# Dance Revolution: Long-Term Dance Generation with Music via Curriculum Learning

arXiv: https://arxiv.org/abs/2006.06119 · HTML: https://mlsanity.com/paper/2006.06119/

## Key facts

- Cited by 81 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jun 2020.

## Built on by (most cited first, 30 of 81)

- [MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model](https://mlsanity.com/paper/2208.15001/) (2022)
- [AI Choreographer: Music Conditioned 3D Dance Generation with AIST++](https://mlsanity.com/paper/2101.08779/) (2021)
- [Multimodal Learning with Transformers: A Survey](https://mlsanity.com/paper/2206.06488/) (2022)
- [MoMask: Generative Masked Modeling of 3D Human Motions](https://mlsanity.com/paper/2312.00063/) (2023)
- [TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts](https://mlsanity.com/paper/2207.01696/) (2022)
- [MoFusion: A Framework for Denoising-Diffusion-based Motion Synthesis](https://mlsanity.com/paper/2212.04495/) (2022)
- [Bailando: 3D Dance Generation by Actor-Critic GPT with Choreographic Memory](https://mlsanity.com/paper/2203.13055/) (2022)
- [GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Cameras](https://mlsanity.com/paper/2112.01524/) (2021)
- [Learning Hierarchical Cross-Modal Association for Co-Speech Gesture Generation](https://mlsanity.com/paper/2203.13161/) (2022)
- [Human Motion Generation: A Survey](https://mlsanity.com/paper/2307.10894/) (2023)
- [FineDance: A Fine-grained Choreography Dataset for 3D Full Body Dance Generation](https://mlsanity.com/paper/2212.03741/) (2022)
- [ActFormer: A GAN-based Transformer towards General Action-Conditioned 3D Human Motion Generation](https://mlsanity.com/paper/2203.07706/) (2022)
- [TM2D: Bimodality Driven 3D Dance Generation via Music-Text Integration](https://mlsanity.com/paper/2304.02419/) (2023)
- [UDE: A Unified Driving Engine for Human Motion Generation](https://mlsanity.com/paper/2211.16016/) (2022)
- [Large Motion Model for Unified Multi-Modal Motion Generation](https://mlsanity.com/paper/2404.01284/) (2024)
- [Lodge: A Coarse to Fine Diffusion Network for Long Dance Generation Guided by the Characteristic Dance Primitives](https://mlsanity.com/paper/2403.10518/) (2024)
- [Learning in Audio-visual Context: A Review, Analysis, and New Perspective](https://mlsanity.com/paper/2208.09579/) (2022)
- [Motion Anything: Any to Motion Generation](https://mlsanity.com/paper/2503.06955/) (2025)
- [M3GPT: An Advanced Multimodal, Multitask Framework for Motion Comprehension and Generation](https://mlsanity.com/paper/2405.16273/) (2024)
- [FLAG3D: A 3D Fitness Activity Dataset with Language Instruction](https://mlsanity.com/paper/2212.04638/) (2022)
- [DiffDance: Cascaded Human Motion Diffusion Model for Dance Generation](https://mlsanity.com/paper/2308.02915/) (2023)
- [Lodge++: High-quality and Long Dance Generation with Vivid Choreography Patterns](https://mlsanity.com/paper/2410.20389/) (2024)
- [DuetGen: Music Driven Two-Person Dance Generation via Hierarchical Masked Modeling](https://mlsanity.com/paper/2506.18680/) (2025)
- [Dance with You: The Diversity Controllable Dancer Generation via Diffusion Models](https://mlsanity.com/paper/2308.13551/) (2023)
- [Aligning Human Motion Generation with Human Perceptions](https://mlsanity.com/paper/2407.02272/) (2024)
- [Action2video: Generating Videos of Human 3D Actions](https://mlsanity.com/paper/2111.06925/) (2021)
- [Dance Any Beat: Blending Beats with Visuals in Dance Video Generation](https://mlsanity.com/paper/2405.09266/) (2024)
- [LongDanceDiff: Long-term Dance Generation with Conditional Diffusion Model](https://mlsanity.com/paper/2308.11945/) (2023)
- [A Unified Framework for Multimodal, Multi-Part Human Motion Synthesis](https://mlsanity.com/paper/2311.16471/) (2023)
- [A Survey of Deep Learning in Sports Applications: Perception, Comprehension, and Decision](https://mlsanity.com/paper/2307.03353/) (2023)

## Abstract (arXiv)

Dancing to music is one of human's innate abilities since ancient times. In machine learning research, however, synthesizing dance movements from music is a challenging problem. Recently, researchers synthesize human motion sequences through autoregressive models like recurrent neural network (RNN). Such an approach often generates short sequences due to an accumulation of prediction errors that are fed back into the neural network. This problem becomes even more severe in the long motion sequence generation. Besides, the consistency between dance and music in terms of style, rhythm and beat is yet to be taken into account during modeling. In this paper, we formalize the music-conditioned dance generation as a sequence-to-sequence learning problem and devise a novel seq2seq architecture to efficiently process long sequences of music features and capture the fine-grained correspondence between music and dance. Furthermore, we propose a novel curriculum learning strategy to alleviate error accumulation of autoregressive models in long motion sequence generation, which gently changes the training process from a fully guided teacher-forcing scheme using the previous ground-truth movements, towards a less guided autoregressive scheme mostly using the generated movements instead. Extensive experiments show that our approach significantly outperforms the existing state-of-the-arts on automatic metrics and human evaluation. We also make a demo video to demonstrate the superior performance of our proposed approach at https://www.youtube.com/watch?v=lmE20MEheZ8.