Multi-Transmotion: Pre-trained Model for Human Motion Prediction

TL;DR

This paper introduces Multi-Transmotion, a transformer-based pre-trained model that integrates multiple datasets and modalities to improve human motion prediction for applications like autonomous navigation and robotics.

Contribution

It presents a novel multimodal pre-training framework with a new masking strategy, merging seven datasets to enhance human motion prediction capabilities.

Findings

Achieves competitive results on trajectory prediction tasks.

Demonstrates effectiveness across diverse datasets and modalities.

Provides publicly available code for reproducibility.

Abstract

The ability of intelligent systems to predict human behaviors is crucial, particularly in fields such as autonomous vehicle navigation and social robotics. However, the complexity of human motion have prevented the development of a standardized dataset for human motion prediction, thereby hindering the establishment of pre-trained models. In this paper, we address these limitations by integrating multiple datasets, encompassing both trajectory and 3D pose keypoints, to propose a pre-trained model for human motion prediction. We merge seven distinct datasets across varying modalities and standardize their formats. To facilitate multimodal pre-training, we introduce Multi-Transmotion, an innovative transformer-based model designed for cross-modality pre-training. Additionally, we present a novel masking strategy to capture rich representations. Our methodology demonstrates competitive performance across various datasets on several downstream tasks, including trajectory prediction in the NBA and JTA datasets, as well as pose prediction in the AMASS and 3DPW datasets. The code is publicly available: https://github.com/vita-epfl/multi-transmotion