中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
MITPose: Multi-Granularity Feature Interaction for Human Pose Estimation

文献类型:会议论文

作者Jiayu, Zou1,2; Jie, Qin1,2; Zhen, Zhang1,2; Xingang, Wang1
出版日期2022-06
会议日期2022-07
会议地点Xi'an, China
页码300-306
英文摘要

Human pose estimation is broadly used in action recognition, Re-Identity, and multi-object tracking. Recently deep
convolutional neural networks have demonstrated their great power in human pose estimation. However, CNN-based methods are limited by the constrained receptive field that has poor performance in modeling global relationships of different body parts. In this paper, we propose a novel multi-granularity feature interaction network for human pose estimation (MITPose), which exploits the multi-granularity feature interaction in global-local level features, multi-scale features, and locality features. Our MITPose can efficiently leverage the long-range representation ability of transformer net and inductive locality of convolution net to obtain the comprehensive information for key point localization and relationship modeling. Extensive experiments illustrate that our proposed MITPose achieves state-of-the-art performance on the public COCO dataset.

语种英语
源URL[http://ir.ia.ac.cn/handle/173211/51537]  
专题精密感知与控制研究中心_精密感知与控制
通讯作者Xingang, Wang
作者单位1.中国科学院大学自动化研究所
2.中国科学院大学
推荐引用方式
GB/T 7714
Jiayu, Zou,Jie, Qin,Zhen, Zhang,et al. MITPose: Multi-Granularity Feature Interaction for Human Pose Estimation[C]. 见:. Xi'an, China. 2022-07.

入库方式: OAI收割

来源:自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。