AI Paper Atlas

Research map / Video / Video generation

CrowdMoGen: Event-Driven Collective Human Motion Generation

Yukang Cao, Xinying Guo, Mingyuan Zhang, Haozhe Xie, Chenyang Gu, Ziwei Liu

IJCV 2026 · Video › Video generation · approach: Text-to-motion diffusion · 8 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 ControlAttention (ablation)CrowdMoGen · HumanML3D ablationFID: 0.150 -> 0.127Improved
add InputMixing (ablation)CrowdMoGen · HumanML3D ablationFID: 0.207 -> 0.127Improved
add controlled keypoint loss L_con (ablation)CrowdMoGen · HumanML3D ablationFID: 0.219 -> 0.127Improved
add foot skating loss L_foot (ablation)CrowdMoGen · HumanML3D ablationFoot skating ratio: 0.1947 -> 0.0762Improved
add foot skating loss L_foot (ablation)CrowdMoGen · HumanML3D ablationAvg. error (m): 0.0147 -> 0.0196Hurt
add IK guidance at inference (ablation)CrowdMoGen · HumanML3D ablationAvg. error (m): 0.2387 -> 0.0196Improved
add IK guidance at inference (ablation)CrowdMoGen · HumanML3D ablationFID: 0.130 -> 0.127No clear effect
replace ControlNet-only control with InputMixing + ControlAttention (ablation)CrowdMoGen · HumanML3D ablationFID: 0.225 -> 0.127Improved
replace InterControl with CrowdMoGentext-to-motion · HumanML3D controllable (Pelvis)FID: 0.159 -> 0.132Improved
replace InterControl with CrowdMoGentext-to-motion · KIT-ML text-to-motionFID: 0.580 -> 0.217Improved
use CrowdMoGen vs OmniControl on foot skatingcontrollable generation · HumanML3D controllable (Pelvis)Foot skating ratio: 0.0547 -> 0.0762Hurt
use full CrowdMoGen vs w/o ControlAttention in user studyCrowdMoGen · User study (25 volunteers)Motion quality preference: 13.04% -> 77.91%Improved

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