Movie Audio Description (AD) aims to narrate visual content during dialogue-free segments, particularly benefiting blind and visually impaired (BVI) audiences. Compared with general video captioning, AD demands plot-relevant narration with explicit character name references, posing unique challenges in movie understanding.To identify active main characters and focus on storyline-relevant regions, we propose FocusedAD, a novel framework that delivers character-centric movie audio descriptions. It includes: (i) a Character Perception Module(CPM) for tracking character regions and linking them to names; (ii) a Dynamic Prior Module(DPM) that injects contextual cues from prior ADs and subtitles via learnable soft prompts; and (iii) a Focused Caption Module(FCM) that generates narrations enriched with plot-relevant details and named characters. To overcome limitations in character identification, we also introduce an automated pipeline for building character query banks. FocusedAD achieves state-of-the-art performance on multiple benchmarks, including strong zero-shot results on MAD-eval-Named and our newly proposed Cinepile-AD dataset. Code and data will be released at https://github.com/Thorin215/FocusedAD .
Cite
@article{arxiv.2504.12157,
title = {FocusedAD: Character-centric Movie Audio Description},
author = {Xiaojun Ye and Chun Wang and Yiren Song and Sheng Zhou and Liangcheng Li and Jiajun Bu},
journal= {arXiv preprint arXiv:2504.12157},
year = {2025}
}
Comments
Code and Demo link: https://github.com/Thorin215/FocusedAD