mlsanityData to 14 Oct 2026

MultiAct: Long-Term 3D Human Motion Generation from Multiple Action Labels

arXiv 2212.05897 ↗First posted 12 Dec 2022cs.CVcited by 45

Not on the map. Why?

Abstract (arXiv)

We tackle the problem of generating long-term 3D human motion from multiple action labels. Two main previous approaches, such as action- and motion-conditioned methods, have limitations to solve this problem. The action-conditioned methods generate a sequence of motion from a single action. Hence, it cannot generate long-term motions composed of multiple actions and transitions between actions. Meanwhile, the motion-conditioned methods generate future motions from initial motion. The generated future motions only depend on the past, so they are not controllable by the user's desired actions. We present MultiAct, the first framework to generate long-term 3D human motion from multiple action labels. MultiAct takes account of both action and motion conditions with a unified recurrent generation system. It repetitively takes the previous motion and action label; then, it generates a smooth transition and the motion of the given action. As a result, MultiAct produces realistic long-term motion controlled by the given sequence of multiple action labels. Codes are available here at https://github.com/TaeryungLee/MultiAct_RELEASE.

Key facts. Cited by 45 papers in the map (data through 14 Oct 2026). Builds on 26 of its 39 references that are in the map. First posted on arXiv 12 Dec 2022.

Builds on

26 of 39 references.

References · 26

  1. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,214
  2. 2021Action-Conditioned 3D Human Motion Synthesis with Transformer VAEcited by 501
  3. 2022TEMOS: Generating diverse human motions from textual descriptionscited by 492
  4. 2020Action2Motion: Conditioned Generation of 3D Human Motionscited by 441
  5. 2022TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Textscited by 359
  6. 2021HuMoR: 3D Human Motion Model for Robust Pose Estimationcited by 324
  7. 2021BABEL: Bodies, Action and Behavior with English Labelscited by 265
  8. 2021Robust Motion In-betweeningcited by 229
  9. 2020Long-term Human Motion Prediction with Scene Contextcited by 192
  10. 2020DLow: Diversifying Latent Flows for Diverse Human Motion Predictioncited by 185
  11. 2017HP-GAN: Probabilistic 3D human motion prediction via GANcited by 176
  12. 2020Synthesizing Long-Term 3D Human Motion and Interaction in 3D Scenescited by 135
14 more
  1. 2020We are More than Our Joints: Predicting how 3D Bodies Movecited by 115
  2. 2017Text2Action: Generative Adversarial Synthesis from Language to Actioncited by 106
  3. 2019Structured Prediction Helps 3D Human Motion Modellingcited by 96
  4. 2021Scene-aware Generative Network for Human Motion Synthesiscited by 70
  5. 2018Pose Guided Human Video Generationcited by 67
  6. 2021Generating Smooth Pose Sequences for Diverse Human Motion Predictioncited by 66
  7. 2021Single-Shot Motion Completion with Transformercited by 59
  8. 2017Deep Video Generation, Prediction and Completion of Human Action Sequencescited by 52
  9. 2020Perpetual Motion: Generating Unbounded Human Motioncited by 36
  10. 2021Task-Generic Hierarchical Human Motion Prior using VAEscited by 33
  11. 2020Generative Tweening: Long-term Inbetweening of 3D Human Motionscited by 23
  12. 2020Dynamic Future Net: Diversified Human Motion Generationcited by 14
  13. 2021MUGL: Large Scale Multi Person Conditional Action Generation with Locomotioncited by 14
  14. 2021An Experimental Validation and Comparison of Reaching Motion Models for Unconstrained Handovers: Towards Generating Humanlike Motions for Human-Robot Handoverscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 10; 2024: 21; 2025: 11; 2026: 3.

45 papers.

