The MI-Motion Dataset and Benchmark for 3D Multi-Person Motion Prediction

TL;DR

This paper introduces the MI-Motion dataset and benchmark for 3D multi-person motion prediction, providing standardized data and evaluation settings to advance research in modeling complex human interactions.

Contribution

The paper presents a new large-scale dataset and benchmark for multi-person motion prediction, along with a novel baseline approach using graph and temporal convolutional networks.

Findings

The MI-Motion dataset contains 167k frames of multi-person skeleton sequences.

Benchmark results demonstrate the effectiveness of the proposed baseline approach.

The dataset covers 5 different activity scenes for comprehensive evaluation.

Abstract

3D multi-person motion prediction is a challenging task that involves modeling individual behaviors and interactions between people. Despite the emergence of approaches for this task, comparing them is difficult due to the lack of standardized training settings and benchmark datasets. In this paper, we introduce the Multi-Person Interaction Motion (MI-Motion) Dataset, which includes skeleton sequences of multiple individuals collected by motion capture systems and refined and synthesized using a game engine. The dataset contains 167k frames of interacting people's skeleton poses and is categorized into 5 different activity scenes. To facilitate research in multi-person motion prediction, we also provide benchmarks to evaluate the performance of prediction methods in three settings: short-term, long-term, and ultra-long-term prediction. Additionally, we introduce a novel baseline approach that leverages graph and temporal convolutional networks, which has demonstrated competitive results in multi-person motion prediction. We believe that the proposed MI-Motion benchmark dataset and baseline will facilitate future research in this area, ultimately leading to better understanding and modeling of multi-person interactions.