Human Pose Estimation via Dynamic Information Transfer
Abstract
:1. Introduction
- We propose a multi-task learning framework that estimates human joints and bones in an end-to-end trainable manner.
- We propose a dynamic information transfer module (DITM) that exploits transferred bone-based part representations to obtain better pose estimation results.
- We integrated attention blocks into the DITM, which balance the shared feature across different granularity levels and induce the network to focus on important features.
2. Related Work
2.1. Human Pose Estimation
2.2. Multi-Task Learning
2.3. Attention Mechanism
3. Method
3.1. Feature Extraction
3.2. Decoder and Grouping
3.3. Dynamic Information Transfer Module
3.4. Attention Blocks
3.5. Loss Function
4. Experiments
4.1. Experiments on MPII Dataset
4.1.1. Dataset and Evaluation Metric
4.1.2. Implementation
4.1.3. Results
4.2. Experiments on COCO Dataset
4.2.1. Dataset and Evaluation Metric
4.2.2. Implementation
4.2.3. Results
4.3. Ablation Study
4.3.1. Network Design
4.3.2. Loss Function
5. Discussion
6. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Dantone, M.; Gall, J.; Leistner, C.; Van Gool, L. Body parts dependent joint regressors for human pose estimation in still images. IEEE Trans. Pattern Anal. Mach. Intell. 2014, 36, 2131–2143. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Wei, S.E.; Ramakrishna, V.; Kanade, T.; Sheikh, Y. Convolutional pose machines. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 27–30 June 2016; pp. 4724–4732. [Google Scholar]
- Shi, Q.; Di, H.; Lu, Y.; Lv, F.; Tian, X. Video pose estimation with global motion cues. Neurocomputing 2017, 219, 269–279. [Google Scholar] [CrossRef]
- Wang, M.; Tighe, J.; Modolo, D. Combining detection and tracking for human pose estimation in videos. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA, 13–19 June 2020; pp. 11088–11096. [Google Scholar]
- Bazarevsky, V.; Grishchenko, I.; Raveendran, K.; Zhu, T.; Zhang, F.; Grundmann, M. Blazepose: On-device real-time body pose tracking. arXiv 2020, arXiv:2006.10204. [Google Scholar]
- Bo, L.; Dai, Y.; Cheng, X.; Chen, H.; He, M. Skeleton based action recognition using translation-scale invariant image mapping and multi-scale deep CNN. In Proceedings of the IEEE International Conference on Multimedia and Expo Workshops, Michigan, WI, USA, 21–25 May 2017; pp. 601–604. [Google Scholar]
- Fang, H.S.; Cao, J.; Tai, Y.W.; Lu, C. Pairwise body-part attention for recognizing human-object interactions. In Proceedings of the European conference on computer vision (ECCV), Munich, Germany, 8–14 September 2018; pp. 51–67. [Google Scholar]
- Zhou, T.; Wang, W.; Liu, S.; Yang, Y.; Gool, L.V. Differentiable multi-granularity human representation learning for instance-aware human semantic parsing. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA, 20–25 June 2021; pp. 1622–1631. [Google Scholar]
- Barmpoutis, A. Tensor body: Real-time reconstruction of the human body and avatar synthesis from RGB-D. IEEE Trans. Cybern. 2013, 43, 1347–1356. [Google Scholar] [CrossRef] [PubMed]
- Felzenszwalb, P.F.; Huttenlocher, D.P. Pictorial structures for object recognition. Int. J. Comput. Vis. 2005, 61, 55–79. [Google Scholar] [CrossRef]
