Temporal Recursive Propagation Network for Action Recognition

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

Abstract

Efficient spatio-temporal information modeling is the key to action recognition. Present state-of-the-art suffers from the trade-off of spatiotemporal information modeling capability and model complexity. In this paper, we propose a novel temporal recursive propagation network (TRP) which can efficiently encode and fusion spatiotemporal information. TRP Module can be inserted in existing 2D CNN architectures such as ResNet and MobileNet. Abundant experiments show that TRP enjoys the performance over 3D CNN at lower computational cost than 2D CNN. We evaluate the proposed TRP on the large action recognition benchmark dataset UCF-101. TRP outperforms the state-of-the-art methods on UCF-101 from scratch.

Original languageEnglish
Title of host publicationProceedings - 2020 International Conference on Computer Engineering and Application, ICCEA 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages604-607
Number of pages4
ISBN (Electronic)9781728159041
DOIs
StatePublished - Mar 2020
Event2020 International Conference on Computer Engineering and Application, ICCEA 2020 - Guangzhou, China
Duration: 27 Mar 202029 Mar 2020

Publication series

NameProceedings - 2020 International Conference on Computer Engineering and Application, ICCEA 2020

Conference

Conference2020 International Conference on Computer Engineering and Application, ICCEA 2020
Country/TerritoryChina
CityGuangzhou
Period27/03/2029/03/20

Keywords

  • Efficient Action Recognition
  • Spatio-Temporal Modeling
  • Video Classification

Fingerprint

Dive into the research topics of 'Temporal Recursive Propagation Network for Action Recognition'. Together they form a unique fingerprint.

Cite this