Research map / 3D vision / Human pose estimation
EgoMusic-driven Human Dance Motion Estimation with Skeleton Mamba
Quang Nguyen, Nhat Le, Baoru Huang, Minh Nhat Vu, Chengcheng Tang, Van Nguyen, Ngan Le, Thieu Vo, Anh Nguyen
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 head guidance sampling (ablation) | EMM · EgoAIST++ | O_head: 0.76 -> 0.53 | Improved |
| add head guidance sampling (ablation) | EMM · EgoAIST++ | MPJPE: 146.38 -> 137.54 | Improved |
| add ego-music alignment loss (ablation) | EMM · EgoAIST++ | MMV: 0.242 -> 0.262 | Improved |
| add ego-music alignment loss (ablation) | EMM · EgoAIST++ | MPJPE: 142.47 -> 137.54 | Improved |
| add egocentric video to music-only input (ablation) | EMM · EgoAIST++ | MPJPE: 157.36 -> 137.54 | Improved |
| add music to egocentric-only input (ablation) | EMM · EgoAIST++ | MPJPE: 186.49 -> 137.54 | Improved |
| use temporal and spatial scans instead of spatial bidirectional only (ablation) | Skeleton Mamba · EgoAIST++ | MPJPE: 160.12 -> 137.54 | Improved |
| add bidirectional spatial scan over unidirectional (ablation) | Skeleton Mamba · EgoAIST++ | MPJPE: 192.38 -> 160.12 | Improved |
| use temporal and spatial scans instead of temporal unidirectional only (ablation) | Skeleton Mamba · EgoAIST++ | MPJPE: 181.43 -> 137.54 | Improved |
| use EMM instead of EDGE | EMM · EgoAIST++ | MPJPE: 167.43 -> 137.54 | Improved |
| use EMM instead of EgoEgo on unseen real data | EMM · EgoExo4D (cross-dataset) | MPJPE: 234.58 -> 191.55 | Improved |
| use Skeleton Mamba instead of MMamba | Skeleton Mamba · HumanML3D | R-Precision: 0.790 -> 0.795 | 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.
- Bailando — Bailando: 3D Dance Generation by Actor-Critic GPT With Choreographic Memory (CVPR 2022) · better on 3 of 3 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
- Bidirectional Autoregessive Diffusion Model for Dance Generation (CVPR 2024 · similarity 0.88)
- DanceAnyWay: Synthesizing Beat-Guided 3D Dances with Randomized Temporal Contrastive Learning (AAAI 2024 · similarity 0.87)
- DanceCamera3D: 3D Camera Movement Synthesis with Music and Dance (CVPR 2024 · similarity 0.86)
- DisCo: Disentangled Control for Realistic Human Dance Generation (CVPR 2024 · similarity 0.86)
- DanceFix: An Exploration in Group Dance Neatness Assessment Through Fixing Abnormal Challenges of Human Pose (AAAI 2025 · similarity 0.86)
- Estimating Ego-Body Pose from Doubly Sparse Egocentric Video Data (NeurIPS 2024 · similarity 0.86)
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.
