AI Paper Atlas

Research map / Video / Video generation

TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts

Chuan Guo, Xinxin Zuo, Sen Wang, Li Cheng

ECCV 2022 · Video › Video generation · approach: Text-to-motion diffusion · 263 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 motion tokens (ablation)motion2text model · HumanML3D test (motion-to-text)Cider: 68.3 -> 72.5Improved
add motion tokens (ablation)motion2text model · KIT-ML test (motion-to-text)Cider: 60.1 -> 79.5Improved
add motion tokens (ablation)motion2text model · KIT-ML test (motion-to-text)R-precision top-1: 0.284 -> 0.359Improved
add motion tokens (ablation)motion2text model · HumanML3D test (motion-to-text)R-precision top-1: 0.483 -> 0.516Improved
add inverse alignment (GRU model) (ablation)text2motion · HumanML3D test (text-to-motion)R-precision top-1: 0.351 -> 0.424Improved
add inverse alignment (GRU model) (ablation)text2motion · HumanML3D test (text-to-motion)R-precision top-3: 0.635 -> 0.729Improved
add inverse alignment (GRU model) (ablation)text2motion · HumanML3D test (text-to-motion)FID: 1.739 -> 1.501Improved
add inverse alignment (GRU model) (ablation)text2motion · KIT-ML test (text-to-motion)FID: 4.814 -> 3.599Improved
add inverse alignment (GRU model) (ablation)text2motion · KIT-ML test (text-to-motion)R-precision top-1: 0.251 -> 0.280Improved
add inverse alignment (GRU model) (ablation)text2motion · HumanML3D test (text-to-motion)MModality: 3.139 -> 2.424Hurt
add inverse alignment (GRU model) (ablation)text2motion · KIT-ML test (text-to-motion)MModality: 4.486 -> 3.292Hurt
use Transformer instead of GRU in text2motion without inverse alignmenttext2motion baseline · HumanML3D test (text-to-motion)FID: 1.739 -> 1.669Mixed

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