mlsanityData to 7 Oct 2026

TEMOS: Generating diverse human motions from textual descriptions

arXiv 2204.14109 ↗First posted 25 Apr 2022cs.CV cs.CLcited by 486

Not on the map. Why?

Cited by 113 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We address the problem of generating diverse 3D human motions from textual descriptions. This challenging task requires joint modeling of both modalities: understanding and extracting useful human-centric information from the text, and then generating plausible and realistic sequences of human poses. In contrast to most previous work which focuses on generating a single, deterministic, motion from a textual description, we design a variational approach that can produce multiple diverse human motions. We propose TEMOS, a text-conditioned generative model leveraging variational autoencoder (VAE) training with human motion data, in combination with a text encoder that produces distribution parameters compatible with the VAE latent space. We show the TEMOS framework can produce both skeleton-based animations as in prior work, as well more expressive SMPL body motions. We evaluate our approach on the KIT Motion-Language benchmark and, despite being relatively straightforward, demonstrate significant improvements over the state of the art. Code and models are available on our webpage.

Key facts. Cited by 486 papers in the map (data through 7 Oct 2026). Builds on 42 of its 66 references that are in the map. First posted on arXiv 25 Apr 2022.

Builds on

42 of 66 references.

References · 42

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  5. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  6. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  7. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
  8. 2013Auto-Encoding Variational Bayescited by 3,980
  9. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
  10. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,208
  11. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,186
  12. 2021Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrievalcited by 1,175
30 more
  1. 2021Florence: A New Foundation Model for Computer Visioncited by 802
  2. 2021Action-Conditioned 3D Human Motion Synthesis with Transformer VAEcited by 497
  3. 2021AI Choreographer: Music Conditioned 3D Dance Generation with AIST++cited by 479
  4. 2020Action2Motion: Conditioned Generation of 3D Human Motionscited by 438
  5. 2017On human motion prediction using recurrent neural networkscited by 336
  6. 2016The KIT Motion-Language Datasetcited by 334
  7. 2019Capture, Learning, and Synthesis of 3D Speaking Stylescited by 257
  8. 2019Language2Pose: Natural Language Grounded Pose Forecastingcited by 257
  9. 2021Robust Motion In-betweeningcited by 223
  10. 2021FaceFormer: Speech-Driven 3D Facial Animation with Transformerscited by 208
  11. 2022Unified Contrastive Learning in Image-Text-Label Spacecited by 194
  12. 2019Learning Individual Styles of Conversational Gesturecited by 190
  13. 2021MeshTalk: 3D Face Animation from Speech using Cross-Modality Disentanglementcited by 189
  14. 2020DLow: Diversifying Latent Flows for Diverse Human Motion Predictioncited by 184
  15. 2022Embodied Hands: Modeling and Capturing Hands and Bodies Togethercited by 179
  16. 2021Synthesis of Compositional Animations from Textual Descriptionscited by 177
  17. 2017HP-GAN: Probabilistic 3D human motion prediction via GANcited by 176
  18. 2020We are More than Our Joints: Predicting how 3D Bodies Movecited by 115
  19. 2018QuaterNet: A Quaternion-based Recurrent Model for Human Motioncited by 108
  20. 2017Text2Action: Generative Adversarial Synthesis from Language to Actioncited by 106
  21. 2019Structured Prediction Helps 3D Human Motion Modellingcited by 96
  22. 2020Weakly Supervised 3D Human Pose and Shape Reconstruction with Normalizing Flowscited by 94
  23. 2020Learning to Generate Diverse Dance Motions with Transformercited by 85
  24. 2017Learning a bidirectional mapping between human whole-body motion and natural language using deep recurrent neural networkscited by 61
  25. 2021Single-Shot Motion Completion with Transformercited by 59
  26. 2021Speech2AffectiveGestures: Synthesizing Co-Speech Gestures with Generative Adversarial Affective Expression Learningcited by 58
  27. 2021Mixed SIGNals: Sign Language Production via a Mixture of Motion Primitivescited by 50
  28. 2019MoGlow: Probabilistic and controllable motion synthesis using normalising flowscited by 47
  29. 2018Human Motion Modeling using DVGANscited by 45
  30. 2020Perpetual Motion: Generating Unbounded Human Motioncited by 36

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 26; 2023: 97; 2024: 141; 2025: 129; 2026: 93.

486 papers.

