AI Paper Atlas

Research map / Video / Video generation

DIM: Dyadic Interaction Modeling for Social Behavior Generation

Minh Tran, Di Chang, Maksim Siniukov, Mohammad Soleymani

ECCV 2024 · Video › Video generation · approach: Talking face generation · 14 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 dyadic interaction pre-training with joint speaker-listener modeling (ablation)DIM-Listener · ViCoFD (Exp): 33.84 -> 24.15Improved
pre-train L2L on CANDOR as wellL2L · ViCoFD (Exp): 33.93 -> 31.03Improved
use VQ-VAE discrete codes instead of continuous prediction (ablation)DIM-Listener · ViCoFD (Exp): 42.52 -> 24.15Improved
unfreeze listener VQ decoder and integrate into motion prediction (ablation)DIM-Listener · ViCoFD (Exp): 39.63 -> 24.15Improved
add contrastive loss between speaker and listener features (ablation)DIM-Listener · ViCoFD (Exp): 28.47 -> 24.15Improved
add two-branch speaker-listener joint modeling (S-L) (ablation)DIM-Listener without contrastive loss · ViCoFD (Exp): 30.92 -> 28.47Improved
add contrastive loss between speaker and listener features (ablation)DIM-Listener · LM_ListenerFD (Exp): 17.92 -> 12.94Improved
use both audio and visual speaker inputs instead of single modality (ablation)DIM-Listener · ViCoFD (Exp): 32.8 -> 23.9Improved
use causal masks for online generation (ablation)DIM-Listener · ViCoFD (Exp): 23.9 -> 28.4Hurt
apply DIM pre-trained model to speaker motion generation (DIM-Speaker)DIM-Speaker · BiWiLVE (x10^-4): 5.40 -> 3.86Improved

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