Deep representation learning for human motion prediction and classification

TL;DR

This paper introduces a deep learning framework that learns a generalizable representation of human motion from large mocap datasets, enabling accurate prediction and classification of unseen movements.

Contribution

The work presents a novel encoding-decoding network architecture tailored for skeletal data, demonstrating improved motion prediction and feature extraction over existing methods.

Findings

Outperforms recent state-of-the-art skeletal motion prediction methods.

Deep networks trained on large mocap datasets generalize well to unseen motions.

Features extracted are effective for action 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.