Dual-stream cross-modality fusion transformer for RGB-D action recognition

Zhen Liu; Jun Cheng; Libo Liu; Ziliang Ren; Qieshi Zhang; Chengqun Song

doi:10.1016/j.knosys.2022.109741

ScienceGate Book Chapters

JOURNAL ARTICLE

Dual-stream cross-modality fusion transformer for RGB-D action recognition

Zhen Liu Jun Cheng Libo Liu Ziliang Ren Qieshi Zhang Chengqun Song

Year: 2022 Journal: Knowledge-Based Systems Vol: 255 Pages: 109741-109741 Publisher: Elsevier BV

DOI: 10.1016/j.knosys.2022.109741

Get Full-Text PDF Get Analytical Report

Keywords:

Computer science Transformer Artificial intelligence Action recognition RGB color model Fusion Modality (human–computer interaction) Computer vision Pattern recognition (psychology) Voltage Electrical engineering

Metrics

Cited By

4.95

FWCI (Field Weighted Citation Impact)

Refs

0.95

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

Hand Gesture Recognition Systems

Physical Sciences → Computer Science → Human-Computer Interaction

Gait Recognition and Analysis

Physical Sciences → Engineering → Biomedical Engineering

Dual-stream cross-modality fusion transformer for RGB-D action recognition

Metrics

Citation History

Topics

Related Documents

Cross-Modality Compensation Convolutional Neural Networks for RGB-D Action Recognition

SlowFast Multimodality Compensation Fusion Swin Transformer Networks for RGB-D Action Recognition

Trear: Transformer-Based RGB-D Egocentric Action Recognition

HDCP: Hierarchical Dual Cross-Modality Prompts Guided RGB-D Fusion for 6D Object Pose Estimation

Feature Fusion for Dual-Stream Cooperative Action Recognition