Hits:

Institution:人工智能学院

Title of Paper:SGM-Net: Skeleton-Guided Multimodal Network for Action Recognition

Teaching and Research Group:智能工程系

Journal:PATTERN RECOGNITION

Place of Publication:THE BOULEVARD, LANGFORD LANE, KIDLINGTON, OXFORD OX5 1GB, OXON, ENGLAND

Project Source:国际自然基金、省重点研发基金

Key Words:Action recognition; multi-modality; skeleton-guided

Summary:Single-modality human action recognition on RGB or skeleton has been extensively studied. Each of these two modalities has its own advantages as well as limitations, because they depict action from different perspectives. The feature of different modalities can complement each other for describing actions. Therefore, it is meaningful to fuse these two modalities using their complementarity for action recognition. However, existing multimodal methods fail to fully exploit the complementarity of RGB and skeleton modalities. In this paper, we propose......

All the Authors:Qingzhe Pan,Yuhan Cao,ZHAOZHIFU

First Author:Jianan Li

Indexed by:Journal paper

Correspondence Author:XIEXUEMEI

Document Code:000532701300025

Discipline:Engineering

First-Level Discipline:Electronics Science and Technology

Document Type:J

Volume:104

ISSN:0031-3203

Translation or Not:No

Date of Publication:2020-02-10

Included Journals:SCI

Date:2020-09-10