# CASIM: Composite Aware Semantic Injection for Text to Motion Generation

arXiv: https://arxiv.org/abs/2502.02063 · HTML: https://mlsanity.com/paper/2502.02063/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 37 references that are in the map.
- First posted on arXiv 4 Feb 2025.

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

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model](https://mlsanity.com/paper/2208.15001/) (2022)
- [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)
- [MotionGPT: Human Motion as a Foreign Language](https://mlsanity.com/paper/2306.14795/) (2023)
- [Action2Motion: Conditioned Generation of 3D Human Motions](https://mlsanity.com/paper/2007.15240/) (2020)
- [MoMask: Generative Masked Modeling of 3D Human Motions](https://mlsanity.com/paper/2312.00063/) (2023)
- [TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts](https://mlsanity.com/paper/2207.01696/) (2022)
- [Human Motion Diffusion as a Generative Prior](https://mlsanity.com/paper/2303.01418/) (2023)
- [The KIT Motion-Language Dataset](https://mlsanity.com/paper/1607.03827/) (2016)
- [Guided Motion Diffusion for Controllable Human Motion Synthesis](https://mlsanity.com/paper/2305.12577/) (2023)
- [Semantic Graph Convolutional Networks for 3D Human Pose Regression](https://mlsanity.com/paper/1904.03345/) (2019)
- [Listen, Denoise, Action! Audio-Driven Motion Synthesis with Diffusion Models](https://mlsanity.com/paper/2211.09707/) (2022)
- [FineMoGen: Fine-Grained Spatio-Temporal Motion Generation and Editing](https://mlsanity.com/paper/2312.15004/) (2023)
- [MotionLLM: Understanding Human Behaviors from Human Motions and Videos](https://mlsanity.com/paper/2405.20340/) (2024)
- [Generating Human Interaction Motions in Scenes with Text Control](https://mlsanity.com/paper/2404.10685/) (2024)
- [MotionFix: Text-Driven 3D Human Motion Editing](https://mlsanity.com/paper/2408.00712/) (2024)
- [AvatarGPT: All-in-One Framework for Motion Understanding, Planning, Generation and Beyond](https://mlsanity.com/paper/2311.16468/) (2023)
- [Generating Human Motion in 3D Scenes from Text Descriptions](https://mlsanity.com/paper/2405.07784/) (2024)
- [Act As You Wish: Fine-Grained Control of Motion Diffusion Model with Hierarchical Semantic Graphs](https://mlsanity.com/paper/2311.01015/) (2023)
- [Iterative Motion Editing with Natural Language](https://mlsanity.com/paper/2312.11538/) (2023)
- [Score-Guided Diffusion for 3D Human Recovery](https://mlsanity.com/paper/2403.09623/) (2024)
- [Unimotion: Unifying 3D Human Motion Synthesis and Understanding](https://mlsanity.com/paper/2409.15904/) (2024)
- [T2LM: Long-Term 3D Human Motion Generation from Multiple Sentences](https://mlsanity.com/paper/2406.00636/) (2024)
- [M3Act: Learning from Synthetic Human Group Activities](https://mlsanity.com/paper/2306.16772/) (2023)
- [On the Equivalency, Substitutability, and Flexibility of Synthetic Data](https://mlsanity.com/paper/2403.16244/) (2024)

## Built on by (most cited first, 2 of 2)

- [MultiAct: Text-to-Motion Generation from Composite Text via Tailored Attention Guidance](https://mlsanity.com/paper/2605.30925/) (2026)
- [Odoriko: A Shape-Aware Multimodal Diffusion Framework for Human Motion](https://mlsanity.com/paper/2606.21135/) (2026)

## Abstract (arXiv)

Recent advances in generative modeling and tokenization have driven significant progress in text-to-motion generation, leading to enhanced quality and realism in generated motions. However, effectively leveraging textual information for conditional motion generation remains an open challenge. We observe that current approaches, primarily relying on fixed-length text embeddings (e.g., CLIP) for global semantic injection, struggle to capture the composite nature of human motion, resulting in suboptimal motion quality and controllability. To address this limitation, we propose the Composite Aware Semantic Injection Mechanism (CASIM), comprising a composite-aware semantic encoder and a text-motion aligner that learns the dynamic correspondence between text and motion tokens. Notably, CASIM is model and representation-agnostic, readily integrating with both autoregressive and diffusion-based methods. Experiments on HumanML3D and KIT benchmarks demonstrate that CASIM consistently improves motion quality, text-motion alignment, and retrieval scores across state-of-the-art methods. Qualitative analyses further highlight the superiority of our composite-aware approach over fixed-length semantic injection, enabling precise motion control from text prompts and stronger generalization to unseen text inputs.