- Tompson, J.J.; Jain, A.; LeCun, Y.; Bregler, C. Joint training of a convolutional network and a graphical model for human pose estimation. In Proceedings of the Advances in neural information processing systems, Montreal, CA, 8–13 December 2014; pp. 1799–1807. [Google Scholar]
- Sun, M.; Savarese, S. Articulated part-based model for joint object detection and pose estimation. In Proceedings of the 2011 International Conference on Computer Vision, Washington, DC, USA, 6–13 November 2011; pp. 723–730. [Google Scholar]
- Chen, X.; Yuille, A. Articulated pose estimation by a graphical model with image dependent pairwise relations. arXiv 2014, arXiv:1407.3399. [Google Scholar]
- Cao, Z.; Hidalgo, G.; Simon, T.; Wei, S.E.; Sheikh, Y. OpenPose: Realtime multi-person 2D pose estimation using Part Affinity Fields. IEEE Trans. Pattern Anal. Mach. Intell. 2019, 43, 172–186. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Insafutdinov, E.; Pishchulin, L.; Andres, B.; Andriluka, M.; Schiele, B. Deepercut: A deeper, stronger, and faster multi-person pose estimation model. In Proceedings of the European Conference on Computer Vision (ECCV), Amsterdam, The Netherlands, 8–16 October 2016; pp. 34–50. [Google Scholar]
- Newell, A.; Yang, K.; Deng, J. Stacked hourglass networks for human pose estimation. In Proceedings of the European Conference on Computer Vision (ECCV), Amsterdam, The Netherlands, 8–16 October 2016; pp. 483–499. [Google Scholar]
- Toshev, A.; Szegedy, C. Deeppose: Human pose estimation via deep neural networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA, 23–28 June 2014; pp. 1653–1660. [Google Scholar]
- Xiao, B.; Wu, H.; Wei, Y. Simple baselines for human pose estimation and tracking. In Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany, 8–14 September 2018; pp. 466–481. [Google Scholar]
- Sun, K.; Xiao, B.; Liu, D.; Wang, J. Deep high-resolution representation learning for human pose estimation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA, 15–20 June 2019; pp. 5693–5703. [Google Scholar]
- Liu, W.; Bao, Q.; Sun, Y.; Mei, T. Recent advances of monocular 2d and 3d human pose estimation: A deep learning perspective. ACM Comput. Surv. 2022, 55, 1–41. [Google Scholar] [CrossRef]
- Yurtsever, M.M.E.; Eken, S. BabyPose: Real-time decoding of baby’s non-verbal communication using 2D video-based pose estimation. IEEE Sensors J. 2022, 22, 13776–13784. [Google Scholar] [CrossRef]
- Liang, S.; Sun, X.; Wei, Y. Compositional human pose regression. Comput. Vis. Image Underst. 2018, 176–177, 1–8. [Google Scholar] [CrossRef] [Green Version]
- Zhang, H.; Ouyang, H.; Liu, S.; Qi, X.; Shen, X.; Yang, R.; Jia, J. Human pose estimation with spatial contextual information. arXiv 2019, arXiv:1901.01760. [Google Scholar]
- Tang, W.; Yu, P.; Wu, Y. Deeply learned compositional models for human pose estimation. In Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany, 8–14 September 2018; pp. 190–206. [Google Scholar]
- Nie, X.; Feng, J.; Zuo, Y.; Yan, S. Human pose estimation with parsing induced learner. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 18–23 June 2018; pp. 2100–2108. [Google Scholar]
