.png){kind=icon}
Return
Rethinking Global Context in Crowd Counting
.png){kind=icon}
PRE
AI
DOI：10.1007/s11633-023-1475-z.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This paper investigates the role of global context for crowd counting. Specifically, a pure transformer is used to extract features with global information from overlapping image patches. Inspired by classification, we add a context token to the input sequence, to facilitate information exchange with tokens corresponding to image patches throughout transformer layers. Due to the fact that transformers do not explicitly model the tried-and-true channel-wise interactions, we propose a token-attention module (TAM) to recalibrate encoded features through channel-wise attention informed by the context token. Beyond that, it is adopted to predict the total person count of the image through regression-token module (RTM). Extensive experiments on various datasets, including ShanghaiTech, UCF-QNRF, JHU-CROWD++ and NWPU, demonstrate that the proposed context extraction techniques can significantly improve the performance over the baselines.
Keywords:
Crowd counting
vision transformer
global context
attention
density map
Journal
IF:
8.7
Papers:
304
Citations:
882
Organization
View more organizations
Cited Papers
ShareSaveShareSaveA novel species-specific tandem repeat DNA family from Sinapis arvensis: detection of telomere-like sequences.png)
Genome
GenomeIF0
PREAI
ShareSave
View more