Enhancing Human Pose Estimation with Privileged Learning
Transformer architecture shows significant improvements in different applications, such as Natural Language Processing, Computer Vision and even Graph Machine Learning. Recent advances in the Human Pose Estimation (HPE) show that Vision Transformers are a great choice for this problem as well. But e...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
FRUCT
2022-04-01
|
| Series: | Proceedings of the XXth Conference of Open Innovations Association FRUCT |
| Subjects: | |
| Online Access: | https://www.fruct.org/publications/fruct31/files/Mar2.pdf |
| _version_ | 1818231639652696064 |
|---|---|
| author | Alexander Marusov Mariam Kaprielova Radoslav Neychev |
| author_facet | Alexander Marusov Mariam Kaprielova Radoslav Neychev |
| author_sort | Alexander Marusov |
| collection | DOAJ |
| description | Transformer architecture shows significant improvements in different applications, such as Natural Language Processing, Computer Vision and even Graph Machine Learning. Recent advances in the Human Pose Estimation (HPE) show that Vision Transformers are a great choice for this problem as well. But even state of the art architectures require additional enhancements to the training process to achieve the best results. In this paper we propose the privileged learning approach to HPE by incorporating the information about body proportions into the training pipeline. We quantitatively and qualitatively evaluate our method on the standard benchmark dataset Human3.6M. The proposed method shows stable improvements using the same model architecture. |
| first_indexed | 2024-12-12T10:53:35Z |
| format | Article |
| id | doaj.art-f0105517f46d43a590a753673bd565bd |
| institution | Directory Open Access Journal |
| issn | 2305-7254 2343-0737 |
| language | English |
| last_indexed | 2024-12-12T10:53:35Z |
| publishDate | 2022-04-01 |
| publisher | FRUCT |
| record_format | Article |
| series | Proceedings of the XXth Conference of Open Innovations Association FRUCT |
| spelling | doaj.art-f0105517f46d43a590a753673bd565bd2022-12-22T00:26:43ZengFRUCTProceedings of the XXth Conference of Open Innovations Association FRUCT2305-72542343-07372022-04-0131117418010.23919/FRUCT54823.2022.9770903Enhancing Human Pose Estimation with Privileged LearningAlexander Marusov0Mariam Kaprielova1Radoslav Neychev2MIPT, RussiaDorodnicyn Computing Centre / Federal Research Center Computer Science and Control of the Russian Academy of Sciences, RussiaDorodnicyn Computing Centre / Federal Research Center Computer Science and Control of the Russian Academy of Sciences, RussiaTransformer architecture shows significant improvements in different applications, such as Natural Language Processing, Computer Vision and even Graph Machine Learning. Recent advances in the Human Pose Estimation (HPE) show that Vision Transformers are a great choice for this problem as well. But even state of the art architectures require additional enhancements to the training process to achieve the best results. In this paper we propose the privileged learning approach to HPE by incorporating the information about body proportions into the training pipeline. We quantitatively and qualitatively evaluate our method on the standard benchmark dataset Human3.6M. The proposed method shows stable improvements using the same model architecture.https://www.fruct.org/publications/fruct31/files/Mar2.pdfcomputer visionhuman pose estimationprivileged learningaction recognition |
| spellingShingle | Alexander Marusov Mariam Kaprielova Radoslav Neychev Enhancing Human Pose Estimation with Privileged Learning Proceedings of the XXth Conference of Open Innovations Association FRUCT computer vision human pose estimation privileged learning action recognition |
| title | Enhancing Human Pose Estimation with Privileged Learning |
| title_full | Enhancing Human Pose Estimation with Privileged Learning |
| title_fullStr | Enhancing Human Pose Estimation with Privileged Learning |
| title_full_unstemmed | Enhancing Human Pose Estimation with Privileged Learning |
| title_short | Enhancing Human Pose Estimation with Privileged Learning |
| title_sort | enhancing human pose estimation with privileged learning |
| topic | computer vision human pose estimation privileged learning action recognition |
| url | https://www.fruct.org/publications/fruct31/files/Mar2.pdf |
| work_keys_str_mv | AT alexandermarusov enhancinghumanposeestimationwithprivilegedlearning AT mariamkaprielova enhancinghumanposeestimationwithprivilegedlearning AT radoslavneychev enhancinghumanposeestimationwithprivilegedlearning |