Paper
16 February 2022 Mini-TKAGCN: a lightweight graph convolutional network via temporal kernel attention for skeleton-based action recognition
Yanan Liu, Shiqi Dong, Hao Zhang, Dan Xu, Haipeng Li
Author Affiliations +
Proceedings Volume 12083, Thirteenth International Conference on Graphics and Image Processing (ICGIP 2021); 120832G (2022) https://doi.org/10.1117/12.2623547
Event: Thirteenth International Conference on Graphics and Image Processing (ICGIP 2021), 2021, Kunming, China
Abstract
Skeleton-based human action recognition has achieved a great interest in recent years. The strong robustness of skeleton data to scene and camera interference makes the recognition algorithm follow with interest robust features of actions. Recent works has proved the effectiveness of skeleton modeling based on graph and learning spatio-temporal modes by Graph Convolutional Network (GCN). Although GCNs have excellent ability of neighborhood feature learning, it is not good at capturing long-distance dependence between joints. In particular, linear temporal skeleton sequences contain a great quantity of joints., which makes the process of learning advanced temporal cues unduly slow. In this paper, we propose a temporal feature enhancer using Temporal Kernel Attention (TKA). And guided by TKA, we design a performance-oriented network TKA-GCN and a lightweight network Mini-TKA-GCN for skeleton-based action recognition. Finally, on NTU-RGBD 60 and Kinetics-Skeleton 400 datasets, TKA-GCN and Mini-TKA-GCN proposed by this work, outperform most advanced works.
© (2022) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Yanan Liu, Shiqi Dong, Hao Zhang, Dan Xu, and Haipeng Li "Mini-TKAGCN: a lightweight graph convolutional network via temporal kernel attention for skeleton-based action recognition", Proc. SPIE 12083, Thirteenth International Conference on Graphics and Image Processing (ICGIP 2021), 120832G (16 February 2022); https://doi.org/10.1117/12.2623547
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Convolution

RGB color model

Bone

Data modeling

Video

Performance modeling

Detection and tracking algorithms

Back to Top