AI Paper Atlas

Research map / Video / Video generation

Large Motion Model for Unified Multi-Modal Motion Generation

Mingyuan Zhang, Daisheng Jin, Chenyang Gu, Fangzhou Hong, Zhongang Cai, Jingfang Huang, Chongzhi Zhang, Xinying Guo, Lei Yang, Ying He, Ziwei Liu

ECCV 2024 · Video › Video generation · approach: Text-to-motion diffusion · 49 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
add random masking in pretraining (ablation)LMM-Base · HumanML3DFID: 31.365 -> 0.138Improved
add random downsampling (frame-rate augmentation) on top of random masking (ablation)LMM-Base · HumanML3DMultiModality: 2.214 -> 2.426Improved
add random downsampling on top of random masking (ablation)LMM-Base · AMASS-BMLrub 1000 msMPJPE (mm): 76.1 -> 73.6Improved
use ArtAttention instead of SAMI (ablation)LMM-Base · HumanML3DFID: 1.866 -> 0.138Improved
scale model from LMM-Tiny to LMM-Large (ablation)LMM · HumanML3DFID: 0.415 -> 0.040Improved
unified generalist LMM-Tiny versus specialist FineMoGen with similar structureLMM-Tiny · HumanML3DFID: 0.151 -> 0.415Hurt
generalist LMM-Large on short-horizon motion predictionLMM-Large · AMASS-BMLrub 80 msMPJPE (mm): 10.2 (GCNext) vs 12.8Hurt
generalist LMM-Large on long-horizon motion predictionLMM-Large · 3DPW 1000 msMPJPE (mm): 72.0 -> 68.0Improved
generalist LMM-Large on music-to-dance quality (FIDk)LMM-Large · AIST++FIDk: 19.01 (TM2D) vs 22.08Hurt

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