AI Paper Atlas

Research map / Video / Video generation

Semantic-Aware Motion Encoding for Topology-Agnostic Character Animation

Zongye Zhang, Yuzhuo Cui, Qingjie Liu, Yunhong Wang

ICML 2026 · Video › Video generation · approach: Text-to-motion diffusion · 0 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 spatial transformer (ablation)SATA autoencoder · AT-HumanML3D reconJR: 0.1243 -> 0.0568Improved
add GNN branch (ablation)SATA autoencoder · AT-HumanML3D reconJR: 0.0747 -> 0.0568Improved
add temporal transformer (ablation)SATA autoencoder · AT-HumanML3D reconRT: 1.3726 -> 0.9583Improved
add semantic fusion block (ablation)SATA autoencoder · AT-HumanML3D reconJR: 0.1196 -> 0.0568Improved
add text fusion (ablation)SATA autoencoder · AT-HumanML3D reconJR: 0.0663 -> 0.0568Improved
add sliding window inference (ablation)SATA VAE · AT-HumanML3D reconRT: 3.1599 -> 0.9583Improved
add sliding window inference (ablation)SATA RVQ · AT-HumanML3D reconRT: 13.3341 -> 3.5855Improved
add 16-frame overlap to sliding window (ablation)SATA VAE · AT-HumanML3D reconRT: 1.1643 -> 0.9583Improved
enlarge window from 16/4 to 64/16 (ablation)SATA VAE · AT-HumanML3D reconRT: 3.2405 -> 0.9583Improved
pre-train on AT-HumanML3D before fine-tuning (ablation)SATA · AT-AniMo4D recon (10% data)JR: 0.6201 -> 0.2825Improved
use VAE instead of RVQ bottleneck (ablation)SATA · AT-HumanML3D retargeting (internal)retargeting error: 1.1238 -> 0.2122Improved
use RVQ instead of VAE bottleneck for text-to-motion (ablation)SATA · AT-HumanML3D text-to-motionFID: 1.226 -> 0.158Improved

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