There is a newer version of the record available.

Published September 30, 2023 | Version v1
Dataset Open

Rethinking pose estimation in crowds: overcoming the detection information bottleneck and ambiguity

  • 1. EPFL

Description

Here we provide neural networks weights for the best models in our article "Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity", ICCV 2023. Each model has the naming convention "dataset"-"modeltype".pth

The code to load and use the models is available at: https://github.com/amathislab/BUCTD

 

Link to the article: https://openaccess.thecvf.com/content/ICCV2023/papers/Zhou_Rethinking_Pose_Estimation_in_Crowds_Overcoming_the_Detection_Information_Bottleneck_ICCV_2023_paper.pdf

 

We also provide 

 

Files

Files (974.2 MB)

Name Size Download all
md5:17b6323cae57357a1d34214d9f85532a
255.4 MB Download
md5:69eb90875a6075d7881a72f413e2b44b
463.5 MB Download
md5:17b6323cae57357a1d34214d9f85532a
255.4 MB Download