CASIA OpenIR  > 智能感知与计算研究中心
Beyond Joints: Learning Representations From Primitive Geometries for Skeleton-Based Action Recognition and Detection
Wang Hongsong(王洪松)1,2,3,4; Wang Liang(王亮)1,2,3,4
2018
发表期刊IEEE Transactions on Image Processing
卷号27期号:9页码:4382 - 4394
摘要

Recently, skeleton-based action recognition becomes popular owing to the development of cost-effective depth sensors and fast pose estimation algorithms. Traditional methods based on pose descriptors often fail on large-scale datasets due to the limited representation of engineered features. Recent recurrent neural networks (RNN) based approaches mostly focus on the temporal evolution of body joints and neglect the geometric relations. In this paper, we aim to leverage the geometric relations among joints for action recognition. We introduce three primitive geometries: joints, edges and surfaces. Accordingly, a generic end-to-end RNN based network is designed to accommodate the three inputs. For action recognition, a novel viewpoint transformation layer and temporal dropout layers are utilized in the RNN based network to learn robust representations. And for action detection, we first perform frame-wise action classification, then exploit a novel multi-scale sliding window algorithm. Experiments on the large-scale 3D action recognition benchmark datasets show that joints, edges and surfaces are effective and complementary for different actions. Our approaches dramatically outperform the existing state-of-the-art methods for both tasks of action recognition and action detection.

关键词Skeleton-based Action Recognition Geometric Relations Viewpoint Transformation Action Detection
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/21061
专题智能感知与计算研究中心
作者单位1.Center for Research on Intelligent Perception and Computing (CRIPAC)
2.National Laboratory of Pattern Recognition (NLPR)
3.Institute of Automation, Chinese Academy of Sciences
4.University of Chinese Academy of Sciences
推荐引用方式
GB/T 7714
Wang Hongsong,Wang Liang. Beyond Joints: Learning Representations From Primitive Geometries for Skeleton-Based Action Recognition and Detection[J]. IEEE Transactions on Image Processing,2018,27(9):4382 - 4394.
APA Wang Hongsong,&Wang Liang.(2018).Beyond Joints: Learning Representations From Primitive Geometries for Skeleton-Based Action Recognition and Detection.IEEE Transactions on Image Processing,27(9),4382 - 4394.
MLA Wang Hongsong,et al."Beyond Joints: Learning Representations From Primitive Geometries for Skeleton-Based Action Recognition and Detection".IEEE Transactions on Image Processing 27.9(2018):4382 - 4394.
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
Beyond Joints Learni(2429KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Wang Hongsong(王洪松)]的文章
[Wang Liang(王亮)]的文章
百度学术
百度学术中相似的文章
[Wang Hongsong(王洪松)]的文章
[Wang Liang(王亮)]的文章
必应学术
必应学术中相似的文章
[Wang Hongsong(王洪松)]的文章
[Wang Liang(王亮)]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Beyond Joints Learning Representations From Primitive Geometries for Skeleton-Based Action Recognition and Detection.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

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。