Sort:

By area:

  1. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,231
  2. 2022Human Motion Diffusion Modelcited by 1,062
  3. 2022MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Modelcited by 768
  4. 2023T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representationscited by 577
  5. 2022Executing your Commands via Motion Diffusion in Latent Spacecited by 567
  6. 2023MotionGPT: Human Motion as a Foreign Languagecited by 521
  7. 2023MoMask: Generative Masked Modeling of 3D Human Motionscited by 388
  8. 2022PhysDiff: Physics-Guided Human Motion Diffusion Modelcited by 365
  9. 2023Human Motion Diffusion as a Generative Priorcited by 354
  10. 2022EDGE: Editable Dance Generation From Musiccited by 284
  11. 2023ReMoDiffuse: Retrieval-Augmented Motion Diffusion Modelcited by 282
  12. 2023OmniControl: Control Any Joint at Any Time for Human Motion Generationcited by 233
38 more
  1. 2023Guided Motion Diffusion for Controllable Human Motion Synthesiscited by 221
  2. 2023Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Datasetcited by 220
  3. 2022MoFusion: A Framework for Denoising-Diffusion-based Motion Synthesiscited by 218
  4. 2022FLAME: Free-form Language-based Motion Synthesis & Editingcited by 217
  5. 2023InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactionscited by 205
  6. 2023TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesiscited by 194
  7. 2022Listen, Denoise, Action! Audio-Driven Motion Synthesis with Diffusion Modelscited by 188
  8. 2023InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusioncited by 181
  9. 2022TEACH: Temporal Action Composition for 3D Humanscited by 173
  10. 2024MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Modelcited by 164
  11. 2023MotionGPT: Finetuned LLMs Are General-Purpose Motion Generatorscited by 145
  12. 2023CG-HOI: Contact-Guided 3D Human-Object Interaction Generationcited by 137
  13. 2023MMM: Generative Masked Motion Modelcited by 129
  14. 2022IMos: Intent-Driven Full-Body Motion Synthesis for Human-Object Interactionscited by 121
  15. 2023AttT2M: Text-Driven Human Motion Generation with Multi-Perspective Attention Mechanismcited by 116
  16. 2024Motion Mamba: Efficient and Long Sequence Motion Generationcited by 111
  17. 2023Synthesizing Diverse Human Motions in 3D Indoor Scenescited by 109
  18. 2024Nymeria: A Massive Collection of Multimodal Egocentric Daily Motion in the Wildcited by 109
  19. 2023Controllable Human-Object Interaction Synthesiscited by 107
  20. 2023FineMoGen: Fine-Grained Spatio-Temporal Motion Generation and Editingcited by 105
  21. 2023HumanTOMATO: Text-aligned Whole-body Motion Generationcited by 103
  22. 2024CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character controlcited by 103
  23. 2023DreamHuman: Animatable 3D Avatars from Textcited by 102
  24. 2023Inter-X: Towards Versatile Human-Human Interaction Analysiscited by 98
  25. 2023Optimizing Diffusion Noise Can Serve As Universal Motion Priorscited by 97
  26. 2023Human Motion Generation: A Surveycited by 95
  27. 2023TLControl: Trajectory and Language Control for Human Motion Synthesiscited by 93
  28. 2024MotionLLM: Understanding Human Behaviors from Human Motions and Videoscited by 89
  29. 2023EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generationcited by 88
  30. 2024Multi-Track Timeline Control for Text-Driven 3D Human Motion Generationcited by 88
  31. 2024Text2HOI: Text-guided 3D Motion Generation for Hand-Object Interactioncited by 84
  32. 2022ZeroEGGS: Zero-shot Example-based Gesture Generation from Speechcited by 83
  33. 2025MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Spacecited by 82
  34. 2023HumanMAC: Masked Motion Completion for Human Motion Predictioncited by 81
  35. 2024DartControl: A Diffusion-Based Autoregressive Motion Model for Real-Time Text-Driven Motion Controlcited by 80
  36. 2023Fg-T2M: Fine-Grained Text-Driven Human Motion Generation via Diffusion Modelcited by 79
  37. 2024Move as You Say, Interact as You Can: Language-guided Human Motion Generation with Scene Affordancecited by 79
  38. 2024OAKINK2: A Dataset of Bimanual Hands-Object Manipulation in Complex Task Completioncited by 78

50 most cited of 486 All 486 (JSON)