Boosting-Crowd-Counting-via-Multifaceted-Attention
Boosting-Crowd-Counting-via-Multifaceted-Attention copied to clipboard
Official Implement of CVPR 2022 paper 'Boosting Crowd Counting via Multifaceted Attention'
作者您好,请问可以提供一份可视化代码吗,我这边也尝试给您发过邮件,但是因为域名被退回,也在知乎联系询问您了
您好,我按照官方下载JHU数据集并没有发现点的标注,只有个gt目录,里面全是框的标注,请问您的数据预处理用到的mat是怎么得到的,能否提供您的训练数据集
Thank you for sharing your awesome work ! Would you please share your pretrained model on NWPU as you did for JHU++ and UCF-QNRF ? It would be nice to...
Thanks for the awesome work! It would be great if you share a source code for IAL module and also a training script.
您好,源代码中的/models/transformer_cosine.py部分的第66行,这里feature的特征为什么是(64,3,512)的形状,这样无法与mask做矩阵乘法。  