19, 20 -
- [41] Z. Feng, J. Kittler, W. J. Christmas, P. Huber, and X. Wu. Dynamic attention-controlled cascaded shape regression exploiting training data augmentation and fuzzy-set sample weighting. In CVPR , pages 3681-3690, 2017. 20 -
- [191] S. Zhu, C. Li, C. C. Loy, and X. Tang. Face alignment by coarseto-fine shape searching. In CVPR , pages 4998-5006, 2015. 19, 20, 21 -
- [192] S. Zhu, C. Li, C. C. Loy, and X. Tang. Unconstrained face alignment via cascaded compositional learning. In CVPR , pages 3409-3417, 2016. 20 -
- [193] X. Zhu and D. Ramanan. Face detection, pose estimation, and landmark localization in the wild. In CVPR , pages 2879-2886, 2012. 19 -
- [186] E. Zhou, H. Fan, Z. Cao, Y. Jiang, and Q. Yin. Extensive facial landmark localization with coarse-to-fine convolutional network cascade. In ICCVW , pages 386-391, 2013. 21 -
- [75] M. K¨ ostinger, P. Wohlhart, P. M. Roth, and H. Bischof. Annotated facial landmarks in the wild: A large-scale, real-world database for facial landmark localization. In ICCV , pages 2144-2151, 2011. 19 -
- [5] P. N. Belhumeur, D. W. Jacobs, D. J. Kriegman, and N. Kumar. Localizing parts of faces using a consensus of exemplars. IEEE Trans. Pattern Anal. Mach. Intell. , 35(12):2930-2940, 2013. 19 -
- [10] X. P. Burgos-Artizzu, P. Perona, and P. Doll´ ar. Robust face landmark estimation under occlusion. In ICCV , pages 1513-1520, 2013. 19, 20 7. We provide the facial landmark detection results in the supplementary file. -
- [57] P. Hu and D. Ramanan. Bottom-up and top-down reasoning with hierarchical rectified gaussians. In CVPR , pages 5600-5609, 2016. 2 -
- [153] S. Xiao, J. Feng, J. Xing, H. Lai, S. Yan, and A. A. Kassim. Robust facial landmark detection via recurrent attentive-refinement networks. In ECCV , pages 57-72, 2016. 20 -
- [150] W. Wu and S. Yang. Leveraging intra and inter-dataset variations for robust face alignment. In CVPR , pages 2096-2105, 2017. 20 -
- [158] X. Xiong and F. D. la Torre. Supervised descent method and its applications to face alignment. In CVPR , pages 532-539. IEEE Computer Society, 2013. 20, 21 -
- [162] J. Yan, Z. Lei, D. Yi, and S. Z. Li. Learn to combine multiple hypotheses for accurate face alignment. In ICCVW , pages 392396, 2013. 21 -
- [164] S. Yang, P. Luo, C. C. Loy, and X. Tang. WIDER FACE: A face detection benchmark. In CVPR , pages 5525-5533, 2016. 19 -
- [169] X. Yu, J. Huang, S. Zhang, W. Yan, and D. N. Metaxas. Posefree facial landmark fitting via optimized part mixtures and cascaded deformable shape model. In ICCV , pages 1944-1951. IEEE Computer Society, 2013. 20 -
- [80] V. Le, J. Brandt, Z. Lin, L. D. Bourdev, and T. S. Huang. Interactive facial feature localization. In ECCV (3) , volume 7574 of Lecture Notes in Computer Science , pages 679-692. Springer, 2012. 19 -
- [78] A. Kumar and R. Chellappa. Disentangling 3d pose in a dendritic CNN for unconstrained 2d face alignment. In CVPR , pages 430439. IEEE Computer Society, 2018. 21 -
- [174] J. Zhang, M. Kan, S. Shan, and X. Chen. Occlusion-free face alignment: Deep regression networks coupled with de-corrupt autoencoders. In CVPR , pages 3428-3437, 2016. 20 -
- [175] J. Zhang, S. Shan, M. Kan, and X. Chen. Coarse-to-fine autoencoder networks (CFAN) for real-time face alignment. In ECCV (2) , volume 8690, pages 1-16. Springer, 2014. 21 -
- [116] S. Ren, X. Cao, Y. Wei, and J. Sun. Face alignment at 3000 FPS via regressing local binary features. In CVPR , pages 1685-1692, 2014. 20, 21 -
- [117] S. Ren, X. Cao, Y. Wei, and J. Sun. Face alignment via regressing local binary features. IEEE Trans. Image Processing , 25(3):12331245, 2016. 19 -
- [120] O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. S. Bernstein, A. C. Berg, and F. Li. Imagenet large scale visual recognition challenge. International Journal of Computer Vision , 115(3):211-252, 2015. 16 -
