AI Paper Atlas

Research map / Video / Video generation

Interactive Conversational Head Generation

Mohan Zhou, Yalong Bai, Wei Zhang, Ting Yao, Tiejun Zhao

TPAMI 2025 · Video › Video generation · approach: Talking face generation · 19 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
use responsive listener conditioned on speaker audio and face instead of random motionRandom listener · ViCo responsive listeningExpFD: 16.435 -> 15.149Improved
use responsive listener instead of random motionRandom listener · ViCo-X responsive listeningExpFD: 13.739 -> 10.656Improved
use responsive listener instead of mirroring the speakerMirror listener · ViCo-X responsive listeningExpFD: 17.635 -> 10.656Improved
use responsive listener instead of mirroring the speakerMirror listener · ViCo responsive listeningAngleFD: 10.155 -> 7.963Improved
add listener visual signals to audio-driven speaker (ablation)Audio-only speaker · ViCo expressive talking headAVOffset: 0.376 -> 0.094Improved
add listener visual signals to audio-driven speaker (ablation)Audio-only speaker · ViCo-X expressive talking headAVOffset: 0.636 -> 0.083Improved
add listener visual signals to audio-driven speaker (ablation)Audio-only speaker · ViCo expressive talking headExpFD: 17.486 -> 16.604Improved
add listener visual signals to audio-driven speaker (ablation)Audio-only speaker · ViCo expressive talking headLMD: 13.505 -> 14.366Hurt
add listener visual signals to audio-driven speaker (ablation)Audio-only speaker · ViCo-X expressive talking headAVConf: 2.524 -> 2.755Improved
add listener visual signals to audio-driven speaker (ablation)Audio-only speaker · ViCo expressive talking headFID: 45.581 -> 46.181No clear effect
use role-switching conversational agent instead of separate best listener plus speakerListener + Speaker baseline · ViCo-X conversational head generationExpFD: 13.954 -> 13.293Improved
use role-switching conversational agent instead of separate listener plus speakerListener + Speaker baseline · ViCo-X conversational head generationAVOffset: 0.193 -> 0.362Hurt

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