Skip to content

The code of paper: Hypergraph Association Weakly Supervised Crowd Counting

Notifications You must be signed in to change notification settings

Boom5426/HACC-Hypergraph-Crowd-Counting

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 

Repository files navigation

HACC-Hypergraph-Association-Weakly-Supervised-Crowd-Counting

The code of paper: Hypergraph Association Weakly Supervised Crowd Counting

Abstruct

Weakly supervised crowd counting involves the regression of the number of individuals present in an image, using only the total number as the label. However, this task is plagued by two primary challenges: the large variation of head size and uneven distribution of crowd density. To address these issues, we propose a novel Hypergraph Association Crowd Counting (HACC) framework. Our approach consists of a new multi-scale expansion pyramid module which can efficiently handle the large variation of head size. Further, we propose a novel hypergraph association module to solve the problem of uneven distribution of crowd density by encoding higher-order associations among features, which opens a new direction to solve this problem. Experimental results on multiple datasets demonstrate that our HACC model achieves new state-of-the-art results.

Overview

image

visualization results

image

Reference

If you find this project is useful for your research, please cite:

@article{li2023hypergraph,
  title={Hypergraph Association Weakly Supervised Crowd Counting},
  author={Li, Bo and Zhang, Yong and Zhang, Chengyang and Piao, Xinglin and Yin, Baocai},
  journal={ACM Transactions on Multimedia Computing, Communications and Applications},
  year={2023},
  publisher={ACM New York, NY}
}

Baseline:

If you want to train the model, please put the module in Trancrowd

@article{liang2022transcrowd,
  title={TransCrowd: weakly-supervised crowd counting with transformers},
  author={Liang, Dingkang and Chen, Xiwu and Xu, Wei and Zhou, Yu and Bai, Xiang},
  journal={Science China Information Sciences},
  volume={65},
  number={6},
  pages={1--14},
  year={2022},
  publisher={Springer}
}

About

The code of paper: Hypergraph Association Weakly Supervised Crowd Counting

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages