Knowledge Commons of Institute of Automation,CAS
Decoupled Representation Learning for Skeleton-Based Gesture Recognition | |
Liu, Jianbo1,2![]() ![]() ![]() ![]() ![]() | |
2020 | |
会议名称 | IEEE Conference on Computer Vision and Pattern Recognition |
会议日期 | 2020-6-14 |
会议地点 | Virtual |
摘要 | Skeleton-based gesture recognition is very challenging, as the high-level information in gesture is expressed by a sequence of complexly composite motions. Previous works often learn all the motions with a single model. In this paper, we propose to decouple the gesture into hand posture variations and hand movements, which are then modeled separately. For the former, the skeleton sequence is embedded into a 3D hand posture evolution volume (HPEV) to represent fine-grained posture variations. For the latter, the shifts |
七大方向——子方向分类 | 目标检测、跟踪与识别 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/46595 |
专题 | 多模态人工智能系统全国重点实验室_先进时空数据分析与学习 中国科学院自动化研究所 |
通讯作者 | Wang, Ying |
作者单位 | 1.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences 2.School of Artificial Intelligence, University of Chinese Academy of Sciences |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Liu, Jianbo,Liu, Yongcheng,Wang, Ying,et al. Decoupled Representation Learning for Skeleton-Based Gesture Recognition[C],2020. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Decoupled representa(818KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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。
修改评论