Transfer Learning based Precise Pose Estimation with Insufficient Data
Authors: 
Wonje Choi, Honguk WooAuthors Info & Claims
Pages 50 - 55
Abstract
With the recent advance in computer vision techniques and the growing utility of real-time human pose detection and tracking, deep learning-based pose estimation has been intensively studied in recent years. These studies rely on large-scale datasets of human pose images, for which expensive annotation jobs are required due to the complex spatial structure of pose keypoints. In this work, we present a transfer learning-based pose estimation model that leverages low-cost synthetic datasets and regressive domain adaptation, enabling the sample-efficient learning on precise human poses. In evaluation, we demonstrate that our model achieves the high accurate pose estimation on a dataset of golf swing images, which is targeted for a virtual golf coaching application.
Supplementary Material
References
[1]
[n.d.]. COCO Keypoints Evaluation. [Online]. Available: https://cocodataset.org/#keypoints-eval. Accessed on: Dec 20, 2021.
[2]
Mykhaylo Andriluka, Leonid Pishchulin, Peter Gehler, and Bernt Schiele. June.2014. 2D Human Pose Estimation: New Benchmark and State of the Art Analysis. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Columbus, Ohio, 3686–3693.
[3]
Jinkun Cao, Hongyang Tang, Hao-Shu Fang, Xiaoyong Shen, Cewu Lu, and Yu-Wing Tai. OCT. 2019. Cross-Domain Adaptation for Animal Pose Estimation. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). Seoul, Korea, 9498–9507.
[4]
Yucheng Chen, Yingli Tian, and Mingyi He. MAR. 2020. Monocular human pose estimation: A survey of deep learning-based methods. Computer Vision and ImageUnderstanding192 (MAR. 2020), 102897–102919.
[5]
Yilun Chen, Zhicheng Wang, Yuxiang Peng, Zhiqiang Zhang, Gang Yu, and JianSun. June. 2018. Cascaded pyramid network for multi-person pose estimation. In Proceedings of the IEEE conference on computer vision and pattern recognition. Salt Lake City, Utah, 7103–7112.
[6]
Xiao Chu, Wei Yang, Wanli Ouyang, Cheng Ma, Alan L Yuille, and Xiaogang Wang.July. 2017. Multi-context attention for human pose estimation. In Proceedings of the IEEE conference on computer vision and pattern recognition. Honolulu, Hawaii,1831–1840.
[7]
Junguang Jiang, Yifei Ji, Ximei Wang, Yufeng Liu, Jianmin Wang, and Mingsheng Long. June. 2021. Regressive Domain Adaptation for Unsupervised Keypoint Detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). virtual only, 6780–6789.
[8]
Masatoshi Kimura, Takayoshi Yamashita, Yuji Yamauchi, and Hironobu Fujiyoshi. SEP. 2015. Facial point detection based on a convolutional neural network with optimal mini-batch procedure. In2015 IEEE International Conference on Image Processing (ICIP). Quebec City, Canada, 2860–2864.
[9]
Chen Li and Gim Hee Lee. June. 2021. From Synthetic to Real: Unsupervised Domain Adaptation for Animal Pose Estimation. In Proceedings of the IEEE/CVFConference on Computer Vision and Pattern Recognition (CVPR). virtual only, 1482–1491.
[10]
Tsung-Yi Lin, Michael Maire, Serge J. Belongie, Lubomir D. Bourdev, Ross B. Gir-shick, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C. Lawrence Zitnick. 2014. Microsoft COCO: Common Objects in Context. CoRRabs/1405.0312(2014). arXiv:1405.0312 http://arxiv.org/abs/1405.0312
[11]
A. Newell, K. Yang, and J. Deng. OCT. 2016. Stacked Hourglass Networks for Human Pose Estimation. In Proceedings of the European Conference on Computer Vision (ECCV). Amsterdam, Netherlands, 483–499.
[12]
Markus Oberweger, Paul Wohlhart, and Vincent Lepetit. DEC. 2015. Hands deep in deep learning for hand pose estimation. arXiv:1502.06807(DEC. 2015).
[13]
Markus Oberweger, Paul Wohlhart, and Vincent Lepetit. DEC. 2015. Training a feedback loop for hand pose estimation. In Proceedings of the IEEE international conference on computer vision. Santiago, Chile, 3316–3324.