- Nie, X.; Feng, J.; Yan, S. Mutual learning to adapt for joint human parsing and pose estimation. In Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany, 8–14 September 2018; pp. 502–517. [Google Scholar]
- He, K.; Gkioxari, G.; Dollár, P.; Girshick, R. Mask r-cnn. In Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy, 22–29 October 2017; pp. 2961–2969. [Google Scholar]
- Wang, G.; Yuan, Y.; Chen, X.; Li, J.; Zhou, X. Learning discriminative features with multiple granularities for person re-identification. In Proceedings of the 26th ACM international conference on Multimedia, Seoul, Korea, 22–26 October 2018; pp. 274–282. [Google Scholar]
- Papandreou, G.; Zhu, T.; Kanazawa, N.; Toshev, A.; Tompson, J.; Bre- gler, C.; Murphy, K. Towards accurate multi-person pose estimation in the wild. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 21–26 July 2017; pp. 4903–4911. [Google Scholar]
- Sun, X.; Xiao, B.; Wei, F.; Liang, S.; Wei, Y. Integral human pose regression. In Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany, 8–14 September 2018; pp. 529–545. [Google Scholar]
- Yang, W.; Li, S.; Ouyang, W.; Li, H.; Wang, X. Learning feature pyramids for human pose estimation. In Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy, 22–29 October 2017; pp. 1290–1299. [Google Scholar]
- Chen, Y.; Wang, Z.; Peng, Y.; Zhang, Z.; Yu, G.; Sun, J. Cascaded pyramid network for multi-person pose estimation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 18–23 June 2018; pp. 7103–7112. [Google Scholar]
- Li, W.; Wang, Z.; Yin, B.; Peng, Q.; Du, Y.; Xiao, T.; Yu, G.; Lu, H.; Wei, Y.; Sun, J. Rethinking on multi-Stage networks for human pose estimation. arXiv 2019, arXiv:1901.00148. [Google Scholar]
- Yu, T.; Li, D.; Yang, Y.; Hospedales, T.; Xiang, T. Robust person re-identification by modelling feature uncertainty. In Proceedings of the IEEE International Conference on Computer Vision (ICCV), Seoul, Korea, 22 October–2 November 2019; pp. 552–561. [Google Scholar]
- Zhou, L.; Chen, Y.; Cao, C.; Chu, Y.; Wang, J.; Lu, H. Macro-micro mutual learning inside compositional model for human pose estimation. Neurocomputing 2021, 449, 176–188. [Google Scholar] [CrossRef]
- Rohrbach, M.; Stark, M.; Schiele, B. Evaluating knowledge transfer and zero-shot learning in a large-scale setting. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Colorado Springs, CO, USA, 20–25 June 2011; pp. 1641–1648. [Google Scholar]
- Bertinetto, L.; Henriques, J.F.; Valmadre, J.; Torr, P.; Vedaldi, A. Learning feed-forward one-shot learners. In Proceedings of the Advances in neural information processing systems, Barcelona, Spain, 5–10 December 2016; pp. 523–531. [Google Scholar]
- Hu, H.; Gu, J.; Zhang, Z.; Dai, J.; Wei, Y. Relation networks for object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 18–23 June 2018; pp. 3588–3597. [Google Scholar]
- Li, K.; Wang, Y.; Zhang, J.; Gao, P.; Song, G.; Liu, Y.; Li, H.; Qiao, Y. Uniformer: Unifying convolution and self-attention for visual recognition. arXiv 2022, arXiv:2201.09450. [Google Scholar]
- Wang, W.; Song, H.; Zhao, S.; Shen, J.; Zhao, S.; Hoi, S.C.H.; Ling, H. Learning unsupervised video object segmentation through visual attention. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA, 15–20 June 2019; pp. 3064–3074. [Google Scholar]
