Action recognition method based on multi-stream attention-enhanced recursive graph convolution

Huaijun Wang; Bingqian Bai; Junhuai Li; Ke Hui; Xiang Wei

doi:10.1007/s10489-024-05719-0

ScienceGate Book Chapters

JOURNAL ARTICLE

Action recognition method based on multi-stream attention-enhanced recursive graph convolution

Huaijun Wang Bingqian Bai Junhuai Li Ke Hui Xiang Wei

Year: 2024 Journal: Applied Intelligence Vol: 54 (20)Pages: 10133-10147 Publisher: Springer Science+Business Media

DOI: 10.1007/s10489-024-05719-0

Get Full-Text PDF Get Analytical Report

Keywords:

Computer science Action recognition Robustness (evolution) Graph Pattern recognition (psychology) Artificial intelligence Convolution (computer science) Joint (building) Skeleton (computer programming) Theoretical computer science Artificial neural network

Metrics

Cited By

1.59

FWCI (Field Weighted Citation Impact)

Refs

0.75

Citation Normalized Percentile

Is in top 1%

Is in top 10%

Citation History

Topics

Human Pose and Action Recognition

Physical Sciences → Computer Science → Computer Vision and Pattern Recognition

Gait Recognition and Analysis

Physical Sciences → Engineering → Biomedical Engineering

Hand Gesture Recognition Systems

Physical Sciences → Computer Science → Human-Computer Interaction

Action recognition method based on multi-stream attention-enhanced recursive graph convolution

Metrics

Citation History

Topics

Related Documents

Multi-stream adaptive 3D attention graph convolution network for skeleton-based action recognition

Skeleton-based Action Recognition with Multi-stream, Temporal-Channel Enhanced Graph Convolution Network

Multi-Stream and Enhanced Spatial-Temporal Graph Convolution Network for Skeleton-Based Action Recognition

Multi-scale and attention enhanced graph convolution network for skeleton-based violence action recognition

Human Action Recognition Method Based on Multi-Attention Mechanism and Spatiotemporal Graph Convolution Networks