mlsanityData to 7 Oct 2026

TEACH: Temporal Action Composition for 3D Humans

arXiv 2209.04066 ↗First posted 9 Sep 2022cs.CVcited by 173

Not on the map. Why?

Cited by 38 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Given a series of natural language descriptions, our task is to generate 3D human motions that correspond semantically to the text, and follow the temporal order of the instructions. In particular, our goal is to enable the synthesis of a series of actions, which we refer to as temporal action composition. The current state of the art in text-conditioned motion synthesis only takes a single action or a single sentence as input. This is partially due to lack of suitable training data containing action sequences, but also due to the computational complexity of their non-autoregressive model formulation, which does not scale well to long sequences. In this work, we address both issues. First, we exploit the recent BABEL motion-text collection, which has a wide range of labeled actions, many of which occur in a sequence with transitions between them. Next, we design a Transformer-based approach that operates non-autoregressively within an action, but autoregressively within the sequence of actions. This hierarchical formulation proves effective in our experiments when compared with multiple baselines. Our approach, called TEACH for "TEmporal Action Compositions for Human motions", produces realistic human motions for a wide variety of actions and temporal compositions from language descriptions. To encourage work on this new task, we make our code available for research purposes at our hrefteach.is.tue.mpg.dewebsite.

Key facts. Cited by 173 papers in the map (data through 7 Oct 2026). Builds on 33 of its 56 references that are in the map. First posted on arXiv 9 Sep 2022.

Builds on

33 of 56 references.

References · 33

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  3. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  4. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
  5. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,208
  6. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,186
  7. 2021Action-Conditioned 3D Human Motion Synthesis with Transformer VAEcited by 497
  8. 2022TEMOS: Generating diverse human motions from textual descriptionscited by 486
  9. 2021AI Choreographer: Music Conditioned 3D Dance Generation with AIST++cited by 479
  10. 2020Action2Motion: Conditioned Generation of 3D Human Motionscited by 438
  11. 2022MotionCLIP: Exposing Human Motion Generation to CLIP Spacecited by 406
  12. 2017On human motion prediction using recurrent neural networkscited by 336
21 more
  1. 2016The KIT Motion-Language Datasetcited by 334
  2. 2021BABEL: Bodies, Action and Behavior with English Labelscited by 261
  3. 2019Language2Pose: Natural Language Grounded Pose Forecastingcited by 257
  4. 2021Robust Motion In-betweeningcited by 223
  5. 2021Stochastic Scene-Aware Motion Predictioncited by 203
  6. 2020DLow: Diversifying Latent Flows for Diverse Human Motion Predictioncited by 184
  7. 2021Character Controllers Using Motion VAEscited by 182
  8. 2021Synthesis of Compositional Animations from Textual Descriptionscited by 177
  9. 2017HP-GAN: Probabilistic 3D human motion prediction via GANcited by 176
  10. 2020We are More than Our Joints: Predicting how 3D Bodies Movecited by 115
  11. 2018Human Motion Prediction via Spatio-Temporal Inpaintingcited by 114
  12. 2017Text2Action: Generative Adversarial Synthesis from Language to Actioncited by 106
  13. 2018A Neural Temporal Model for Human Motion Predictioncited by 87
  14. 2020Convolutional Autoencoders for Human Motion Infillingcited by 73
  15. 2021Single-Shot Motion Completion with Transformercited by 59
  16. 2018Recurrent Transition Networks for Character Locomotioncited by 52
  17. 2019Modeling Human Motion with Quaternion-based Neural Networkscited by 45
  18. 2022Weakly-supervised Action Transition Learning for Stochastic Human Motion Predictioncited by 26
  19. 2022Conditional Motion In-betweeningcited by 25
  20. 2020Generative Tweening: Long-term Inbetweening of 3D Human Motionscited by 23
  21. 2021Transflower: probabilistic autoregressive dance generation with multimodal attentioncited by 22

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 36; 2024: 65; 2025: 38; 2026: 30.

173 papers.

