Context-aware Transformer Model for Crowd Localization

Yiming Gong, Kan Li

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

1 Citation (Scopus)

Abstract

Because crowd density varies greatly in real scenes, detection-based methods are less reliable in crowded areas. Existing methods of applying detection-based transformer models to complete crowd localization are also subject to the same constraints. Moreover, there are many small targets in the scene of dense crowds, which is even more obvious. To address this issue, our model employs context-aware module to extract information that fuses different scales, thereby addressing the potential rapid scale change, and uses transformer to build an end-to-end crowd localization model. Extensive experiments show that our model adaptively learns contextual information for crowd localization, significantly outperforming previous more advanced models.

Original languageEnglish
Title of host publication2022 3rd International Conference on Computer Vision, Image and Deep Learning and International Conference on Computer Engineering and Applications, CVIDL and ICCEA 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages199-202
Number of pages4
ISBN (Electronic)9781665459112
DOIs
Publication statusPublished - 2022
Event3rd International Conference on Computer Vision, Image and Deep Learning and International Conference on Computer Engineering and Applications, CVIDL and ICCEA 2022 - Virtual, Changchun, China
Duration: 20 May 202222 May 2022

Publication series

Name2022 3rd International Conference on Computer Vision, Image and Deep Learning and International Conference on Computer Engineering and Applications, CVIDL and ICCEA 2022

Conference

Conference3rd International Conference on Computer Vision, Image and Deep Learning and International Conference on Computer Engineering and Applications, CVIDL and ICCEA 2022
Country/TerritoryChina
CityVirtual, Changchun
Period20/05/2222/05/22

Keywords

  • Crowd counting
  • Crowd localization
  • transformer

Fingerprint

Dive into the research topics of 'Context-aware Transformer Model for Crowd Localization'. Together they form a unique fingerprint.

Cite this