Deep representation learning for human motion prediction and classification

Abstract

Generative models of 3D human motion are often restricted to a small number of activities and can therefore not generalize well to novel movements or applications. In this work we propose a deep learning framework for human motion capture data that learns a generic representation from a large corpus of motion capture data and generalizes well to new, unseen, motions. Using an encoding-decoding network that learns to predict future 3D poses from the most recent past, we extract a feature representation of human motion. Most work on deep learning for sequence prediction focuses on video and speech. Since skeletal data has a different structure, we present and evaluate different network architectures that make different assumptions about time dependencies and limb correlations. To quantify the learned features, we use the output of different layers for action classification and visualize the receptive fields of the network units. Our method outperforms the recent state of the art in skeletal motion prediction even though these use action specific training data. Our results show that deep feedforward networks, trained from a generic mocap database, can successfully be used for feature extraction from human motion data and that this representation can be used as a foundation for classification and prediction.

This paper is published at the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017

References in corpus (3)

• Caffe: Convolutional Architecture for Fast Feature Embedding
• Recurrent Network Models for Human Dynamics
• Space-Time Representation of People Based on 3D Skeletal Data: A Review

Cited by in corpus (10)

• Learning a bidirectional mapping between human whole-body motion and natural language using deep recurrent neural networks
• Investigating Pose Representations and Motion Contexts Modeling for 3D Motion Prediction
• Diverse Human Motion Prediction Guided by Multi-Level Spatial-Temporal Anchors
• DiffDance: Cascaded Human Motion Diffusion Model for Dance Generation
• Human-Robot Collaboration: From Psychology to Social Robotics
• Simultaneous Action Recognition and Human Whole-Body Motion and Dynamics Prediction from Wearable Sensors
• Predictive Learning: Using Future Representation Learning Variantial Autoencoder for Human Action Prediction
• Component attention network for multimodal dance improvisation recognition
• A Variational Time Series Feature Extractor for Action Prediction
• Real-Time Cleaning and Refinement of Facial Animation Signals