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

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 Note that the weights for OCHuman, are also called COCO-* as one only trains on COCO. So OCHuman-X = COCO-X The code to load and use the models is available at: https://github.com/amathislab/BUCTD We also share the predictions from various bottom-up models to reproduce the training (as zip files). See our repository for more details. 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