AI Paper Atlas

Research map / Video / Video generation

Music-to-Dance Generation via Atomic Movements

Xinhao Cai, Yixuan Sun, Minghang Zheng, Qingchao Chen, Xin Jin, Song-Chun Zhu, Yang Liu

ECCV 2026 · Video › Video generation · approach: Text-to-motion diffusion · 1 citations (OpenAlex)

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 changedWhereMeasuredEffect
LLM-assisted in-group re-clustering instead of naive clustering (ablation)atomic movement discovery · AIST++FID_k: 32.68 -> 25.26Improved
LLM-assisted re-clustering instead of re-clustering without LLM (ablation)atomic movement discovery · AIST++R-precision: 23.3 -> 26.6Improved
use 125 base clusters instead of 100 (ablation)atomic movement discovery · AIST++FID_k: 32.68 -> 34.57Hurt
use 75 base clusters instead of 100 (ablation)atomic movement discovery · AIST++FID_k: 32.68 -> 33.24Hurt
add post-processing to atomic planning (ablation)two-stage planner · AIST++FID_k: 25.26 -> 24.02Improved
use ground-truth atomic labels instead of planned labels (ablation)two-stage framework · AIST++FID_k: 24.02 -> 21.59Improved
flexible re-creation of atomic movements instead of fixed concatenation (ablation)dance completion · AIST++MultiModality: 1.43 -> 2.25Improved
flexible re-creation of atomic movements instead of fixed (ablation)dance completion · AIST++FID_k: 24.13 -> 25.26Hurt
duration-nearest retrieval instead of random choice (ablation)dance completion · AIST++FID_k: 27.94 -> 25.26Improved
duration-nearest retrieval instead of single candidate (ablation)dance completion · AIST++Div_k: 6.42 -> 8.01Improved
two-stage atomic planning framework instead of Lodgemusic-to-dance · AIST++R-precision: 18.2 -> 26.6Improved
two-stage framework instead of Bailandomusic-to-dance · AIST++FID_k: 28.16 -> 25.26Improved

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy