Off-the-shelf ChatGPT is a Good Few-shot Human Motion Predictor

TL;DR

This paper introduces FMP-OC, a training-free framework that leverages off-the-shelf ChatGPT to perform few-shot human motion prediction, eliminating the need for dedicated motion prediction models.

Contribution

The paper proposes a novel training-free approach using ChatGPT for few-shot human motion prediction, enabling direct application without specialized training.

Findings

FMP-OC achieves accurate motion prediction without training.

The framework effectively extracts implicit knowledge from ChatGPT.

Motion-in-context learning enhances prediction performance.

Abstract

To facilitate the application of motion prediction in practice, recently, the few-shot motion prediction task has attracted increasing research attention. Yet, in existing few-shot motion prediction works, a specific model that is dedicatedly trained over human motions is generally required. In this work, rather than tackling this task through training a specific human motion prediction model, we instead propose a novel FMP-OC framework. In FMP-OC, in a totally training-free manner, we enable Few-shot Motion Prediction, which is a non-language task, to be performed directly via utilizing the Off-the-shelf language model ChatGPT. Specifically, to lead ChatGPT as a language model to become an accurate motion predictor, in FMP-OC, we first introduce several novel designs to facilitate extracting implicit knowledge from ChatGPT. Moreover, we also incorporate our framework with a motion-in-context learning mechanism. Extensive experiments demonstrate the efficacy of our proposed framework.