P-CNN: Pose-based CNN Features for Action Recognition
This work addresses action recognition for video analysis, offering a novel pose-based representation that improves performance on challenging datasets.
The authors tackled human action recognition in video by proposing a new Pose-based Convolutional Neural Network descriptor (P-CNN) that aggregates motion and appearance along human body part tracks, achieving consistent improvement over state-of-the-art methods on JHMDB and MPII Cooking datasets.
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.