- Zhou, T.; Li, J.; Wang, S.; Tao, R.; Shen, J. Matnet: Motion-attentive transition network for zero-shot video object segmentation. IEEE Trans. Image Process. 2020, 29, 8326–8338. [Google Scholar] [CrossRef] [PubMed]
- Zhou, T.; Li, L.; Bredell, G.; Li, J.; Unkelbach, J.; Konukoglu, E. Volumetric memory network for interactive medical image segmentation. Med Image Anal. 2023, 83, 1361–8415. [Google Scholar] [CrossRef] [PubMed]
- Zhou, T.; Qi, S.; Wang, W.; Shen, J.; Zhu, S.C. Cascaded parsing of human-object interaction recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 2021, 44, 2827–2840. [Google Scholar] [CrossRef] [PubMed]
- Zhou, T.; Li, L.; Li, X.; Feng, C.M.; Li, J.; Shao, L. Group-Wise Learning for Weakly Supervised Semantic Segmentation. IEEE Transactions on Image Processing 2021, 31, 799–811. [Google Scholar] [CrossRef] [PubMed]
- Zhou, T.; Wang, W.; Konukoglu, E.; Van Gool, L. Rethinking semantic segmentation: A prototype view. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA, 19–24 June 2022; pp. 2582–2593. [Google Scholar]
- Hu, J.; Shen, L.; Sun, G. Squeeze-and-excitation networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 18–23 June 2018; pp. 7132–7141. [Google Scholar]
- Woo, S.; Park, J.; Lee, J.Y.; Kweon, I.S. Cbam: Convolutional block attention module. In Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany, 8–14 September 2018; pp. 3–19. [Google Scholar]
- Cai, Y.; Wang, Z.; Luo, Z.; Yin, B.; Du, A.; Wang, H.; Zhang, X.; Zhou, X.; Zhou, E.; Sun, J. Learning delicate local representations for multi-person pose estimation. In Proceedings of the European Conference on Computer Vision (ECCV), Glasgow, UK, 23–28 August 2020; pp. 455–472. [Google Scholar]
- Wang, J.; Sun, K.; Cheng, T.; Jiang, B.; Deng, C.; Zhao, Y.; Liu, D.; Mu, Y.; Tan, M.; Wang, X.; et al. Deep high-resolution representation learning for visual recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 2020, 43, 3349–3364. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Yuan, Y.; Chen, X.; Wang, J. Object-contextual representations for semantic segmentation. In Proceedings of the European Conference on Computer Vision (ECCV), Glasgow, UK, 23–28 August 2020; pp. 173–190. [Google Scholar]
- He, K.; Zhang, X.; Ren, S.; Sun, J. Deep Residual Learning for Image Recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 27–30 June 2016; pp. 770–778. [Google Scholar]
- Li, J.; Su, W.; Wang, Z. Simple pose: Rethinking and improving a bottom-up approach for multi-person pose estimation. In Proceedings of the AAAI Conference on Artificial Intelligence, New York, NY, USA, 7–12 February 2020; pp. 11354–11361. [Google Scholar]
- Girshick, R. Fast r-cnn. In Proceedings of the IEEE International Conference on Computer Vision (ICCV), Santiago, Chile, 7–13 December 2015; pp. 1440–1448. [Google Scholar]
- Andriluka, M.; Pishchulin, L.; Gehler, P.; Schiele, B. 2D Human Pose Estimation: New Benchmark and State of the Art Analysis. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA, 23–28 June 2014; pp. 3686–3693. [Google Scholar]
- Lin, T.Y.; Maire, M.; Belongie, S.; Hays, J.; Perona, P.; Ramanan, D.; Dollár, P.; Zitnick, C.L. Microsoft coco: Common objects in context. In Proceedings of the European Conference on Computer Vision (ECCV), Zurich, Switzerland, 6–12 September 2014; pp. 740–755. [Google Scholar]
