.png){kind=icon}
返回
MSRT: multi-scale representation transformer for regression-based human pose estimation
.png){kind=icon}
PRE
AI
DOI：10.1007/s10044-023-01130-6.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In this paper, we are interested in the human pose estimation problem with a focus on leveraging discriminative pose features. Recent pose estimation works concentrate on extracting high-level features but ignore the low-level details, thus reducing the prediction accuracy. To mitigate the above issues, we propose an end-to-end method called multi-scale representation transformer network (MSRT). Our network consists of two key components: feature aggregation module (FAM) and transformers. The FAM splits and stacks feature maps of different scales, then fuses them to achieve multi-scale representation learning. This module makes up for the lack of detailed information in the high-level features. Furthermore, we utilize Transformers to identify long-range interactions among feature maps, and capture implicit body structure information, which allows the proposed network to refine the locations of terminal and occluded joints. Compared with existing regression-based methods, MSRT achieves superior results on the COCO2017 and MPII datasets.
Keyword:
Human pose estimation
Multi-scale representation
Transformer
Deep learning
期刊
IF:
2
论文数:
1.9K
被引数:
1.9K
机构
引用论文
.png){kind=icon}
Inflexibility of mental planning: A characteristic disorder with prefrontal lobe lesions?心理计划的僵化: 前额叶病变的特征性障碍？
PREAI
分享收藏
The food water energy nexus in an urban context: Connecting theory and practice for nexus governance
OAAI
OAAI分享收藏
查看更多内容