Skip to main navigation Skip to search Skip to main content

A ConvNet Structure Learning Spatiotemporal Features for Gesture Recognition

  • Guishuang Fan
  • , Shidong Jin
  • , Fei Wang*
  • , Dan Yan*
  • *Corresponding author for this work
  • Harbin Institute of Technology Shenzhen
  • Wuhan University of Technology

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Gesture recognition makes Human-computer interaction more intuitive and natural, while recognizing complex dynamic gestures challenging. Building a powerful and efficient recognition model is very critical. In this paper, we propose a new network structure for dynamic gesture recognition: S3D + ConvLSTM + Mobilenet. Common RGB video frames are fed into this network, and then processed in three model sections sequentially. Our proposed methodology was rigorously evaluated using two prominent large-scale gesture recognition datasets, namely the Jester and IsoGD datasets. Experimental results demonstrated that our approach achieved performance that are comparable to cutting-edge methods, which significantly reduces the training and prediction calculation overhead by nearly 70%.

Original languageEnglish
Title of host publicationProceedings - 2023 International Conference on Intelligent Perception and Computer Vision, CIPCV 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages40-46
Number of pages7
ISBN (Electronic)9798350323382
DOIs
StatePublished - 2023
Externally publishedYes
Event2023 International Conference on Intelligent Perception and Computer Vision, CIPCV 2023 - Hybrid, Xi'an, China
Duration: 19 May 202321 May 2023

Publication series

NameProceedings - 2023 International Conference on Intelligent Perception and Computer Vision, CIPCV 2023

Conference

Conference2023 International Conference on Intelligent Perception and Computer Vision, CIPCV 2023
Country/TerritoryChina
CityHybrid, Xi'an
Period19/05/2321/05/23

Keywords

  • S3D
  • dynamic gesture recognition
  • feature extraction
  • network structure

Fingerprint

Dive into the research topics of 'A ConvNet Structure Learning Spatiotemporal Features for Gesture Recognition'. Together they form a unique fingerprint.

Cite this