Research map / Image generation / Autoregressive and latent generation
A Brand New Dance Partner: Music-Conditioned Pluralistic Dancing Controlled by Multiple Dance Genres
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use a single Transformer conditional GAN with mapping-network style codes for multiple dance genres | Music-conditioned dance generation on AIST++ · AIST++ | FIDk: 33.08 -> 29.52 | Helped |
| use a single Transformer conditional GAN with mapping-network style codes for multiple dance genres | Music-conditioned dance generation on AIST++ · AIST++ | Distm,k: 5.83 -> 6.93 | Helped |
| use a single Transformer conditional GAN with mapping-network style codes for multiple dance genres | Music-conditioned dance generation on AIST++ · AIST++ | BeatAlign: 0.241 -> 0.246 | Helped |
| use a single Transformer conditional GAN with mapping-network style codes for multiple dance genres | Music-conditioned dance generation on AIST++ · AIST++ | MNET WinRate: 62.39 % -> - | Helped |
| replace transformer layer normalization with style-modulated layer normalization (ablation) | MNET generator · AIST++ | FIDk: 29.52 -> 59.84 | Hurt |
| embed style code by concatenating it with input conditions in a transformer encoder generator (ablation) | MNET generator · AIST++ | FIDk: 29.52 -> 35.27 | Hurt |
| replace the transformer discriminator with a GRU-based motion discriminator (ablation) | MNET · AIST++ | FIDk: 29.52 -> 29.40 | No clear effect |
| add pose-parameter appearance loss (ablation) | MNET with adversarial loss · AIST++ | FIDk: 59.58 -> 33.84 | Helped |
| add vertex-coordinate loss to pose-parameter appearance loss (ablation) | MNET with pose loss · AIST++ | FIDk: 33.84 -> 31.71 | Helped |
| add style diversity loss (ablation) | MNET with pose and vertex losses · AIST++ | Distm,k: 4.39 -> 6.71 | Helped |
| add style diversity loss (ablation) | MNET with pose and vertex losses · AIST++ | BeatAlign: 0.215 -> 0.207 | Hurt |
| add style-focusing loss (ablation) | MNET with diversity loss · AIST++ | BeatAlign: 0.207 -> 0.246 | Helped |
Closest papers by meaning
- MEGADance: Mixture-of-Experts Architecture for Genre-Aware 3D Dance Generation (NeurIPS 2025 · similarity 0.90)
- DanceAnyWay: Synthesizing Beat-Guided 3D Dances with Randomized Temporal Contrastive Learning (AAAI 2024 · similarity 0.89)
- Bidirectional Autoregessive Diffusion Model for Dance Generation (CVPR 2024 · similarity 0.89)
- Breaking the Group Size Barrier: Parameter-Efficient Group Dance Generation with Chain-of-Dancers (NeurIPS 2026 · similarity 0.88)
- Lodge: A Coarse to Fine Diffusion Network for Long Dance Generation Guided by the Characteristic Dance Primitives (CVPR 2024 · similarity 0.87)
- DanceMVP: Self-Supervised Learning for Multi-Task Primitive-Based Dance Performance Assessment via Transformer Text Prompting (AAAI 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.