LingoMotion: An Interpretable and Unambiguous Symbolic Representation for Human Motion

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Yao, Liu, Zhuchenyang, Xiao, Yu
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918387833110528
author Zhang, Yao
Liu, Zhuchenyang
Xiao, Yu
author_facet Zhang, Yao
Liu, Zhuchenyang
Xiao, Yu
contents Existing representations for human motion, such as MotionGPT, often operate as black-box latent vectors with limited interpretability and build on joint positions which can cause ambiguity. Inspired by the hierarchical structure of natural languages - from letters to words, phrases, and sentences - we propose LingoMotion, a motion language that facilitates interpretable and unambiguous symbolic representation for both simple and complex human motion. In this paper, we introduce the concept design of LingoMotion, including the definitions of motion alphabet based on joint angles, the morphology for forming words and phrases to describe simple actions like walking and their attributes like speed and scale, as well as the syntax for describing more complex human activities with sequences of words and phrases. The preliminary results, including the implementation and evaluation of motion alphabet using a large-scale motion dataset Motion-X, demonstrate the high fidelity of motion representation.
format Preprint
id arxiv_https___arxiv_org_abs_2603_13578
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle LingoMotion: An Interpretable and Unambiguous Symbolic Representation for Human Motion
Zhang, Yao
Liu, Zhuchenyang
Xiao, Yu
Computer Vision and Pattern Recognition
Existing representations for human motion, such as MotionGPT, often operate as black-box latent vectors with limited interpretability and build on joint positions which can cause ambiguity. Inspired by the hierarchical structure of natural languages - from letters to words, phrases, and sentences - we propose LingoMotion, a motion language that facilitates interpretable and unambiguous symbolic representation for both simple and complex human motion. In this paper, we introduce the concept design of LingoMotion, including the definitions of motion alphabet based on joint angles, the morphology for forming words and phrases to describe simple actions like walking and their attributes like speed and scale, as well as the syntax for describing more complex human activities with sequences of words and phrases. The preliminary results, including the implementation and evaluation of motion alphabet using a large-scale motion dataset Motion-X, demonstrate the high fidelity of motion representation.
title LingoMotion: An Interpretable and Unambiguous Symbolic Representation for Human Motion
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.13578