Knowledge Commons of Institute of Automation,CAS
Decoupled Spatial-Temporal Attention Network for Skeleton-Based Action-Gesture Recognition | |
Shi L(史磊)1,2; Zhang YF(张一帆)1,2; Cheng J(程健)1,2,3; Lu HQ(卢汉清)1,2 | |
2020 | |
会议名称 | Asian Conference on Computer Vision (ACCV) |
会议日期 | 2020 |
会议地点 | 日本京都 |
出版者 | IEEE Computer Society |
摘要 | Dynamic skeletal data, represented as the 2D/3D coordinates of human joints, has been widely studied for human action recognition due to its high-level semantic information and environmental robustness. However, previous methods heavily rely on designing hand-crafted traversal rules or graph topologies to draw dependencies between the joints, which are limited in performance and generalizability. In this work, we present a novel decoupled spatial-temporal attention network (DSTA-Net) for skeleton-based action recognition. It involves solely the attention blocks, allowing for modeling spatial-temporal dependencies between joints without the requirement of knowing their positions or mutual connections. Specifically, to meet the specific requirements of the skeletal data, three techniques are proposed for building attention blocks, namely, spatial-temporal attention decoupling, decoupled position encoding and spatial global regularization. Besides, from the data aspect, we introduce a skeletal data decoupling technique to emphasize the specific characteristics of space/time and different motion scales, resulting in a more comprehensive understanding of the human actions. To test the effectiveness of the proposed method, extensive experiments are conducted on four challenging datasets for skeleton-based gesture and action recognition, namely, SHREC, DHG, NTU-60 and NTU-120, where DSTA-Net achieves state-of-the-art performance on all of them. |
语种 | 英语 |
七大方向——子方向分类 | 图像视频处理与分析 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/44377 |
专题 | 紫东太初大模型研究中心_图像与视频分析 |
作者单位 | 1.NLPR & AIRIA, Institute of Automation 2.CAS Center for Excellence in Brain Science and Intelligence Technology 3.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 |
推荐引用方式 GB/T 7714 | Shi L,Zhang YF,Cheng J,et al. Decoupled Spatial-Temporal Attention Network for Skeleton-Based Action-Gesture Recognition[C]:IEEE Computer Society,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 | ||
0359.pdf(530KB) | 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