mlsanityData to 7 Oct 2026

ActFormer: A GAN-based Transformer towards General Action-Conditioned 3D Human Motion Generation

arXiv 2203.07706 ↗First posted 15 Mar 2022cs.CV cs.GR cs.MMcited by 77

Not on the map. Why?

Abstract (arXiv)

We present a GAN-based Transformer for general action-conditioned 3D human motion generation, including not only single-person actions but also multi-person interactive actions. Our approach consists of a powerful Action-conditioned motion TransFormer (ActFormer) under a GAN training scheme, equipped with a Gaussian Process latent prior. Such a design combines the strong spatio-temporal representation capacity of Transformer, superiority in generative modeling of GAN, and inherent temporal correlations from the latent prior. Furthermore, ActFormer can be naturally extended to multi-person motions by alternately modeling temporal correlations and human interactions with Transformer encoders. To further facilitate research on multi-person motion generation, we introduce a new synthetic dataset of complex multi-person combat behaviors. Extensive experiments on NTU-13, NTU RGB+D 120, BABEL and the proposed combat dataset show that our method can adapt to various human motion representations and achieve superior performance over the state-of-the-art methods on both single-person and multi-person motion generation tasks, demonstrating a promising step towards a general human motion generator.

Key facts. Cited by 77 papers in the map (data through 7 Oct 2026). Builds on 34 of its 67 references that are in the map. First posted on arXiv 15 Mar 2022.

Builds on

34 of 67 references.

References · 34

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2014Conditional Generative Adversarial Netscited by 2,152
  4. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,208
  5. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,199
  6. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,186
  7. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 806
  8. 2018Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networkscited by 687
  9. 2017Wasserstein GANcited by 635
  10. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 615
  11. 2019NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understandingcited by 530
  12. 2021Action-Conditioned 3D Human Motion Synthesis with Transformer VAEcited by 497
22 more
  1. 2020Action2Motion: Conditioned Generation of 3D Human Motionscited by 438
  2. 2017On human motion prediction using recurrent neural networkscited by 336
  3. 2021BABEL: Bodies, Action and Behavior with English Labelscited by 261
  4. 2019Language2Pose: Natural Language Grounded Pose Forecastingcited by 257
  5. 2018cGANs with Projection Discriminatorcited by 253
  6. 2015Structural-RNN: Deep Learning on Spatio-Temporal Graphscited by 234
  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. 2017Modulating early visual processing by languagecited by 167
  11. 2021ViTGAN: Training GANs with Vision Transformerscited by 110
  12. 2017Text2Action: Generative Adversarial Synthesis from Language to Actioncited by 106
  13. 2019Structured Prediction Helps 3D Human Motion Modellingcited by 96
  14. 2018MT-VAE: Learning Motion Transformations to Generate Multimodal Human Dynamicscited by 86
  15. 2020Learning to Generate Diverse Dance Motions with Transformercited by 85
  16. 2018Learning to Detect and Track Visible and Occluded Body Joints in a Virtual Worldcited by 81
  17. 2020Dance Revolution: Long-Term Dance Generation with Music via Curriculum Learningcited by 81
  18. 2021TRiPOD: Human Trajectory and Pose Dynamics Forecasting in the Wildcited by 52
  19. 2020Socially and Contextually Aware Human Motion and Pose Forecastingcited by 51
  20. 2020UniCon: Universal Neural Controller For Physics-based Character Motioncited by 39
  21. 2020Perpetual Motion: Generating Unbounded Human Motioncited by 36
  22. 2021Combining Transformer Generators with Convolutional Discriminatorscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 11; 2024: 18; 2025: 35; 2026: 12.

77 papers.

Sort:

By area:

