mlsanityData to 14 Oct 2026

ChatMotion: A Multimodal Multi-Agent for Human Motion Analysis

arXiv 2502.18180 ↗First posted 25 Feb 2025cs.AI cs.MAcited by 14

On the map: Multimodal LLMs / vision-language models → Embodied and 3D vision-language models

also in 1 more
Abstract (arXiv)

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.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 19 of its 44 references that are in the map. First posted on arXiv 25 Feb 2025.

Builds on

19 of 44 references.

References · 19

  1. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  2. 2023Video-LLaVA: Learning United Visual Representation by Alignment Before Projectioncited by 1,402
  3. 2023MVBench: A Comprehensive Multi-modal Video Understanding Benchmarkcited by 1,109
  4. 2023MotionGPT: Human Motion as a Foreign Languagecited by 527
  5. 2022MotionCLIP: Exposing Human Motion Generation to CLIP Spacecited by 408
  6. 2016The KIT Motion-Language Datasetcited by 338
  7. 2020We are More than Our Joints: Predicting how 3D Bodies Movecited by 115
  8. 2024MotionLLM: Understanding Human Behaviors from Human Motions and Videoscited by 90
  9. 2017Learning a bidirectional mapping between human whole-body motion and natural language using deep recurrent neural networkscited by 61
  10. 2023Motion Question Answering via Modular Motion Programscited by 27
  11. 2022Versatile Multi-Modal Pre-Training for Human-Centric Perceptioncited by 26
  12. 2024CHOPS: CHat with custOmer Profile Systems for Customer Service with LLMscited by 17
7 more
  1. 2025Intrinsic Entropy of Context Length Scaling in LLMscited by 14
  2. 2024Graph Canvas for Controllable 3D Scene Generationcited by 11
  3. 2023Efficient Domain Adaptation via Generative Prior for 3D Infant Pose Estimationcited by 8
  4. 2024Chain-of-Thought in Large Language Models: Decoding, Projection, and Activationcited by 6
  5. 2025Reassessing the Role of Chain-of-Thought in Sentiment Analysis: Insights and Limitationscited by 3
  6. 2024Category-Agnostic Pose Estimation for Point Cloudscited by 2
  7. 2020Human-Computer Interaction with Adaptable & Adaptive Motion-based Games for Healthcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 9.

14 papers.

Sort:

By area:

  1. 2026ConeSep: Cone-based Robust Noise-Unlearning Compositional Network for Composed Image Retrievalcited by 17
  2. 2026Task-Specific Efficiency Analysis: When Small Language Models Outperform Large Language Modelscited by 15
  3. 2025CountLLM: Towards Generalizable Repetitive Action Counting via Large Language Modelcited by 14
  4. 2026RAM: Recover Any 3D Human Motion in-the-Wildcited by 12
  5. 2025SafeMT: Multi-turn Safety for Multimodal Language Modelscited by 6
  6. 2026Video Understanding: From Geometry and Semantics to Unified Modelscited by 5
  7. 2025Revisiting Image Manipulation Localization under Realistic Manipulation Scenarioscited by 3
  8. 2025UniMo: Unifying 2D Video and 3D Human Motion with an Autoregressive Frameworkcited by 2
  9. 2025Coarse-to-Fine Personalized LLM Impressions for Streamlined Radiology Reportscited by 1
  10. 2026VigilFormer: Deformable Attention for Video Anomaly Detection with Causal Risk Inferencecited by 0
  11. 2026Bridging Geographic Bias in Urban Streetscape Inference via Lifelong Learning with Visual-Semantic Pivotingcited by 0
  12. 2026URDF Synthesis from RGB-D Sequences via Differentiable Joint Inference and Energy-Consistent Verificationcited by 0
2 more
  1. 2026Fine-grained Human Motion Understanding with Language Modelscited by 0
  2. 2026Human-Centric Intelligence in the Era of Foundation Models: A Surveycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024VersatileMotion: A Unified Framework for Motion Synthesis and Comprehension
  2. 2024A Unified Framework for Motion Reasoning and Generation in Human Interaction
  3. 2024Motion-Agent: A Conversational Framework for Human Motion Generation with LLMs
  4. 2025MotionGPT3: Human Motion as a Second Modality
  5. 2024MotionGPT-2: A General-Purpose Motion-Language Model for Motion Generation and Understanding
  6. 2024The Language of Motion: Unifying Verbal and Non-verbal Language of 3D Human Motion
  7. 2026NextMotionQA: Benchmarking and Judging Human Motion Understanding with Vision-Language Models
  8. 2025MotionVerse: A Unified Multimodal Framework for Motion Comprehension, Generation and Editing