AI Paper Atlas

Research map / Video / Video generation

TriC-Motion: Tri-Domain Causal Modeling Grounded Text-to-Motion Generation

Yiyang Cao, Yunze Deng, Ziyu Lin, Bin Feng, Xinggang Wang, Wenyu Liu, DanDan Zheng, Jingdong Chen

ICLR 2026 · Video › Video generation · approach: Compositional text-to-video diffusion

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 STM (spatial) to temporal encoder (ablation)TME · HumanML3D testR-Precision Top-1: 0.470 -> 0.570Improved
add HFA (frequency) to temporal encoder (ablation)TME · HumanML3D testFID: 2.110 -> 0.374Improved
add S-Fus score-guided fusion instead of concatenation (ablation)TME + STM + HFA · HumanML3D testR-Precision Top-1: 0.592 -> 0.607Improved
add FFT branch to low-frequency band (ablation)HFA · HumanML3D testFID: 0.405 -> 0.347Improved
add high-frequency branch (ablation)HFA · HumanML3D testFID: 0.504 -> 0.347Improved
add joint-wise frequency branch (ablation)HFA · HumanML3D testFID: 0.418 -> 0.347Improved
add CCMD causal intervention (ablation)TriC-Motion · HumanML3D testFID: 0.561 -> 0.347Improved
apply CCMD to all three domains instead of temporal only (ablation)TriC-Motion · HumanML3D testR-Precision Top-1: 0.580 -> 0.607Improved
apply CCMD after S-Fus (post) instead of before (ablation)TriC-Motion · HumanML3D testFID: 0.328 post vs 0.347 pre; R@1 0.604 vs 0.607Mixed
use increasing layer weights {0.1,0.2,0.3,0.4} for L_fcf instead of uniform (ablation)TriC-Motion · HumanML3D testFID: 0.478 -> 0.347Improved
replace MDM baseline with TriC-Motion (base)MDM · HumanML3D testR-Precision Top-1: 0.320 -> 0.607Improved
compare TriC-Motion with MoMask++ on SnapMoGenMoMask++ · SnapMoGen testFID: 15.060 -> 26.346Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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