Sort:

By area:

  1. 2023T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representationscited by 577
  2. 2023MoMask: Generative Masked Modeling of 3D Human Motionscited by 388
  3. 2023Human Motion Diffusion as a Generative Priorcited by 354
  4. 2023ReMoDiffuse: Retrieval-Augmented Motion Diffusion Modelcited by 282
  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. 2024MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Modelcited by 164
  8. 2023AttT2M: Text-Driven Human Motion Generation with Multi-Perspective Attention Mechanismcited by 116
  9. 2023FineMoGen: Fine-Grained Spatio-Temporal Motion Generation and Editingcited by 105
  10. 2024CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character controlcited by 103
  11. 2023DreamHuman: Animatable 3D Avatars from Textcited by 102
  12. 2023Human Motion Generation: A Surveycited by 95
38 more
  1. 2023TLControl: Trajectory and Language Control for Human Motion Synthesiscited by 93
  2. 2024Multi-Track Timeline Control for Text-Driven 3D Human Motion Generationcited by 88
  3. 2025MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Spacecited by 82
  4. 2024DartControl: A Diffusion-Based Autoregressive Motion Model for Real-Time Text-Driven Motion Controlcited by 80
  5. 2024Move as You Say, Interact as You Can: Language-guided Human Motion Generation with Scene Affordancecited by 79
  6. 2024Seamless Human Motion Composition with Blended Positional Encodingscited by 77
  7. 2023TM2D: Bimodality Driven 3D Dance Generation via Music-Text Integrationcited by 76
  8. 2025Go to Zero: Towards Zero-shot Motion Generation with Million-scale Datacited by 67
  9. 2024CoMo: Controllable Motion Generation through Language Guided Pose Code Editingcited by 66
  10. 2024Large Motion Model for Unified Multi-Modal Motion Generationcited by 65
  11. 2024InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object Interactioncited by 63
  12. 2024MotionFix: Text-Driven 3D Human Motion Editingcited by 63
  13. 2023SINC: Spatial Composition of 3D Human Motions for Simultaneous Action Generationcited by 62
  14. 2023ReMoS: 3D Motion-Conditioned Reaction Synthesis for Two-Person Interactionscited by 62
  15. 2024DiffH2O: Diffusion-Based Synthesis of Hand-Object Interactions from Textual Descriptionscited by 60
  16. 2023FaceTalk: Audio-Driven Motion Diffusion for Neural Parametric Head Modelscited by 55
  17. 2024ScaMo: Exploring the Scaling Law in Autoregressive Motion Generation Modelcited by 52
  18. 2024Generating Human Motion in 3D Scenes from Text Descriptionscited by 49
  19. 2024THOR: Text to Human-Object Interaction Diffusion via Relation Interventioncited by 46
  20. 2024Duolando: Follower GPT with Off-Policy Reinforcement Learning for Dance Accompanimentcited by 46
  21. 2022Being Comes from Not-being: Open-vocabulary Text-to-Motion Generation with Wordless Trainingcited by 45
  22. 2025GENMO: A GENeralist Model for Human MOtioncited by 43
  23. 2023LivelySpeaker: Towards Semantic-Aware Co-Speech Gesture Generationcited by 40
  24. 2024MoGenTS: Motion Generation based on Spatial-Temporal Joint Modelingcited by 40
  25. 2023Emotional Speech-driven 3D Body Animation via Disentangled Latent Diffusioncited by 39
  26. 2025SALAD: Skeleton-aware Latent Diffusion for Text-driven Motion Generation and Editingcited by 37
  27. 2024HIMO: A New Benchmark for Full-Body Human Interacting with Multiple Objectscited by 34
  28. 2023Going Beyond Nouns With Vision & Language Models Using Synthetic Datacited by 33
  29. 2024MotionChain: Conversational Motion Controllers via Multimodal Promptscited by 30
  30. 2024EnergyMoGen: Compositional Human Motion Generation with Energy-Based Diffusion Model in Latent Spacecited by 30
  31. 2025MotionLab: Unified Human Motion Generation and Editing via the Motion-Condition-Motion Paradigmcited by 30
  32. 2024in2IN: Leveraging individual Information to Generate Human INteractionscited by 29
  33. 2024Unimotion: Unifying 3D Human Motion Synthesis and Understandingcited by 29
  34. 2022Action-GPT: Leveraging Large-scale Language Models for Improved and Generalized Action Generationcited by 28
  35. 2023Motion Question Answering via Modular Motion Programscited by 27
  36. 2023Interactive Humanoid: Online Full-Body Motion Reaction Synthesis with Social Affordance Canonicalization and Forecastingcited by 27
  37. 2023Plan, Posture and Go: Towards Open-World Text-to-Motion Generationcited by 26
  38. 2024ReinDiffuse: Crafting Physically Plausible Motions with Reinforced Diffusion Modelcited by 25

50 most cited of 173 All 173 (JSON)