mlsanityData to 14 Oct 2026

Fg-T2M: Fine-Grained Text-Driven Human Motion Generation via Diffusion Model

arXiv 2309.06284 ↗First posted 12 Sep 2023cs.CV cs.MMcited by 79

On the map: Diffusion models → Video generation

Abstract (arXiv)

Text-driven human motion generation in computer vision is both significant and challenging. However, current methods are limited to producing either deterministic or imprecise motion sequences, failing to effectively control the temporal and spatial relationships required to conform to a given text description. In this work, we propose a fine-grained method for generating high-quality, conditional human motion sequences supporting precise text description. Our approach consists of two key components: 1) a linguistics-structure assisted module that constructs accurate and complete language feature to fully utilize text information; and 2) a context-aware progressive reasoning module that learns neighborhood and overall semantic linguistics features from shallow and deep graph neural networks to achieve a multi-step inference. Experiments show that our approach outperforms text-driven motion generation methods on HumanML3D and KIT test sets and generates better visually confirmed motion to the text conditions.

Key facts. Cited by 79 papers in the map (data through 14 Oct 2026). Placed in Video generation, one of 14 directions in Diffusion models. Builds on 25 of its 34 references that are in the map. First posted on arXiv 12 Sep 2023.

Builds on

25 of 34 references.

Closest ancestors · 2

Same direction, newest first

  1. 2022Human Motion Diffusion Model29 Sep
  2. 2022MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model31 Aug

Other references · 23

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2020Denoising Diffusion Implicit Modelscited by 9,781
  5. 2017Graph Attention Networkscited by 8,923
  6. 2022Generative Adversarial Networkscited by 5,627
  7. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  8. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,236
  9. 2023T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representationscited by 588
  10. 2017MoCoGAN: Decomposing Motion and Content for Video Generationcited by 524
  11. 2021Action-Conditioned 3D Human Motion Synthesis with Transformer VAEcited by 501
  12. 2022TEMOS: Generating diverse human motions from textual descriptionscited by 492
11 more
  1. 2021AI Choreographer: Music Conditioned 3D Dance Generation with AIST++cited by 485
  2. 2020Action2Motion: Conditioned Generation of 3D Human Motionscited by 441
  3. 2022TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Textscited by 359
  4. 2016The KIT Motion-Language Datasetcited by 338
  5. 2019Language2Pose: Natural Language Grounded Pose Forecastingcited by 257
  6. 2021Synthesis of Compositional Animations from Textual Descriptionscited by 178
  7. 2017Text2Action: Generative Adversarial Synthesis from Language to Actioncited by 106
  8. 2021Text2Gestures: A Transformer-Based Network for Generating Emotive Body Gestures for Virtual Agentscited by 106
  9. 2017Learning a bidirectional mapping between human whole-body motion and natural language using deep recurrent neural networkscited by 61
  10. 2022Implicit Neural Representations for Variable Length Human Motion Generationcited by 61
  11. 2020Temporally Guided Music-to-Body-Movement Generationcited by 21

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 6; 2024: 29; 2025: 30; 2026: 14.

79 papers.

Sort:

By area:

