User: Guest  Login
Document type:
Preprint
Author(s):
Soubarna Banik; Patricia Gschoßmann; Alejandro Mendoza Garcia; Alois Knoll
Title:
Occlusion Robust 3D Human Pose Estimation with StridedPoseGraphFormer and Data Augmentation
Abstract:
Occlusion is an omnipresent challenge in 3D human pose estimation (HPE). In spite of the large amount of research dedicated to 3D HPE, only a limited number of studies address the problem of occlusion explicitly. To fill this gap, we propose to combine exploitation of spatio-temporal features with synthetic occlusion augmentation during training to deal with occlusion. To this end, we build a spatio-temporal 3D HPE model, StridedPoseGraphFormer based on graph convolution and transformers, an...     »
Keywords:
3D Human Pose Estimation, Occlusion, Graph Convolution Network, Transformer
Dewey Decimal Classification:
500 Naturwissenschaften
Journal title:
IEEE Internatioal Joint Conference on Neural Networks
Year:
2023
Copyright statement:
2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
 BibTeX