We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
Enhanced 3D Human Pose Estimation from Videos by Using Attention-Based Neural Network with Dilated Convolutions.
- Authors
Liu, Ruixu; Shen, Ju; Wang, He; Chen, Chen; Cheung, Sen-ching; Asari, Vijayan K.
- Abstract
The attention mechanism provides a sequential prediction framework for learning spatial models with enhanced implicit temporal consistency. In this work, we show a systematic design (from 2D to 3D) for how conventional networks and other forms of constraints can be incorporated into the attention framework for learning long-range dependencies for the task of pose estimation. The contribution of this paper is to provide a systematic approach for designing and training of attention-based models for the end-to-end pose estimation, with the flexibility and scalability of arbitrary video sequences as input. We achieve this by adapting temporal receptive field via a multi-scale structure of dilated convolutions. Besides, the proposed architecture can be easily adapted to a causal model enabling real-time performance. Any off-the-shelf 2D pose estimation systems, e.g. Our method achieves the state-of-the-art performance and outperforms existing methods by reducing the mean per joint position error to 33.4mm on Human 3.6M dataset. Our code is available at https://github.com/lrxjason/Attention3DHumanPose
- Subjects
CONVOLUTIONAL neural networks; HUMAN error
- Publication
International Journal of Computer Vision, 2021, Vol 129, Issue 5, p1596
- ISSN
0920-5691
- Publication type
Article
- DOI
10.1007/s11263-021-01436-0