mlsanityData to 7 Oct 2026

Music-Driven Group Choreography

arXiv 2303.12337 ↗First posted 22 Mar 2023cs.MM cs.CV cs.SDcited by 36

Not on the map. Why?

Abstract (arXiv)

Music-driven choreography is a challenging problem with a wide variety of industrial applications. Recently, many methods have been proposed to synthesize dance motions from music for a single dancer. However, generating dance motion for a group remains an open problem. In this paper, we present rm AIOZ-GDANCE, a new large-scale dataset for music-driven group dance generation. Unlike existing datasets that only support single dance, our new dataset contains group dance videos, hence supporting the study of group choreography. We propose a semi-autonomous labeling method with humans in the loop to obtain the 3D ground truth for our dataset. The proposed dataset consists of 16.7 hours of paired music and 3D motion from in-the-wild videos, covering 7 dance styles and 16 music genres. We show that naively applying single dance generation technique to creating group dance motion may lead to unsatisfactory results, such as inconsistent movements and collisions between dancers. Based on our new dataset, we propose a new method that takes an input music sequence and a set of 3D positions of dancers to efficiently produce multiple group-coherent choreographies. We propose new evaluation metrics for measuring group dance quality and perform intensive experiments to demonstrate the effectiveness of our method. Our project facilitates future research on group dance generation and is available at: https://aioz-ai.github.io/AIOZ-GDANCE/

Key facts. Cited by 36 papers in the map (data through 7 Oct 2026). Builds on 32 of its 69 references that are in the map. First posted on arXiv 22 Mar 2023.

Builds on

32 of 69 references.

References · 32

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2016Layer Normalizationcited by 5,579
  4. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
  5. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  6. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,161
  7. 2015Scheduled Sampling for Sequence Prediction with Recurrent Neural Networkscited by 779
  8. 2021AI Choreographer: Music Conditioned 3D Dance Generation with AIST++cited by 479
  9. 2016RMPE: Regional Multi-person Pose Estimationcited by 340
  10. 2019Learning Trajectory Dependencies for Human Motion Predictioncited by 245
  11. 2021DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motioncited by 213
  12. 2022Bailando: 3D Dance Generation by Actor-Critic GPT with Choreographic Memorycited by 210
20 more
  1. 2016Single-Image Depth Perception in the Wildcited by 179
  2. 2020Coherent Reconstruction of Multiple Humans from a Single Imagecited by 136
  3. 2018Convolutional Sequence to Sequence Model for Human Dynamicscited by 115
  4. 2021Multi-Person 3D Motion Prediction with Multi-Range Transformerscited by 63
  5. 2020Socially and Contextually Aware Human Motion and Pose Forecastingcited by 51
  6. 2021Learning Dynamics via Graph Neural Networks for Human Pose Estimation and Trackingcited by 37
  7. 2020Learning to dance: A graph convolutional adversarial network to generate realistic dance motions from audiocited by 33
  8. 2020ChoreoNet: Towards Music to Dance Synthesis with Choreographic Action Unitcited by 31
  9. 2022Uncertainty-aware Label Distribution Learning for Facial Expression Recognitioncited by 30
  10. 2018Weakly Supervised Deep Recurrent Neural Networks for Basic Dance Step Generationcited by 22
  11. 2021Global-Local Attention for Emotion Recognitioncited by 20
  12. 2022Dance Style Transfer with Cross-modal Transformercited by 20
  13. 2021GAN-based Reactive Motion Synthesis with Class-aware Discriminators for Human-human Interactioncited by 18
  14. 2019Generative Autoregressive Networks for 3D Dancing Move Synthesis from Musiccited by 14
  15. 2021Graph-based Person Signature for Person Re-Identificationscited by 14
  16. 2021When Creators Meet the Metaverse: A Survey on Computational Artscited by 12
  17. 2021Human Interaction Recognition Framework based on Interacting Body Part Attentioncited by 11
  18. 2019An Extensive Review of Computational Dance Automation Techniques and Applicationscited by 8
  19. 2021Dance Generation with Style Embedding: Learning and Transferring Latent Representations of Dance Stylescited by 5
  20. 2023Style Transfer for 2D Talking Head Animationcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 5; 2024: 9; 2025: 14; 2026: 8.

