计算机科学
人工智能
人工神经网络
联营
缩放
模式识别(心理学)
冗余(工程)
分类器(UML)
计算机视觉
机器学习
操作系统
镜头(地质)
石油工程
工程类
作者
Zhifu Zhao,Ziwei Chen,Jianan Li,Xiaotian Wang,Xuemei Xie,Lei Huang,Wanxin Zhang,Guangming Shi
出处
期刊:IEEE Transactions on Circuits and Systems for Video Technology
[Institute of Electrical and Electronics Engineers]
日期:2024-07-01
卷期号:34 (7): 5616-5629
被引量:3
标识
DOI:10.1109/tcsvt.2024.3358836
摘要
GCN-based methods have achieved remarkable performance in skeleton-based action recognition. However, existing methods have not explicitly attempted to remove temporal and spatial redundancy that might introduce additional computational costs. Inspired by the fact that humans always tend to glimpse at overall motion and then zoom into the most important spatio-temporal regions, we propose a Spatio Temporal Focused Dynamic Network (STFD-Net) trained with reinforcement learning for skeleton-based action recognition. Specifically, we first propose a global extractor with Skeleton Pooling Module (SPM) to enable the network to focus on overall motion information with a refined skeleton structure. Then, a local extractor, containing pair-wise part partition, tubelet proposal network, and Partition-Grouped Module (PGM), is proposed to extract local motion details as a complement to the overall motion information. Finally, the dynamic classifier utilizes a recurrent neural network to dynamically terminate the process once the network is adequately confident. Extensive experiments have demonstrated that the proposed network achieves SOTA level performance with lower computational cost on the NTU 60 and NTU 120 dataset.
科研通智能强力驱动
Strongly Powered by AbleSci AI