Research map / Video / Video generation
Align Your Rhythm: Generating Highly Aligned Dance Poses with Gating-Enhanced Rhythm-Aware Feature Representation
Congyi Fan, Jian Guan, Xuanjia Zhao, Dongli Xu, Youtian Lin, Tong Ye, Pengming Feng, Haiwei Pan
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| add Phase-based Rhythm Extraction (PRE) (ablation) | Danceba · AIST++ ablation | FID: 20.62 -> 14.53 | Improved |
| add PRE (ablation) | Danceba · AIST++ ablation | BAS: 0.2474 -> 0.2779 | Improved |
| add PRE (ablation) | Danceba · AIST++ ablation | Div: 6.53 -> 7.67 | Improved |
| add Temporal-Gated Causal Attention (TGCA) (ablation) | Danceba · AIST++ ablation | FID: 33.22 -> 14.53 | Improved |
| add TGCA (ablation) | Danceba · AIST++ ablation | Div: 6.74 -> 7.67 | Improved |
| add Parallel Mamba Motion Modeling (PMMM) (ablation) | Danceba · AIST++ ablation | FID: 25.24 -> 14.53 | Improved |
| add PMMM (ablation) | Danceba · AIST++ ablation | Div: 5.78 -> 7.67 | Improved |
| use parallel upper/lower Mamba instead of single Mamba (ablation) | Danceba · AIST++ | FID_k: 82.50 -> 15.48 | Improved |
| use parallel upper/lower Mamba instead of single Mamba (ablation) | Danceba · AIST++ | FID_g: 83.97 -> 13.57 | Improved |
| Danceba vs Bailando++ on kinetic FID | Bailando++ · AIST++ | FID_k: 22.74 -> 11.67 | Improved |
| Danceba vs Bailando++ on geometric FID | Bailando++ · AIST++ | FID_g: 11.58 -> 11.90 | Hurt |
| Danceba vs best baseline on beat alignment | Lodge · AIST++ | BAS: 0.2423 -> 0.2714 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Lodge — Lodge++: High-Quality and Long Dance Generation With Robust Choreography Patterns (TPAMI 2025) · better on 5 of 5 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- DanceAnyWay: Synthesizing Beat-Guided 3D Dances with Randomized Temporal Contrastive Learning (AAAI 2024 · similarity 0.90)
- Music-Aligned Holistic 3D Dance Generation via Hierarchical Motion Modeling (ICCV 2025 · similarity 0.90)
- MNET++: Music-Driven Pluralistic Dancing Toward Multiple Dance Genre Synthesis (TPAMI 2023 · similarity 0.90)
- BRACE: The Breakdancing Competition Dataset for Dance Motion Synthesis (ECCV 2022 · similarity 0.90)
- MEGADance: Mixture-of-Experts Architecture for Genre-Aware 3D Dance Generation (NeurIPS 2025 · similarity 0.88)
- Bidirectional Autoregessive Diffusion Model for Dance Generation (CVPR 2024 · similarity 0.88)
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.
