Research map / Video / Video generation
DanceTogether: Generating Interactive Multi-Person Video without Identity Drifting
Junhao Chen, Mingjin Chen, Jianjin Xu, Xiang Li, Junting Dong, Mingze Sun, Puhua Jiang, Hongxiang Li, Yuhang Yang, Hao Zhao, Xiao-Xiao Long, Ruqi Huang
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 MaskPoseAdapter instead of plain PoseNet (ablation) | DanceTog · DanceTogEval-100 | HOTA: 48.95 -> 83.94 | Improved |
| replace attention fusion with simple summation (ablation) | DanceTog · DanceTogEval-100 | HOTA: 83.94 -> 58.23 | Hurt |
| add separate mask input (ablation) | DanceTog · DanceTogEval-100 | IDF1: 42.49 -> 89.59 | Improved |
| add separate pose input (ablation) | DanceTog · DanceTogEval-100 | MPJPE2D: 1292.33 -> 492.24 | Improved |
| add MultiFaceEncoder (ablation) | DanceTog · DanceTogEval-100 | MPJPE2D: 893.32 -> 492.24 | Improved |
| add PairFS-4K training data (ablation) | DanceTog · DanceTogEval-100 | HOTA: 81.79 -> 83.94 | Improved |
| add all multi-person datasets beyond Swing Dance (ablation) | DanceTog · DanceTogEval-100 | HOTA: 80.26 -> 81.79 | Improved |
| use DanceTog architecture instead of StableAnimator, both on Swing Dance | DanceTog · DanceTogEval-100 | HOTA: 71.35 -> 80.26 | Improved |
| fine-tune StableAnimator on Swing Dance data | StableAnimator · DanceTogEval-100 | HOTA: 67.75 -> 71.35 | Improved |
| DanceTog vs StableAnimator w. Dataswing on mask-region FVD | DanceTog · DanceTogEval-100 (human masked region) | FVD (masked): 29.0 -> 17.1 | Improved |
| DanceTog vs StableAnimator inference speed | DanceTog · DanceTogEval-100 | FPS: 0.89 -> 0.88 | No clear effect |
Closest papers by meaning
- VLOGGER: Multimodal Diffusion for Embodied Avatar Synthesis (CVPR 2025 · similarity 0.88)
- Breaking the Group Size Barrier: Parameter-Efficient Group Dance Generation with Chain-of-Dancers (NeurIPS 2026 · similarity 0.88)
- TokenMotion: Decoupled Motion Control via Token Disentanglement for Human-centric Video Generation (CVPR 2025 · similarity 0.88)
- HumanDreamer: Generating Controllable Human-Motion Videos via Decoupled Generation (CVPR 2025 · similarity 0.87)
- Make Pixels Dance: High-Dynamic Video Generation (CVPR 2024 · similarity 0.87)
- MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance (ICML 2025 · 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.
