Audiovisual crowd counting dataset

Qingzhong Wang, Di Hu, Lichao Mou, Junyu Gao, Yuansheng Hua, Dejing Dou, Xiao Xiang ZhuZenodo 2020 · DOI · OpenAlexGitHub resource

Abstract

This dataset contains 1,935 annotated images, each image has one-second audio and a density map. For more details, please refer to our paper Ambient Sound Helps: Audiovisual Crowd Counting in Extreme Conditions and code.
BibTeX
@inproceedings{wang2020audiovisual,
  author = {Qingzhong Wang and Di Hu and Lichao Mou and Junyu Gao and Yuansheng Hua and Dejing Dou and Xiao Xiang Zhu},
  title = {{Audiovisual crowd counting dataset}},
  booktitle = {Zenodo},
  year = {2020},
  doi = {10.5281/zenodo.3828467},
}

Loading related content...

Figure