# Fine-grained Human Motion Understanding with Language Models

arXiv: https://arxiv.org/abs/2606.20888 · HTML: https://mlsanity.com/paper/2606.20888/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 44 of its 68 references that are in the map.
- First posted on arXiv 18 Jun 2026.

## Builds on (most cited first, 30 of 44)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Video-LLaVA: Learning United Visual Representation by Alignment Before Projection](https://mlsanity.com/paper/2311.10122/) (2023)
- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [TSM: Temporal Shift Module for Efficient Video Understanding](https://mlsanity.com/paper/1811.08383/) (2018)
- [NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding](https://mlsanity.com/paper/1905.04757/) (2019)
- [MotionGPT: Human Motion as a Foreign Language](https://mlsanity.com/paper/2306.14795/) (2023)
- [MotionCLIP: Exposing Human Motion Generation to CLIP Space](https://mlsanity.com/paper/2203.08063/) (2022)
- [MoMask: Generative Masked Modeling of 3D Human Motions](https://mlsanity.com/paper/2312.00063/) (2023)
- [Temporal Relational Reasoning in Videos](https://mlsanity.com/paper/1711.08496/) (2017)
- [Learning 3D Human Dynamics from Video](https://mlsanity.com/paper/1812.01601/) (2018)
- [BABEL: Bodies, Action and Behavior with English Labels](https://mlsanity.com/paper/2106.09696/) (2021)
- [Revisiting Skeleton-based Action Recognition](https://mlsanity.com/paper/2104.13586/) (2021)
- [FineGym: A Hierarchical Video Dataset for Fine-grained Action Understanding](https://mlsanity.com/paper/2004.06704/) (2020)
- [Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset](https://mlsanity.com/paper/2307.00818/) (2023)
- [PoseTrack: A Benchmark for Human Pose Estimation and Tracking](https://mlsanity.com/paper/1710.10000/) (2017)
- [Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Want](https://mlsanity.com/paper/2403.20271/) (2024)
- [MotionLLM: Understanding Human Behaviors from Human Motions and Videos](https://mlsanity.com/paper/2405.20340/) (2024)
- [Fg-T2M: Fine-Grained Text-Driven Human Motion Generation via Diffusion Model](https://mlsanity.com/paper/2309.06284/) (2023)
- [ChatPose: Chatting about 3D Human Pose](https://mlsanity.com/paper/2311.18836/) (2023)
- [AvatarGPT: All-in-One Framework for Motion Understanding, Planning, Generation and Beyond](https://mlsanity.com/paper/2311.16468/) (2023)
- [MotionGPT-2: A General-Purpose Motion-Language Model for Motion Generation and Understanding](https://mlsanity.com/paper/2410.21747/) (2024)
- [Motion-Agent: A Conversational Framework for Human Motion Generation with LLMs](https://mlsanity.com/paper/2405.17013/) (2024)
- [SportsCap: Monocular 3D Human Motion Capture and Fine-grained Understanding in Challenging Sports Videos](https://mlsanity.com/paper/2104.11452/) (2021)
- [Motion-X++: A Large-Scale Multimodal 3D Whole-body Human Motion Dataset](https://mlsanity.com/paper/2501.05098/) (2025)
- [Human Motion Instruction Tuning](https://mlsanity.com/paper/2411.16805/) (2024)

## Abstract (arXiv)

Fine-grained motion understanding requires knowing not only which poses occur, but also when they occur. Existing motion-language models either compress motion clips or concatenate pose features without retaining the timing of each pose, making action duration and temporal scale ambiguous under temporal subsampling. We introduce FiGMo, an LLM-based model that represents motion as timestamp-grounded skeletal poses, supporting reasoning over action order and duration. A unified pose encoder applies this representation to both 2D and 3D skeletons, including poses detected from real videos, while RGB can optionally provide contextual information. To reason over timestamped pose sequences, the model must understand both individual body configurations and how they change over time. As existing data provides limited pose-level grounding, we construct the required pose-to-motion supervision. Controlled experiments show that timestamps improve temporal localization and preserve physical timing under subsampling, while the constructed supervision drives the main performance gains. FiGMo achieves state-of-the-art results across motion question answering, dense motion captioning, and action recognition with detected poses. Our code is available at: https://github.com/Thomas-Markhorst/FiGMo