Skip to Main content Skip to Navigation
Conference papers

2D/3D Pose Estimation and Action Recognition using Multitask Deep Learning

Abstract : Action recognition and human pose estimation are closely related but both problems are generally handled as distinct tasks in the literature. In this work, we propose a multitask framework for jointly 2D and 3D pose estimation from still images and human action recognition from video sequences. We show that a single architecture can be used to solve the two problems in an efficient way and still achieves state-of-the-art results. Additionally , we demonstrate that optimization from end-to-end leads to significantly higher accuracy than separated learning. The proposed architecture can be trained with data from different categories simultaneously in a seamlessly way. The reported results on four datasets (MPII, Human3.6M, Penn Action and NTU) demonstrate the effectiveness of our method on the targeted tasks.
Document type :
Conference papers
Complete list of metadatas

Cited literature [59 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01815703
Contributor : Diogo Luvizon <>
Submitted on : Thursday, June 14, 2018 - 2:01:00 PM
Last modification on : Monday, January 25, 2021 - 3:16:04 PM
Long-term archiving on: : Saturday, September 15, 2018 - 2:04:09 PM

File

camera_ready.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01815703, version 1

Collections

Citation

Diogo Luvizon, David Picard, Hedi Tabia. 2D/3D Pose Estimation and Action Recognition using Multitask Deep Learning. The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2018, Salt Lake City, United States. ⟨hal-01815703⟩

Share

Metrics

Record views

202

Files downloads

589