36 papers.

Sort:

By area:

  1. 2023Human Motion Generation: A Surveycited by 95
  2. 2025Go to Zero: Towards Zero-shot Motion Generation with Million-scale Datacited by 67
  3. 2024FreeMotion: A Unified Framework for Number-free Text-to-Motion Synthesiscited by 42
  4. 2024in2IN: Leveraging individual Information to Generate Human INteractionscited by 29
  5. 2024Towards Open Domain Text-Driven Synthesis of Multi-Person Motionscited by 27
  6. 2025Ready-to-React: Online Reaction Policy for Two-Character Interaction Generationcited by 25
  7. 2025ChainHOI: Joint-based Kinematic Chain Modeling for Human-Object Interaction Generationcited by 19
  8. 2023Dance with You: The Diversity Controllable Dancer Generation via Diffusion Modelscited by 17
  9. 2025X-Dancer: Expressive Music to Human Dance Video Generationcited by 15
  10. 2025SocialGen: Modeling Multi-Human Social Interaction with Language Modelscited by 14
  11. 2023Language-driven Scene Synthesis using Multi-conditional Diffusion Modelcited by 10
  12. 2024Synergy and Synchrony in Couple Dancescited by 8
24 more
  1. 2024DanceCamera3D: 3D Camera Movement Synthesis with Music and Dancecited by 7
  2. 2025MoSa: Motion Generation with Scalable Autoregressive Modelingcited by 5
  3. 2025UniAct: Unified Motion Generation and Action Streaming for Humanoid Robotscited by 5
  4. 2024Scalable Group Choreography via Variational Phase Manifold Learningcited by 4
  5. 2024FG-CXR: A Radiologist-Aligned Gaze Dataset for Enhancing Interpretability in Chest X-Ray Report Generationcited by 4
  6. 2025TCDiff++: An End-to-end Trajectory-Controllable Diffusion Model for Harmonious Music-Driven Group Choreographycited by 4
  7. 2025MDD: A Dataset for Text-and-Music Conditioned Duet Dance Generationcited by 4
  8. 2026TeamHOI: Learning a Unified Policy for Cooperative Human-Object Interactions with Any Team Sizecited by 4
  9. 2023The MI-Motion Dataset and Benchmark for 3D Multi-Person Motion Predictioncited by 3
  10. 2024LM2D: Lyrics- and Music-Driven Dance Synthesiscited by 3
  11. 2026TokenDance: Token-to-Token Music-to-Dance Generation with Bidirectional Mambacited by 3
  12. 2025Multi-Modal Motion Retrieval by Learning a Fine-Grained Joint Embedding Spacecited by 2
  13. 2025EgoMusic-driven Human Dance Motion Estimation with Skeleton Mambacited by 2
  14. 2025OmniMotion-X: Versatile Multimodal Whole-Body Motion Generationcited by 2
  15. 2026Language-Guided Transformer Tokenizer for Human Motion Generationcited by 2
  16. 2023MDSC: Towards Evaluating the Style Consistency Between Music and Dancecited by 1
  17. 2024Motion Generation Review: Exploring Deep Learning for Lifelike Animation with Manifoldcited by 1
  18. 2025ST-GDance: Long-Term and Collision-Free Group Choreography from Musiccited by 1
  19. 2026Wan-Dancer: A Hierarchical Framework for Minute-scale Coherent Music-to-Dance Generationcited by 1
  20. 2025A Survey of Body and Face Motion: Datasets, Performance Evaluation Metrics and Generative Techniquescited by 0
  21. 2026ST-GDance++: A Scalable Spatial-Temporal Diffusion for Long-Duration Group Choreographycited by 0
  22. 2026Learning Quantised Structure-Preserving Motion Representations for Dance Fingerprintingcited by 0
  23. 2026SalsaAgent: A multimodal embodied language model for interactive dance generationcited by 0
  24. 2026WeLike2Party! In-Context Motion Transfer for Multi-Human Image Animationcited by 0