TY - GEN
T1 - Context-aware Transformer Model for Crowd Localization
AU - Gong, Yiming
AU - Li, Kan
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - 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.
AB - 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.
KW - Crowd counting
KW - Crowd localization
KW - transformer
UR - http://www.scopus.com/inward/record.url?scp=85135404594&partnerID=8YFLogxK
U2 - 10.1109/CVIDLICCEA56201.2022.9824361
DO - 10.1109/CVIDLICCEA56201.2022.9824361
M3 - Conference contribution
AN - SCOPUS:85135404594
T3 - 2022 3rd International Conference on Computer Vision, Image and Deep Learning and International Conference on Computer Engineering and Applications, CVIDL and ICCEA 2022
SP - 199
EP - 202
BT - 2022 3rd International Conference on Computer Vision, Image and Deep Learning and International Conference on Computer Engineering and Applications, CVIDL and ICCEA 2022
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 3rd International Conference on Computer Vision, Image and Deep Learning and International Conference on Computer Engineering and Applications, CVIDL and ICCEA 2022
Y2 - 20 May 2022 through 22 May 2022
ER -