  1. 2023InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactionscited by 205
  2. 2024MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Modelcited by 164
  3. 2023Inter-X: Towards Versatile Human-Human Interaction Analysiscited by 98
  4. 2023EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generationcited by 88
  5. 2024Multi-Track Timeline Control for Text-Driven 3D Human Motion Generationcited by 88
  6. 2025InterMimic: Towards Universal Whole-Body Control for Physics-Based Human-Object Interactionscited by 67
  7. 2025Go to Zero: Towards Zero-shot Motion Generation with Million-scale Datacited by 67
  8. 2024ReGenNet: Towards Human Action-Reaction Synthesiscited by 53
  9. 2023OMG: Towards Open-vocabulary Motion Generation via Mixture of Controllerscited by 47
  10. 2024THOR: Text to Human-Object Interaction Diffusion via Relation Interventioncited by 46
  11. 2024Motion-Agent: A Conversational Framework for Human Motion Generation with LLMscited by 46
  12. 2025GENMO: A GENeralist Model for Human MOtioncited by 43
38 more
  1. 2022Interaction Transformer for Human Reaction Generationcited by 42
  2. 2024CORE4D: A 4D Human-Object-Human Interaction Dataset for Collaborative Object REarrangementcited by 40
  3. 2024HIMO: A New Benchmark for Full-Body Human Interacting with Multiple Objectscited by 34
  4. 2023Interactive Humanoid: Online Full-Body Motion Reaction Synthesis with Social Affordance Canonicalization and Forecastingcited by 27
  5. 2024WANDR: Intention-guided Human Motion Generationcited by 26
  6. 2025A Survey on Human Interaction Motion Generationcited by 25
  7. 2023Revisit Human-Scene Interaction via Space Occupancycited by 24
  8. 2025ViPRA: Video Prediction for Robot Actionscited by 24
  9. 2023MotionScript: Natural Language Descriptions for Expressive 3D Human Motionscited by 21
  10. 2024Programmable Motion Generation for Open-Set Motion Control Taskscited by 20
  11. 2025Towards Immersive Human-X Interaction: A Real-Time Framework for Physically Plausible Motion Synthesiscited by 20
  12. 2024PhysReaction: Physically Plausible Real-Time Humanoid Reaction Synthesis via Forward Dynamics Guided 4D Imitationcited by 18
  13. 2024Closely Interactive Human Reconstruction with Proxemics and Physics-Guided Adaptioncited by 18
  14. 2025Ego4o: Egocentric Human Motion Capture and Understanding from Multi-Modal Inputcited by 17
  15. 2025Dance Like a Chicken: Low-Rank Stylization for Human Motion Diffusioncited by 16
  16. 2025HERO: Human Reaction Generation from Videoscited by 15
  17. 2024MotionBank: A Large-scale Video Motion Benchmark with Disentangled Rule-based Annotationscited by 14
  18. 2023Bridging the Gap between Human Motion and Action Semantics via Kinematic Phrasescited by 13
  19. 2025Auto-Regressive Diffusion for Generating 3D Human-Object Interactionscited by 12
  20. 2025MOSPA: Human Motion Generation Driven by Spatial Audiocited by 11
  21. 2023Transformer-based Generative Adversarial Networks in Computer Vision: A Comprehensive Surveycited by 10
  22. 2025Motion Synthesis with Sparse and Flexible Keyjoint Controlcited by 9
  23. 2025PINO: Person-Interaction Noise Optimization for Long-Duration and Customizable Motion Generation of Arbitrary-Sized Groupscited by 8
  24. 2024Generation of Complex 3D Human Motion by Temporal and Spatial Composition of Diffusion Modelscited by 7
  25. 2025Think-Then-React: Towards Unconstrained Human Action-to-Reaction Generationcited by 7
  26. 2025ARFlow: Human Action-Reaction Flow Matching with Physical Guidancecited by 7
  27. 2025Perceiving and Acting in First-Person: A Dataset and Benchmark for Egocentric Human-Object-Human Interactionscited by 7
  28. 2025EgoReAct: Egocentric Video-Driven 3D Human Reaction Generationcited by 7
  29. 2024Multi-Condition Latent Diffusion Network for Scene-Aware Neural Human Motion Predictioncited by 6
  30. 2024Diffusion Implicit Policy for Unpaired Scene-aware Motion Synthesiscited by 6
  31. 20253D Human Interaction Generation: A Surveycited by 6
  32. 2025Unified Multi-Modal Interactive & Reactive 3D Motion Generation via Rectified Flowcited by 6
  33. 2024LS-GAN: Human Motion Synthesis with Latent-space GANscited by 5
  34. 2024Efficient Text-driven Motion Generation via Latent Consistency Trainingcited by 4
  35. 2025Advances in 4D Representation: Geometry, Motion, and Interactioncited by 4
  36. 2024Shape Conditioned Human Motion Generation with Diffusion Modelcited by 3
  37. 2025Versatile Multimodal Controls for Expressive Talking Human Animationcited by 3
  38. 2025Large-Scale Multi-Character Interaction Synthesiscited by 3

50 most cited of 77 All 77 (JSON)