- [121] C. Sagonas, G. Tzimiropoulos, S. Zafeiriou, and M. Pantic. 300 faces in-the-wild challenge: The first facial landmark localization challenge. In ICCV Workshops , pages 397-403, 2013. 19 -
- [14] X. Cao, Y. Wei, F. Wen, and J. Sun. Face alignment by explicit shape regression. In CVPR , pages 2887-2894, 2012. 20, 21 -
- [101] J. Lv, X. Shao, J. Xing, C. Cheng, and X. Zhou. A deep regression architecture with two-stage re-initialization for high performance facial landmark detection. In CVPR , pages 3691-3700, 2017. 20 -
- [102] X. Miao, X. Zhen, X. Liu, C. Deng, V. Athitsos, and H. Huang. Direct shape regression networks for end-to-end face alignment. In CVPR , pages 5040-5049, 2018. 20, 21 -
- [23] Y. Chen, C. Shen, X. Wei, L. Liu, and J. Yang. Adversarial posenet: A structure-aware convolutional network for human pose estimation. In ICCV , pages 1221-1230, 2017. 19, 21 -
- [138] G. Trigeorgis, P. Snape, M. A. Nicolaou, E. Antonakos, and S. Zafeiriou. Mnemonic descent method: A recurrent process applied for end-to-end face alignment. In CVPR , pages 41774187, 2016. 21 -
- [146] Z. Wang, W. Li, B. Yin, Q. Peng, T. Xiao, Y. Du, Z. Li, X. Zhang, G. Yu, and J. Sun. Mscoco keypoints challenge 2018. In Joint Recognition Challenge Workshop at ECCV 2018 , 2018. 6 -
Cited by
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00986 · Cited by 35,534
“Since then, deeper and more effective con- 2While there are efficient methods to implement a sliding-window based convolution layer on general hardware, thanks to its shared kernel weights across a feature map, it is difficult for a sliding-window based self-attention layer to have efficient memory access in practice.…”
BackgroundReview of deep learning: concepts, CNN architectures, challenges, applications, future directions
Alzubaidi, L., Zhang, J., Humaidi, A. J., Al-Dujaili, A., Duan, Y., Al-Shamma, O., Santamaría, J., Fadhel, M. A., Al-Amidie, M., & Farhan, L. (2021) · Journal of Big Data · doi:10.1186/s40537-021-00444-8 · Cited by 7,906
Masked-attention Mask Transformer for Universal Image Segmentation
Cheng, B., Misra, I., Schwing, A. G., Kirillov, A., & Girdhar, R. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00135 · Cited by 3,565
Vision Transformers for Dense Prediction
Ranftl, R., Bochkovskiy, A., & Koltun, V. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01196 · Cited by 2,373
FairMOT: On the Fairness of Detection and Re-identification in Multiple Object Tracking
Zhang, Y., Wang, C., Wang, X., Zeng, W., & Liu, W. (2021) · International Journal of Computer Vision · doi:10.1007/s11263-021-01513-4 · Cited by 1,861
Self-citation
Metadata
- Authors
- Wang, J., Sun, K., Cheng, T., Jiang, B., Deng, C., Zhao, Y., Liu, D., Mu, Y., Tan, M., Wang, X., Liu, W., & Xiao, B.
- Affiliations
- Microsoft Research Asia (China) (CN)
- University of Science and Technology of China (CN)
- Huazhong University of Science and Technology (CN)
- Peking University (CN)
- South China University of Technology (CN)
- Griffith University (AU)
- Microsoft (United States) (US)
- ORCID
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 2021-10-01
- Volume
- 43
- Issue
- 10
- Pages
- 3349-3364
- ISSN
- 0162-8828 (ISSN-L)
- 2160-9292
- 1939-3539
- OpenAlex
- W3014641072
- Cited by
- 4,894
- References
- 169
- Citations by year
- 2026: 762 · 2025: 984 · 2024: 1040 · 2023: 896 · 2022: 670 · 2021: 454
- FWCI
- 204.78
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Transactions on Pattern Analysis and Machine Intelligence (publishedVersion)
- PubMed (publishedVersion)
- Griffith Research Online (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Human Pose and Action Recognition
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Keywords
- HRNet, human pose estimation, semantic segmentation, object detection, backbone networks
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.