AI Paper Atlas

Research map / Video / Video generation

GestureLSM: Latent Shortcut based Co-Speech Gesture Generation with Spatial-Temporal Modeling

Pinxin Liu, Luchuan Song, Junhua Huang, Haiyang Liu, Chenliang Xu

ICCV 2025 · Video › Video generation · approach: Text-to-motion diffusion · 36 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 attention across body regions to temporal attention (ablation)GestureLSM · BEAT2FGD: 8.232 -> 4.088Improved
add temporal attention to spatial attention (ablation)GestureLSM · BEAT2FGD: 22.412 -> 4.088Improved
add spatial and temporal positional encodings (ablation)GestureLSM · BEAT2FGD: 4.523 -> 4.088Improved
use beta(2,1.2) timestep sampling instead of uniform (ablation)GestureLSM · BEAT2FGD: 5.051 -> 4.088Improved
use beta sampling instead of Logit-Normal, Mode or CosMap (ablation)GestureLSM · BEAT2FGD: 4.447 -> 4.088Improved
use latent shortcut instead of standard rectified flow (ablation)GestureLSM · BEAT2FGD: 4.724 -> 4.088Improved
use latent shortcut flow matching instead of DDPM diffusion (ablation)GestureLSM · BEAT2AIST (s): 2.942 -> 0.039Improved
add flattened spatial-temporal attention layer on top of separate attentions (ablation)GestureLSM · BEAT2FGD: 4.088 -> 4.132No clear effect
replace spatial-temporal attention with Bi-Mamba (ablation)GestureLSM · BEAT2FGD: 4.088 -> 4.323Hurt
increase sampling steps from 8 to 20 (ablation)GestureLSM · BEAT2FGD: 4.088 -> 4.040No clear effect
reduce sampling steps from 8 to 2 (ablation)GestureLSM · BEAT2FGD: 4.088 -> 4.988Hurt
use cross-attention fusion instead of concatenation or addition (ablation)GestureLSM · BEAT2FGD: 6.012 -> 4.088Improved

Later papers that compared with this method

5 later accepted papers report GestureLSM as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.

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