- Loshchilov, I.; Hutter, F. Fixing weight decay regularization in adam. arXiv 2017, arXiv:1711.05101. [Google Scholar]
- Tompson, J.; Goroshin, R.; Jain, A.; LeCun, Y.; Bregler, C. Efficient object localization using convolutional networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA, 6–10 June 2015; pp. 648–656. [Google Scholar]
Method | Network Type | Technique | Datasets | Evaluation Measures | Highlights |
---|---|---|---|---|---|
Papandreou et al. [29] | ResNet | Two-step cascade | COCO | AP | Predict activation heat maps and offsets for each keypoint Keypoint-based non-maximum-suppression (NMS) |
Newell et al. [16] | Hourglass | Multiple stacked hourglass modules | MPII | PCKh | Captures and consolidates information across multiple scales Repeated bottom-up, top-down inference |
Yang et al. [31] | Hourglass | Learning feature pyramids | MPII | PCKh | Pyramid residual module (PRM) learns filters for input features with different resolutions |
Tang et al. [24] | DLCM | Deeply learned compositional models | LSP MPII | PCKh | Learns the hierarchical compositionality of visual patterns Intermediates supervision for hierarchical representation of body parts |
Xiao et al. [18] | ResNet | Combining the upsampling and convolutional parameters into deconvolutional layers | MPII COCO | PCKh AP | Simply adds a few deconvolutional layers after ResNet to generate high-resolution heat maps |
Sun et al. [19] | HRNet | Deep high-resolution representation learning | MPII COCO | PCKh AP | High-resolution representations of features across the whole network Multi-scale fusion |
Nie et al. [25] | Hourglass | Parsing-induced learner | MPII | PCKh | Exploits parsing information to extract complementary features Transferable across datasets |
Cai et al. [48] | RSN | Delicate local representation learning | MPII COCO | PCKh AP | Learns delicate local representations by efficient intra-level feature fusion Proposes an attention mechanism to make a trade-off between representations |
Zhou et al. [35] | Hourglass | Macro–micro mutual learning mechanism | MPII COCO | PCKh AP | Macro mutual learning module to conduct the information interaction Micro mutual learning module to propagate the mutual information |
Method | Head | Shoulder | Elbow | Wrist | Hip | Knee | Ankle | Total |
---|---|---|---|---|---|---|---|---|
Newell et al. [16] | ||||||||
Yang et al. [31] | ||||||||
Xiao et al. [18] | ||||||||
Tang et al. [24] | ||||||||
Sun et al. [19] | ||||||||
Zhou et al. [35] | ||||||||
Ours |
Method | Backbone | Pretrain | Input Size | Params | GFLOPs | AP | AR | ||||
---|---|---|---|---|---|---|---|---|---|---|---|
8-stage hourglass [16] | 8-stage hourglass | N | M | − | − | − | − | − | |||
CPN [32] | ResNet-50 | Y | M | − | − | − | − | − | |||
CPN + OHKM [32] | ResNet-50 | Y | M | − | − | − | − | − | |||
SimpleBaseline [18] | ResNet-50 | Y | M | ||||||||
SimpleBaseline [18] | ResNet-101 | Y | M | ||||||||
SimpleBaseline [18] | ResNet-152 | Y | M | ||||||||
HRNet-W32 [19] | HRNet-W32 | N | M | ||||||||
HRNet-W32 [19] | HRNet-W32 | Y | M | ||||||||
HRNet-W48 [19] | HRNet-W48 | Y | M | ||||||||
