Deformable pose traversal convolution for 3D action and gesture recognition
The representation of 3D pose plays a critical role for 3D action and gesture recognition. Rather than representing a 3D pose directly by its joint locations, in this paper, we propose a Deformable Pose Traversal Convolution Network that applies one-dimensional convolution to traverse the 3D pose fo...
Saved in:
Main Authors: | Weng, Junwu, Liu, Mengyuan, Jiang, Xudong, Yuan, Junsong |
---|---|
其他作者: | School of Electrical and Electronic Engineering |
格式: | Conference or Workshop Item |
語言: | English |
出版: |
2020
|
主題: | |
在線閱讀: | https://hdl.handle.net/10356/140842 |
標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
機構: | Nanyang Technological University |
語言: | English |
相似書籍
-
Hand PointNet : 3D hand pose estimation using point sets
由: Ge, Liuhao, et al.
出版: (2018) -
Recognizing human actions as the evolution of pose estimation maps
由: Liu, Mengyuan, et al.
出版: (2020) -
Feature boosting network for 3D pose estimation
由: Liu, Jun, et al.
出版: (2022) -
Real-time 3D hand pose estimation with 3D convolutional neural networks
由: Ge, Liuhao, et al.
出版: (2019) -
Handling pose variation in face recognition using SIFT
由: Bhattacharya, B., et al.
出版: (2014)