Multitask Non-Autoregressive Model for Human Motion Prediction

TL;DR

This paper introduces a non-autoregressive model for human motion prediction that predicts future poses independently, reducing error accumulation and improving performance over traditional autoregressive models.

Contribution

The paper proposes a novel non-autoregressive architecture with a context encoder, positional encoding, and multitask training for improved human motion prediction.

Findings

Outperforms state-of-the-art autoregressive methods on benchmarks

Reduces error accumulation in pose prediction

Effective multitask training enhances prediction accuracy

Abstract

Human motion prediction, which aims at predicting future human skeletons given the past ones, is a typical sequence-to-sequence problem. Therefore, extensive efforts have been continued on exploring different RNN-based encoder-decoder architectures. However, by generating target poses conditioned on the previously generated ones, these models are prone to bringing issues such as error accumulation problem. In this paper, we argue that such issue is mainly caused by adopting autoregressive manner. Hence, a novel Non-auToregressive Model (NAT) is proposed with a complete non-autoregressive decoding scheme, as well as a context encoder and a positional encoding module. More specifically, the context encoder embeds the given poses from temporal and spatial perspectives. The frame decoder is responsible for predicting each future pose independently. The positional encoding module injects positional signal into the model to indicate temporal order. Moreover, a multitask training paradigm is presented for both low-level human skeleton prediction and high-level human action recognition, resulting in the convincing improvement for the prediction task. Our approach is evaluated on Human3.6M and CMU-Mocap benchmarks and outperforms state-of-the-art autoregressive methods.