 |
Conference papers
P-CNN: Pose-based CNN Features for Action Recognition
Abstract : This work targets human action recognition in video. While recent methods typically represent actions by statistics of local video features, here we argue for the importance of a representation derived from human pose. To this end we propose a new Pose-based Convolutional Neural Network descriptor (P-CNN) for action recognition. The descriptor aggregates motion and appearance information along tracks of human body parts. We investigate different schemes of temporal aggregation and experiment with P-CNN features obtained both for automatically estimated and manually annotated human poses. We evaluate our method on the recent and challenging JHMDB and MPII Cooking datasets. For both datasets our method shows consistent improvement over the state of the art.
Cited literature [44 references]
https://hal.inria.fr/hal-01187690
Contributor : Thoth Team <>
Submitted on : Wednesday, September 23, 2015 - 1:55:35 PM
Last modification on : Tuesday, February 9, 2021 - 3:16:02 PM
Long-term archiving on: : Tuesday, December 29, 2015 - 9:36:06 AM
Contributor : Thoth Team <>
Submitted on : Wednesday, September 23, 2015 - 1:55:35 PM
Last modification on : Tuesday, February 9, 2021 - 3:16:02 PM
Long-term archiving on: : Tuesday, December 29, 2015 - 9:36:06 AM
File
P-CNN_cheronICCV15.pdf
Files produced by the author(s)