Macro–micro [35] | 8-stage hourglass | N | M | 74.3 | 89.7 | 81.3 | 70.9 | 81.1 | 79.6 | ||
Ours | HRNet-W32 | Y | M | 75.0 | 90.4 | 82.5 | 72.1 | 80.5 | 81.3 |
Method | Backbone | Input Size | Params | GFLOPs | AP | AR | ||||
---|---|---|---|---|---|---|---|---|---|---|
CPN [32] | ResNet-50 | M | − | − | − | − | − | |||
G-RMI [29] | ResNet-101 | 42.6 M | 57.0 | 68.5 | 87.1 | 75.5 | 65.8 | 73.3 | 73.3 | |
IPR [30] | ResNet-101 | 45.0 M | 11.0 | 67.8 | 88.2 | 74.8 | 63.9 | 74.0 | - | |
RSN [48] | RSN-50 | - | - | 72.5 | 93.0 | 81.3 | 69.9 | 76.5 | 78.8 | |
Macro–micro [35] | 8-stage hourglass | M | 73.7 | 91.9 | 81.7 | 70.6 | 79.3 | 79.1 | ||
Ours | HRNet-W32 | M | 73.9 | 92.3 | 82.0 | 70.6 | 79.5 | 84.7 |
Backbone | MTL | DITM | CAB | SAB | PCKh@0.5 |
---|---|---|---|---|---|
HRNet-W32 | 90.330 | ||||
✓ | 90.458 | ||||
✓ | ✓ | 90.585 | |||
✓ | ✓ | ✓ | 90.596 | ||
✓ | ✓ | ✓ | 90.632 | ||
✓ | ✓ | ✓ | ✓ | 90.658 |
Loss | PCKh@0.5 |
---|---|
MSE + MSE | 88.81 |
Focal L2 + Focal L2 | 88.58 |
Focal L2 + Smooth L1 | 88.90 |
Backbone | |||
---|---|---|---|
ResNet-50 |
Arch | Layer | IC | OC | Nums | K | S | P | BN | ReLU | Params | FLOPs |
---|---|---|---|---|---|---|---|---|---|---|---|
Backbone: HRNet-W32 | Stage 1-Stage 4 | 3 | 64 | - | - | - | - | - | - | 28.5 M | 9.49 G |
Bone Decoder Module | conv | 32 | 64 | 1 | 1 | 1 | 0 | Y | Y | 21.2k | 83.4 M |
conv | 64 | 32 | 3 | 1 | 1 | Y | Y | ||||
conv | 32 | 15 | 1 | 1 | 0 | Y | Y | ||||
Joint Decoder Module | conv | 32 | 32 | 1 | 1 | 1 | 0 | Y | Y | 21.2 k | 83.6 M |
conv | 32 | 32 | 3 | 1 | 1 | Y | Y | ||||
conv | 32 | 16 | 1 | 1 | 0 | Y | Y | ||||
Parameter Adapter | conv | 2 | 2 | 15 | 3 | 2 | 0 | N | N | 1.6 k | 0.6 M |
max-pooling | 2 | 2 | 2 | 2 | 0 | N | N | ||||
conv | 2 | 2 | 3 | 1 | 1 | N | N | ||||
max-pooling | 2 | 2 | 2 | 2 | 0 | N | N | ||||
conv | 2 | 2 | 3 | 1 | 1 | N | N | ||||
Transfer Module | conv | 16 | 16 | 1 | 1 | 1 | 0 | N | N | 3.2 k | 12.5 M |
adaptive conv | 2 | 2 | 15 | 7 | 1 | 3 | N | N | |||
Channel Attention Blocks | conv | 2 | 2 | 15 | 3 | 1 | 1 | Y | Y | 0.8 k | 3.1 M |
avg pooling | 2 | 2 | 32 | 1 | 0 | N | N | ||||
conv | 2 | 2 | 3 | 1 | 1 | Y | Y | ||||
sigmoid | 2 | 2 | - | - | - | - | - | ||||
Spatial Attention Blocks | conv | 16 | 16 | 1 | 3 | 1 | 1 | Y | Y | 4.0 k | 16.1 M |
conv | 16 | 16 | 1 | 1 | 0 | Y | Y | ||||
depthwise conv | 16 | 16 | 9 | 1 | 4 | Y | Y | ||||
sigmoid | 16 | 16 | - | - | - | - | - | ||||
Total | - | - | - | - | - | - | - | - | - | 28.6 M | 7.26 G |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Li, Y.; Shi, Q.; Song, J.; Yang, F. Human Pose Estimation via Dynamic Information Transfer. Electronics 2023, 12, 695. https://doi.org/10.3390/electronics12030695
Li Y, Shi Q, Song J, Yang F. Human Pose Estimation via Dynamic Information Transfer. Electronics. 2023; 12(3):695. https://doi.org/10.3390/electronics12030695
Chicago/Turabian StyleLi, Yihang, Qingxuan Shi, Jingya Song, and Fang Yang. 2023. "Human Pose Estimation via Dynamic Information Transfer" Electronics 12, no. 3: 695. https://doi.org/10.3390/electronics12030695
APA StyleLi, Y., Shi, Q., Song, J., & Yang, F. (2023). Human Pose Estimation via Dynamic Information Transfer. Electronics, 12(3), 695. https://doi.org/10.3390/electronics12030695