P-CNN: Pose-based CNN Features for Action Recognition

2015/06/11 by Guilhem Chéron, Ivan Laptev, Chéron, Guilhem +3 · 1 citation
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Hand Gesture Recognition Systems #Human Pose and Action Recognition #Video Surveillance and Tracking Methods

paper · doi:10.48550/arxiv.1506.03607

openalex publication_date 2015/06/11 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• Random sample consensus
• Gradient-based learning applied to document recognition

Cited by

• Explainable Action Form Assessment by Exploiting Multimodal Chain-of-Thoughts Reasoning

Related

• Action Recognition with Image Based CNN Features
• Action Recognition via Pose-Based Graph Convolutional Networks with Intermediate Dense Supervision
• Pose from Action: Unsupervised Learning of Pose Features based on Motion
• R-CNNs for Pose Estimation and Action Detection
• Dynamic Action Recognition: A convolutional neural network model for\n temporally organized joint location data