Human pose regression by combining indirect part detection and contextual information

Abstract : In this paper, we tackle the problem of human pose estimation from still images, which is a very active topic, specially due to its several applications, from image annotation to human-machine interface. We use the soft-argmax function to convert feature maps directly to body joint coordinates, resulting in a fully differentiable framework. Our method is able to learn heat maps representations indirectly, without additional steps of artificial ground truth generation. Consequently, contextual information can be included to the pose predictions in a seamless way. We evaluated our method on two challenging datasets, the Leeds Sports Poses (LSP) and the MPII Human Pose datasets, reaching the best performance among all the existing regression methods. Source code available at: https://github.com/dluvizon/pose-regression.
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-02314445
Contributor : Frédéric Davesne <>
Submitted on : Saturday, October 12, 2019 - 3:28:00 PM
Last modification on : Tuesday, February 18, 2020 - 10:28:43 AM

Links full text

Identifiers

Citation

Diogo Luvizon, Hedi Tabia, David Picard. Human pose regression by combining indirect part detection and contextual information. Computers and Graphics, Elsevier, 2019, 85, pp.15--22. ⟨10.1016/j.cag.2019.09.002⟩. ⟨hal-02314445⟩

Share

Metrics

Record views

95