A 3D motion image recognition model based on 3D CNN-GRU model and attention mechanism

C Cheng, H Xu - Image and Vision Computing, 2024 - Elsevier
Moving image recognition has become a well-explored problem in computer vision.
However, it is difficult for the traditional convolutional neural network (CNN) model to …

SkelFormer: Markerless 3D pose and shape estimation using skeletal transformers

V Davoodnia, S Ghorbani, A Messier… - arxiv preprint arxiv …, 2024 - arxiv.org
We introduce SkelFormer, a novel markerless motion capture pipeline for multi-view human
pose and shape estimation. Our method first uses off-the-shelf 2D keypoint estimators, pre …

KBody: Towards general, robust, and aligned monocular whole-body estimation

N Zioulis, JF O'Brien - … of the IEEE/CVF Conference on …, 2023 - openaccess.thecvf.com
KBody is a method for fitting a low-dimensional body model to an image. It follows a predict-
and-optimize approach, relying on data-driven model estimates for the constraints that will …

KBody: Balanced monocular whole-body estimation

N Zioulis, JF O'Brien - … of the IEEE/CVF Conference on …, 2023 - openaccess.thecvf.com
KBody is a method for fitting a low-dimensional body model to an image. It follows a predict-
and-optimize approach, relying on data-driven model estimates for the constraints that will …