ChatMotion: A Multimodal Multi-Agent for Human Motion Analysis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Lei, Jia, Sen, Wang, Jianhao, An, Zhaochong, Li, Jiaang, Hwang, Jenq-Neng, Belongie, Serge
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912249627541504
author Li, Lei
Jia, Sen
Wang, Jianhao
An, Zhaochong
Li, Jiaang
Hwang, Jenq-Neng
Belongie, Serge
author_facet Li, Lei
Jia, Sen
Wang, Jianhao
An, Zhaochong
Li, Jiaang
Hwang, Jenq-Neng
Belongie, Serge
contents Advancements in Multimodal Large Language Models (MLLMs) have improved human motion understanding. However, these models remain constrained by their "instruct-only" nature, lacking interactivity and adaptability for diverse analytical perspectives. To address these challenges, we introduce ChatMotion, a multimodal multi-agent framework for human motion analysis. ChatMotion dynamically interprets user intent, decomposes complex tasks into meta-tasks, and activates specialized function modules for motion comprehension. It integrates multiple specialized modules, such as the MotionCore, to analyze human motion from various perspectives. Extensive experiments demonstrate ChatMotion's precision, adaptability, and user engagement for human motion understanding.
format Preprint
id arxiv_https___arxiv_org_abs_2502_18180
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ChatMotion: A Multimodal Multi-Agent for Human Motion Analysis
Li, Lei
Jia, Sen
Wang, Jianhao
An, Zhaochong
Li, Jiaang
Hwang, Jenq-Neng
Belongie, Serge
Artificial Intelligence
Multiagent Systems
Advancements in Multimodal Large Language Models (MLLMs) have improved human motion understanding. However, these models remain constrained by their "instruct-only" nature, lacking interactivity and adaptability for diverse analytical perspectives. To address these challenges, we introduce ChatMotion, a multimodal multi-agent framework for human motion analysis. ChatMotion dynamically interprets user intent, decomposes complex tasks into meta-tasks, and activates specialized function modules for motion comprehension. It integrates multiple specialized modules, such as the MotionCore, to analyze human motion from various perspectives. Extensive experiments demonstrate ChatMotion's precision, adaptability, and user engagement for human motion understanding.
title ChatMotion: A Multimodal Multi-Agent for Human Motion Analysis
topic Artificial Intelligence
Multiagent Systems
url https://arxiv.org/abs/2502.18180