Velocity-to-velocity human motion forecasting
文献类型：期刊论文
| 作者 | Wang, Hongsong2 ; Wang, Liang1; Feng, Jiashi2; Zhou, Daquan2
|
| 刊名 | PATTERN RECOGNITION
 |
| 出版日期 | 2022-04-01 |
| 卷号 | 124页码:11 |
| 关键词 | Human motion prediction Action anticipation |
| ISSN号 | 0031-3203 |
| DOI | 10.1016/j.patcog.2021.108424 |
| 通讯作者 | Wang, Hongsong(hongsongsui@gmail.com) |
| 英文摘要 | Forecasting human motion from a sequence of human poses is an important problem in the fields of computer vision and robotics. Most previous approaches merely consider learning the temporal dynamics of body joints or joint angles, while neglect derivatives of body joints (i.e., pose velocities) which could reasonably reduce noise impact and improve stability. To exploit the benefits of pose velocities, we propose the velocity-to-velocity learning paradigm for human motion prediction which attempts to directly build the sequence-to-sequence model in the velocity space. Two variant architectures based on recurrent encoder-decoder networks are introduced under this paradigm. Considering human motion as kinematics of rigid bodies, joint angles which denote transformation are the computations of inverse kinematics. Accordingly, a novel loss function in terms of rotation matrices is designed during training for human motion prediction through a rotation matrix transformation (RMT) layer. Finally, we present an effective training algorithm which exploits sequence transformation to improve model generalization. Our approaches substantially outperform state-of-the-art approaches on two large-scale datasets, Human3.6M and CMU Motion Capture, for both short-term prediction and long-term prediction. In particular, our model can competently forecast human-like and meaningful poses up to 10 0 0 milliseconds. The code is available on GitHub: https://github.com/hongsong-wang/RNN _ based _ human _ motion _ prediction .(c) 2021 Elsevier Ltd. All rights reserved. |
| WOS关键词 | ACTION RECOGNITION |
| 资助项目 | National Natural Science Foundation of China[61633021] ; National Natural Science Foundation of China[61721004] ; National Natural Science Foundation of China[U1803261] ; Shandong Provincial Key Research and Development Program[2019JZZY010119] ; CAS-AIR |
| WOS研究方向 | Computer Science ; Engineering |
| 语种 | 英语 |
| WOS记录号 | WOS:000776697500005 |
| 出版者 | ELSEVIER SCI LTD |
| 资助机构 | National Natural Science Foundation of China ; Shandong Provincial Key Research and Development Program ; CAS-AIR |
| 源URL | [http://ir.ia.ac.cn/handle/173211/48313]  |
| 专题 | 自动化研究所_智能感知与计算研究中心 |
| 通讯作者 | Wang, Hongsong |
| 作者单位 | 1.Chinese Acad Sci, Univ Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing, Peoples R China 2.Natl Univ Singapore, Singapore, Singapore |
| 推荐引用方式 GB/T 7714 | Wang, Hongsong,Wang, Liang,Feng, Jiashi,et al. Velocity-to-velocity human motion forecasting[J]. PATTERN RECOGNITION,2022,124:11. |
| APA | Wang, Hongsong,Wang, Liang,Feng, Jiashi,&Zhou, Daquan.(2022).Velocity-to-velocity human motion forecasting.PATTERN RECOGNITION,124,11. |
| MLA | Wang, Hongsong,et al."Velocity-to-velocity human motion forecasting".PATTERN RECOGNITION 124(2022):11. |
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。