Sort:

By area:

  1. 2023TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesiscited by 198
  2. 2024MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Modelcited by 168
  3. 2023HumanTOMATO: Text-aligned Whole-body Motion Generationcited by 104
  4. 2023Human Motion Generation: A Surveycited by 96
  5. 2024MotionLLM: Understanding Human Behaviors from Human Motions and Videoscited by 90
  6. 2023EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generationcited by 89
  7. 2024Text2HOI: Text-guided 3D Motion Generation for Hand-Object Interactioncited by 86
  8. 2024Seamless Human Motion Composition with Blended Positional Encodingscited by 80
  9. 2023SINC: Spatial Composition of 3D Human Motions for Simultaneous Action Generationcited by 64
  10. 2024InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object Interactioncited by 64
  11. 2024MotionFix: Text-Driven 3D Human Motion Editingcited by 64
  12. 2024Motion-Agent: A Conversational Framework for Human Motion Generation with LLMscited by 47
33 more
  1. 2024HIMO: A New Benchmark for Full-Body Human Interacting with Multiple Objectscited by 36
  2. 2024M2D2M: Multi-Motion Generation from Text with Discrete Diffusion Modelscited by 24
  3. 2023Synthesizing Long-Term Human Motions with Diffusion Models via Coherent Samplingcited by 19
  4. 2024KMM: Key Frame Mask Mamba for Extended Motion Generationcited by 16
  5. 2024Diffgrasp: Whole-Body Grasping Synthesis Guided by Object Motion Using a Diffusion Modelcited by 13
  6. 2024T2LM: Long-Term 3D Human Motion Generation from Multiple Sentencescited by 12
  7. 2024InfiniDreamer: Arbitrarily Long Human Motion Generation via Segment Score Distillationcited by 12
  8. 2025Text-driven Motion Generation: Overview, Challenges and Directionscited by 8
  9. 2025Motion Generation: A Survey of Generative Approaches and Benchmarkscited by 8
  10. 2024FORCE: Physics-aware Human-object Interactioncited by 7
  11. 2024Autonomous LLM-Enhanced Adversarial Attack for Text-to-Motioncited by 7
  12. 2024Efficient Text-driven Motion Generation via Latent Consistency Trainingcited by 6
  13. 2023AMD:Anatomical Motion Diffusion with Interpretable Motion Decomposition and Fusioncited by 5
  14. 2023Orientation-Aware Leg Movement Learning for Action-Driven Human Motion Predictioncited by 4
  15. 2024Infinite Motion: Extended Motion Generation via Long Text Instructionscited by 4
  16. 2024ContactGen: Contact-Guided Interactive 3D Human Generation for Partnerscited by 3
  17. 2024Shape Conditioned Human Motion Generation with Diffusion Modelcited by 3
  18. 2024COLLAGE: Collaborative Human-Agent Interaction Generation using Hierarchical Latent Diffusion and Language Modelscited by 3
  19. 2025Versatile Multimodal Controls for Expressive Talking Human Animationcited by 3
  20. 2025Streaming Generation of Co-Speech Gestures via Accelerated Rolling Diffusioncited by 2
  21. 2025Multi-Modal Motion Retrieval by Learning a Fine-Grained Joint Embedding Spacecited by 2
  22. 2025MoReact: Generating Reactive Motion from Textual Descriptionscited by 2
  23. 2023MDSC: Towards Evaluating the Style Consistency Between Music and Dancecited by 1
  24. 2025Human Motion Prediction, Reconstruction, and Generationcited by 1
  25. 2025Multimodal Generative AI with Autoregressive LLMs for Human Motion Understanding and Generation: A Way Forwardcited by 1
  26. 2025SIGNER: Temporally Grounded Sign Language Generation via Time-Resolved Conditioningcited by 1
  27. 2025A Plug-and-Play Multi-Criteria Guidance for Diverse In-Betweening Human Motion Generationcited by 1
  28. 2026Sketch2Colab: Sketch-Conditioned Multi-Human Animation via Controllable Flow Distillationcited by 1
  29. 2026LaMoGen: Language to Motion Generation Through LLM-Guided Symbolic Inferencecited by 1
  30. 2023Personalized Pose Forecastingcited by 0
  31. 2024TextIM: Part-aware Interactive Motion Synthesis from Textcited by 0
  32. 2025A Survey of Body and Face Motion: Datasets, Performance Evaluation Metrics and Generative Techniquescited by 0
  33. 2026Text Dictates, Music Decorates: Energy-based Attention for Editable Dance Motion Generationcited by 0