AI Paper Atlas

Research map / Video / Video-language understanding

Towards Authentic Movie Dubbing with Retrieve-Augmented Director-Actor Interaction Learning

Rui Liu, Yuan Zhao, Zhenqi Jia

AAAI 2026 · Video › Video-language understanding · approach: Long video understanding · 2 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 LLM-generated scene and face emotion captions instead of I3D/EmoFan embeddings (ablation)Authentic-Dubber · V2C-Animation testEMO-ACC: 46.02 -> 47.21Improved
add emotion-similarity retrieval augmentation (all modalities) (ablation)Authentic-Dubber · V2C-Animation testEMO-ACC: 45.23 -> 47.21Improved
add text retrieval (ablation)Authentic-Dubber · V2C-Animation testMOS-DE: 3.540 -> 3.792Improved
add direct emotion audio nodes in progressive graph (ablation)Authentic-Dubber · V2C-Animation testEMO-ACC: 45.30 -> 47.21Improved
add indirect multimodal information (ablation)Authentic-Dubber · V2C-Animation testMOS-DE: 3.542 -> 3.792Improved
add graph-based modeling (ablation)Authentic-Dubber · V2C-Animation testEMO-ACC: 45.92 -> 47.21Improved
add construct-and-encode paradigm (ablation)Authentic-Dubber · V2C-Animation testEMO-ACC: 46.85 -> 47.21Improved
add hierarchical aggregation (ablation)Authentic-Dubber · V2C-Animation testEMO-ACC: 46.71 -> 47.21Improved
use speaker-agnostic instead of speaker-specific retrieval (ablation)Authentic-Dubber · V2C-Animation testEMO-ACC: peak 47.21 at K=3Improved
increase retrieved Top-K beyond optimum (ablation)Authentic-Dubber · V2C-Animation testEMO-ACCHurt
increase retrieval footage scale from 10% to 100% (ablation)Authentic-Dubber · V2C-Animation testEMO-ACC: peak 47.21Improved
use cosine similarity instead of dot product or Euclidean distance for retrieval (ablation)Authentic-Dubber · V2C-Animation testEMO-ACCImproved

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