DocumentCode :
3748800
Title :
P-CNN: Pose-Based CNN Features for Action Recognition
Author :
Ch?ron;Ivan Laptev;Cordelia Schmid
Author_Institution :
Dept. d´Inf., Ecole Normale Super., Paris, France
fYear :
2015
Firstpage :
3218
Lastpage :
3226
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.
Keywords :
"Feature extraction","Tracking","Head","Neural networks","Dynamics","Face recognition"
Publisher :
ieee
Conference_Titel :
Computer Vision (ICCV), 2015 IEEE International Conference on
Electronic_ISBN :
2380-7504
Type :
conf
DOI :
10.1109/ICCV.2015.368
Filename :
7410725
Link To Document :
بازگشت