Human Pose Estimation from Ambiguous Pressure Recordings with Spatio-temporal Masked Transformers
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917716838842368 |
|---|---|
| author | Davoodnia, Vandad Etemad, Ali |
| author_facet | Davoodnia, Vandad Etemad, Ali |
| contents | Despite the impressive performance of vision-based pose estimators, they generally fail to perform well under adverse vision conditions and often don't satisfy the privacy demands of customers. As a result, researchers have begun to study tactile sensing systems as an alternative. However, these systems suffer from noisy and ambiguous recordings. To tackle this problem, we propose a novel solution for pose estimation from ambiguous pressure data. Our method comprises a spatio-temporal vision transformer with an encoder-decoder architecture. Detailed experiments on two popular public datasets reveal that our model outperforms existing solutions in the area. Moreover, we observe that increasing the number of temporal crops in the early stages of the network positively impacts the performance while pre-training the network in a self-supervised setting using a masked auto-encoder approach also further improves the results. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2303_05691 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Human Pose Estimation from Ambiguous Pressure Recordings with Spatio-temporal Masked Transformers Davoodnia, Vandad Etemad, Ali Computer Vision and Pattern Recognition Machine Learning Despite the impressive performance of vision-based pose estimators, they generally fail to perform well under adverse vision conditions and often don't satisfy the privacy demands of customers. As a result, researchers have begun to study tactile sensing systems as an alternative. However, these systems suffer from noisy and ambiguous recordings. To tackle this problem, we propose a novel solution for pose estimation from ambiguous pressure data. Our method comprises a spatio-temporal vision transformer with an encoder-decoder architecture. Detailed experiments on two popular public datasets reveal that our model outperforms existing solutions in the area. Moreover, we observe that increasing the number of temporal crops in the early stages of the network positively impacts the performance while pre-training the network in a self-supervised setting using a masked auto-encoder approach also further improves the results. |
| title | Human Pose Estimation from Ambiguous Pressure Recordings with Spatio-temporal Masked Transformers |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2303.05691 |