AI Paper Atlas

Research map / Video / Video generation

Priority-Centric Human Motion Generation in Discrete Latent Space

Hanyang Kong, Kehong Gong, Dongze Lian, Michael Bi Mi, Xinchao Wang

ICCV 2023 · Video › Video generation · approach: Text-to-motion diffusion · 57 citations (OpenAlex)

Read the paper

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
replace linear noise schedule with dynamic-assessment priority-centric schedule (ablation)M2DM · HumanML3D testFID: 0.417 -> 0.352Improved
replace linear noise schedule with static-assessment priority-centric schedule (ablation)M2DM · HumanML3D testFID: 0.417 -> 0.395Improved
replace linear noise schedule with priority-centric schedule (ablation)M2DM · KIT-ML testFID: 0.502 -> 0.515No clear effect
add l2 normalization and orthogonal regularization to the VQ-VAE codebook (ablation)Transformer VQ-VAE · HumanML3D test (reconstruction)FID: 0.079 -> 0.063Improved
add orthogonal regularization on codebook entriesTransformer VQ-VAE · HumanML3D testcodebook usageImproved
use priority-centric discrete diffusion for long text descriptions (>30 words)text-to-motion · HumanML3D test, text >30 wordsFID: 0.947 -> 0.356Improved
longer textual descriptionsMLD · HumanML3D testR-Precision Top-1: 0.492 -> 0.289Hurt
use Transformer-based VQ-VAE with discrete diffusion instead of competing methodsM2DM · HumanML3D testFID: 0.141 (T2M-GPT) vs 0.352Mixed

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