AI Paper Atlas

Research map / Video / Video generation

Role-Aware Interaction Generation from Textual Description

Mikihiro Tanaka, Kent Fujiwara

ICCV 2023 · Video › Video generation · approach: Text-to-motion diffusion · 50 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 cross attention between the two human motion transformers (ablation)two-Transformer baseline · NTU-RGB+D 120 interactionsMutual Consistency: 46.3 -> 98.3Improved
add cross attention between the two human motion transformers (ablation)two-Transformer baseline · NTU-RGB+D 120 interactionsFID: 21.1 -> 13.1Improved
initialize with pretrained single-person motion model (ablation)Ours · NTU-RGB+D 120 interactionsAccuracy: 76.1 -> 79.9Improved
initialize with pretrained single-person motion model (ablation)Ours · NTU-RGB+D 120 interactionsFID: 13.1 -> 12.8No clear effect
use role-aware two-transformer model instead of single transformer (ablation)interaction generation · NTU-RGB+D 120 interactionsFID: 12.3 -> 13.1No clear effect
use pseudo-label role assignment from PIT model rather than label-based PIT generation (ablation)role-aware model · NTU-RGB+D 120 interactionsAccuracy: 70.5 -> 76.1Improved
use per-motion transformers with cross attention instead of compressing both motions into one latent (MUGL, DSAG)interaction generation · NTU-RGB+D 120 interactionsMutual Consistency: 88.6 -> 98.3 (vs DSAG)Improved
use noise step around t=800 for actor/receiver separation instead of early steps (ablation)PIT role separation · NTU-RGB+D 120 asymmetric interactionsseparation accuracyImproved
use ensemble majority vote during role identification (ablation)PIT role separation · NTU-RGB+D 120 asymmetric interactionsseparation accuracyImproved
use Mutual Consistency in addition to FID and accuracyevaluation · NTU-RGB+D 120 interactionsmetric sensitivity: Baseline (Two Trans.) accuracy 73.2 but Mutual Consistency 46.3Improved

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