[14]
George Papandreou, Tyler Zhu, Nori Kanazawa, Alexander Toshev, Jonathan Tompson, Chris Bregler, and Kevin Murphy. July. 2017. Towards accurate multi-person pose estimation in the wild. In Proceedings of the IEEE conference on computer vision and pattern recognition. Honolulu, Hawaii, 4903–4911.
[15]
Leonid Pishchulin, Eldar Insafutdinov, Siyu Tang, Bjoern Andres, Mykhaylo Andriluka, Peter V Gehler, and Bernt Schiele. June. 2016. Deepcut: Joint subsetpartition and labeling for multi person pose estimation. In Proceedings of the IEEE conference on computer vision and pattern recognition. Las Vegas, Nevada,4929–4937.
[16]
Ke Sun, Bin Xiao, Dong Liu, and Jingdong Wang. June. 2019. Deep High-Resolution Representation Learning for Human Pose Estimation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach, California, 5693–5703.
[17]
Yi Sun, Xiaogang Wang, and Xiaoou Tang. June. 2013. Deep convolutional network cascade for facial point detection. In Proceedings of the IEEE conference on computer vision and pattern recognition. Portland, Oregon, 3476–3483.
[18]
Jonathan Tompson, Murphy Stein, Yann Lecun, and Ken Perlin. 2014. Real-time continuous pose recovery of human hands using convolutional networks. ACM Transactions on Graphics (ToG)33, 5 (2014), 1–10.
[19]
Shih-En Wei, Varun Ramakrishna, Takeo Kanade, and Yaser Sheikh. June. 2016.Convolutional pose machines. In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. Las Vegas, Nevada, 4724–4732.
[20]
Bin Xiao, Haiping Wu, and Yichen Wei. SEP. 2018. Simple Baselines for Human Pose Estimation and Tracking. In Proceedings of the European Conference on Computer Vision (ECCV). Munich, Germany, 466–481.
[21]
Wei Yang, Shuang Li, Wanli Ouyang, Hongsheng Li, and Xiaogang Wang. OCT.2017. Learning feature pyramids for human pose estimation. In proceedings of the IEEE international conference on computer vision. Venice, Italy, 1281–1290.
[22]
Yizhai Zhang, Kuo Chen, Jingang Yi, Tao Liu, and Quan Pan. FEB. 2016. Whole-Body Pose Estimation in Human Bicycle Riding Using a Small Set of Wearable Sensors. IEEE/ASME Transactions on Mechatronics21, 1, 163–174.
[23]
Yuchen Zhang, Tianle Liu, Mingsheng Long, and Michael Jordan. June. 2019.Bridging theory and algorithm for domain adaptation. In International Conference on Machine Learning. Long Beach, California, 7404–7413.
[24]
Xingyi Zhou, Qingfu Wan, Wei Zhang, Xiangyang Xue, and Yichen Wei. June.2016. Model-based deep hand pose estimation. arXiv:1606.06854(June. 2016).
Recommendations
Deep Learning-based Human Pose Estimation: A Survey
Human pose estimation aims to locate the human body parts and build human body representation (e.g., body skeleton) from input data such as images and videos. It has drawn increasing attention during the past decade and has been utilized in a wide range ...
Animal pose estimation: A closer look at the state-of-the-art, existing gaps and opportunities
AbstractOver the past few years, research on animal pose estimation in computer vision field has grown in many aspects such as 2D and 3D pose estimation, 3D mesh reconstruction, and behavior prediction. Promoted by deep learning, more and more ...
Highlights- Collecting and categorizing animal pose estimation work from 2013 to 2021 into 2D and 3D pose estimation, model reconstruction, and behavior prediction, ...
Learning to Augment Poses for 3D Human Pose Estimation in Images and Videos
Existing 3D human pose estimation methods often suffer inferior generalization performance to new datasets, largely due to the limited diversity of 2D-3D pose pairs in the training data. To address this problem, we present PoseAug, a novel auto-...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
February 2022
128 pages
ISBN:9781450395670
DOI:10.1145/3523111
Copyright © 2022 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 02 May 2022
Check for updates
Qualifiers
- Research-article
- Research
- Refereed limited
Conference
ICMVA 2022
ICMVA 2022: 2022 the 5th International Conference on Machine Vision and Applications
February 18 - 20, 2022
Singapore, Singapore
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 129Total Downloads
- Downloads (Last 12 months)10
- Downloads (Last 6 weeks)0
Reflects downloads up to 10 Feb 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign inFull Access
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML Format