# Exploring Vision Transformers for 3D Human Motion-Language Models with Motion Patches

arXiv: https://arxiv.org/abs/2405.04771 · HTML: https://mlsanity.com/paper/2405.04771/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 61 references that are in the map.
- First posted on arXiv 8 May 2024.

## Builds on (most cited first, 30 of 43)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [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)
- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [VL-BERT: Pre-training of Generic Visual-Linguistic Representations](https://mlsanity.com/paper/1908.08530/) (2019)
- [MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model](https://mlsanity.com/paper/2208.15001/) (2022)
- [Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation](https://mlsanity.com/paper/2311.17117/) (2023)
- [NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis](https://mlsanity.com/paper/1604.02808/) (2016)
- [T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations](https://mlsanity.com/paper/2301.06052/) (2023)
- [Executing your Commands via Motion Diffusion in Latent Space](https://mlsanity.com/paper/2212.04048/) (2022)
- [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)
- [Action-Conditioned 3D Human Motion Synthesis with Transformer VAE](https://mlsanity.com/paper/2104.05670/) (2021)
- [TEMOS: Generating diverse human motions from textual descriptions](https://mlsanity.com/paper/2204.14109/) (2022)
- [Action2Motion: Conditioned Generation of 3D Human Motions](https://mlsanity.com/paper/2007.15240/) (2020)
- [MotionCLIP: Exposing Human Motion Generation to CLIP Space](https://mlsanity.com/paper/2203.08063/) (2022)
- [TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts](https://mlsanity.com/paper/2207.01696/) (2022)
- [The KIT Motion-Language Dataset](https://mlsanity.com/paper/1607.03827/) (2016)
- [MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model](https://mlsanity.com/paper/2311.16498/) (2023)
- [BABEL: Bodies, Action and Behavior with English Labels](https://mlsanity.com/paper/2106.09696/) (2021)
- [Language2Pose: Natural Language Grounded Pose Forecasting](https://mlsanity.com/paper/1907.01108/) (2019)

## Built on by (most cited first, 22 of 22)

- [Chronologically Accurate Retrieval for Temporal Grounding of Motion-Language Models](https://mlsanity.com/paper/2407.15408/) (2024)
- [Causal Motion Diffusion Models for Autoregressive Motion Generation](https://mlsanity.com/paper/2602.22594/) (2026)
- [WaMo: Wavelet-Enhanced Multi-Frequency Trajectory Analysis for Fine-Grained Text-Motion Retrieval](https://mlsanity.com/paper/2508.03343/) (2025)
- [IRG-MotionLLM: Interleaving Motion Generation, Assessment and Refinement for Text-to-Motion Generation](https://mlsanity.com/paper/2512.10730/) (2025)
- [Self-Supervised Skeleton-Based Action Representation Learning: A Benchmark and Beyond](https://mlsanity.com/paper/2406.02978/) (2024)
- [IMoRe: Implicit Program-Guided Reasoning for Human Motion Q&A](https://mlsanity.com/paper/2508.01984/) (2025)
- [Infinite Motion: Extended Motion Generation via Long Text Instructions](https://mlsanity.com/paper/2407.08443/) (2024)
- [Beyond Global Alignment: Fine-Grained Motion-Language Retrieval via Pyramidal Shapley-Taylor Learning](https://mlsanity.com/paper/2601.21904/) (2026)
- [Geometric Visual Fusion Graph Neural Networks for Multi-Person Human-Object Interaction Recognition in Videos](https://mlsanity.com/paper/2506.03440/) (2025)
- [SegMo: Segment-aligned Text to 3D Human Motion Generation](https://mlsanity.com/paper/2512.21237/) (2025)
- [MonSTeR: a Unified Model for Motion, Scene, Text Retrieval](https://mlsanity.com/paper/2510.03200/) (2025)
- [Joint-Dataset Learning and Cross-Consistent Regularization for Text-to-Motion Retrieval](https://mlsanity.com/paper/2407.02104/) (2024)
- [Fine-grained Motion Retrieval via Joint-Angle Motion Images and Token-Patch Late Interaction](https://mlsanity.com/paper/2603.09930/) (2026)
- [Retrieving and Refining Winning Noise Tickets for Diffusion-Based Motion Generation](https://mlsanity.com/paper/2607.06843/) (2026)
- [(LiFT) Lightweight Fitness Transformer: A language-vision model for Remote Monitoring of Physical Training](https://mlsanity.com/paper/2506.06480/) (2025)
- [MoCHA: Denoising Caption Supervision for Motion-Text Retrieval](https://mlsanity.com/paper/2603.23684/) (2026)
- [Motion-Adapter: A Diffusion Model Adapter for Text-to-Motion Generation of Compound Actions](https://mlsanity.com/paper/2604.16135/) (2026)
- [Cross-Domain Human Action Recognition from Multiview Motion and Textual Descriptions](https://mlsanity.com/paper/2605.22697/) (2026)
- [CL4D: Contrastive Language-4D Pretraining for Vision-Language Reasoning in Dynamic Scenes](https://mlsanity.com/paper/2608.18734/) (2026)
- [Spatiotemporally Decoupled Autoregressive Diffusion Model for Human Motion Generation](https://mlsanity.com/paper/2608.23279/) (2026)
- [ReMoMask-2: Latent Retrieval-Augmented Masked Motion Generation](https://mlsanity.com/paper/2609.08365/) (2026)
- [MotionSpaceFlow: Representation-Aware Flow Matching in Direct Motion Space](https://mlsanity.com/paper/2609.34190/) (2026)

## Abstract (arXiv)

To build a cross-modal latent space between 3D human motion and language, acquiring large-scale and high-quality human motion data is crucial. However, unlike the abundance of image data, the scarcity of motion data has limited the performance of existing motion-language models. To counter this, we introduce "motion patches", a new representation of motion sequences, and propose using Vision Transformers (ViT) as motion encoders via transfer learning, aiming to extract useful knowledge from the image domain and apply it to the motion domain. These motion patches, created by dividing and sorting skeleton joints based on body parts in motion sequences, are robust to varying skeleton structures, and can be regarded as color image patches in ViT. We find that transfer learning with pre-trained weights of ViT obtained through training with 2D image data can boost the performance of motion analysis, presenting a promising direction for addressing the issue of limited motion data. Our extensive experiments show that the proposed motion patches, used jointly with ViT, achieve state-of-the-art performance in the benchmarks of text-to-motion retrieval, and other novel challenging tasks, such as cross-skeleton recognition, zero-shot motion classification, and human interaction recognition, which are currently impeded by the lack of data.