  1. 2023CG-HOI: Contact-Guided 3D Human-Object Interaction Generationcited by 138
  2. 2023MMM: Generative Masked Motion Modelcited by 131
  3. 2025MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Spacecited by 86
  4. 2024Large Motion Model for Unified Multi-Modal Motion Generationcited by 65
  5. 2024LaMP: Language-Motion Pretraining for Motion Generation, Retrieval, and Captioningcited by 59
  6. 2024Taming Diffusion Probabilistic Models for Character Controlcited by 57
  7. 2024ParCo: Part-Coordinating Text-to-Motion Synthesiscited by 55
  8. 2024BAMM: Bidirectional Autoregressive Motion Modelcited by 55
  9. 2024StableMoFusion: Towards Robust and Efficient Diffusion-based Motion Generation Frameworkcited by 50
  10. 2024RoHM: Robust Human Motion Reconstruction via Diffusioncited by 48
  11. 2024Motion-Agent: A Conversational Framework for Human Motion Generation with LLMscited by 47
  12. 2024THOR: Text to Human-Object Interaction Diffusion via Relation Interventioncited by 46
38 more
  1. 2023Digital Life Project: Autonomous 3D Characters with Social Intelligencecited by 43
  2. 2025Motion Anything: Any to Motion Generationcited by 42
  3. 2024MoGenTS: Motion Generation based on Spatial-Temporal Joint Modelingcited by 41
  4. 2025SALAD: Skeleton-aware Latent Diffusion for Text-driven Motion Generation and Editingcited by 39
  5. 2025HOIGPT: Learning Long Sequence Hand-Object Interaction with Language Modelscited by 33
  6. 2024Light-T2M: A Lightweight and Fast Model for Text-to-motion Generationcited by 23
  7. 2023MotionScript: Natural Language Descriptions for Expressive 3D Human Motionscited by 21
  8. 2025Fg-T2M++: LLMs-Augmented Fine-Grained Text Driven Human Motion Generationcited by 21
  9. 2024SATO: Stable Text-to-Motion Frameworkcited by 20
  10. 2025ChainHOI: Joint-based Kinematic Chain Modeling for Human-Object Interaction Generationcited by 20
  11. 2024DisCoRD: Discrete Tokens to Continuous Motion via Rectified Flow Decodingcited by 19
  12. 2024CoMA: Compositional Human Motion Generation with Multi-modal Agentscited by 19
  13. 2023Realistic Human Motion Generation with Cross-Diffusion Modelscited by 17
  14. 2024Tri-Modal Motion Retrieval by Learning a Joint Embedding Spacecited by 16
  15. 2024Text-controlled Motion Mamba: Text-Instructed Temporal Grounding of Human Motioncited by 16
  16. 2024Language-Driven 6-DoF Grasp Detection Using Negative Prompt Guidancecited by 16
  17. 2024SoPo: Text-to-Motion Generation Using Semi-Online Preference Optimizationcited by 15
  18. 2025MVPortrait: Text-Guided Motion and Emotion Control for Multi-view Vivid Portrait Animationcited by 14
  19. 2025SocialGen: Modeling Multi-Human Social Interaction with Language Modelscited by 14
  20. 2023Bridging the Gap between Human Motion and Action Semantics via Kinematic Phrasescited by 13
  21. 2025Cafe-Talk: Generating 3D Talking Face Animation with Multimodal Coarse- and Fine-grained Controlcited by 12
  22. 2025FineMotion: A Dataset and Benchmark with both Spatial and Temporal Annotation for Fine-grained Motion Generation and Editingcited by 11
  23. 2024Local Action-Guided Motion Diffusion Model for Text-to-Motion Generationcited by 10
  24. 2024Length-Aware Motion Synthesis via Latent Diffusioncited by 10
  25. 2024MotionRL: Align Text-to-Motion Generation to Human Preferences with Multi-Reward Reinforcement Learningcited by 10
  26. 2024Text-guided 3D Human Motion Generation with Keyframe-based Parallel Skip Transformercited by 9
  27. 2024MoLA: Motion Generation and Editing with Latent Diffusion Enhanced by Adversarial Trainingcited by 9
  28. 2024LEAD: Latent Realignment for Human Motion Diffusioncited by 9
  29. 2024You Think, You ACT: The New Task of Arbitrary Text to Motion Generationcited by 8
  30. 2025Progressive Human Motion Generation Based on Text and Few Motion Framescited by 8
  31. 2025Text-driven Motion Generation: Overview, Challenges and Directionscited by 8
  32. 2025Motion Generation: A Survey of Generative Approaches and Benchmarkscited by 8
  33. 2024Learning Generalizable Human Motion Generator with Reinforcement Learningcited by 7
  34. 2025TaxaDiffusion: Progressively Trained Diffusion Model for Fine-Grained Species Generationcited by 7
  35. 2024BiPO: Bidirectional Partial Occlusion Network for Text-to-Motion Synthesiscited by 6
  36. 2025GenM3: Generative Pretrained Multi-path Motion Model for Text Conditional Human Motion Generationcited by 6
  37. 2025Separate to Collaborate: Dual-Stream Diffusion Model for Coordinated Piano Hand Motion Synthesiscited by 4
  38. 2025MDD: A Dataset for Text-and-Music Conditioned Duet Dance Generationcited by 4

50 most cited of 79 All 79 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023Act As You Wish: Fine-Grained Control of Motion Diffusion Model with Hierarchical Semantic Graphs
  2. 2024Text-driven Human Motion Generation with Motion Masked Diffusion Model
  3. 2023FG-MDM: Towards Zero-Shot Human Motion Generation via ChatGPT-Refined Descriptions
  4. 2023Priority-Centric Human Motion Generation in Discrete Latent Space
  5. 2024FTMoMamba: Motion Generation with Frequency and Text State Space Models
  6. 2023DiffusionPhase: Motion Diffusion in Frequency Domain
  7. 2024M2D2M: Multi-Motion Generation from Text with Discrete Diffusion Models
  8. 2022Diffusion Motion: Generate Text-Guided 3D Human Motion by Diffusion Model