An Efficient Action Recognition Framework Based on ELM and 3D CNN

Yiping Zou, Xuemei Ren*

*Corresponding author for this work

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

1 Citation (Scopus)

Abstract

Deep neural network is shown to be the most efficient method for video representation and has achieved state-of-art results on different datasets of action recognition. In this paper, we proposed a hybrid architecture which integrates deep convolutional neural networks and extreme learning machine. The hybrid structure makes the most of their advantages: in the first stage the deep residual 3D network learns the features from both temporal and spatial sequences, then the ELM, instead of traditional classifiers, classifies the actions without tuning the parameters. The resulting network can not only extract the representation fully, but also obtain more accurate results faster. We show the effectiveness and outperformance of the proposed strategy on experiments.

Original languageEnglish
Title of host publicationProceedings of 2020 Chinese Intelligent Systems Conference - Volume II
EditorsYingmin Jia, Weicun Zhang, Yongling Fu
PublisherSpringer Science and Business Media Deutschland GmbH
Pages641-648
Number of pages8
ISBN (Print)9789811584572
DOIs
Publication statusPublished - 2021
EventChinese Intelligent Systems Conference, CISC 2020 - Shenzhen, China
Duration: 24 Oct 202025 Oct 2020

Publication series

NameLecture Notes in Electrical Engineering
Volume706 LNEE
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Conference

ConferenceChinese Intelligent Systems Conference, CISC 2020
Country/TerritoryChina
CityShenzhen
Period24/10/2025/10/20

Keywords

  • Action recognition
  • Extreme learning machine
  • Hybrid structure

Fingerprint

Dive into the research topics of 'An Efficient Action Recognition Framework Based on ELM and 3D CNN'. Together they form a unique fingerprint.

Cite this