FocusedAD: Character-centric Movie Audio Description

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ye, Xiaojun, Wang, Chun, Song, Yiren, Zhou, Sheng, Li, Liangcheng, Bu, Jiajun
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910935471357952
author Ye, Xiaojun
Wang, Chun
Song, Yiren
Zhou, Sheng
Li, Liangcheng
Bu, Jiajun
author_facet Ye, Xiaojun
Wang, Chun
Song, Yiren
Zhou, Sheng
Li, Liangcheng
Bu, Jiajun
contents 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 .
format Preprint
id arxiv_https___arxiv_org_abs_2504_12157
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FocusedAD: Character-centric Movie Audio Description
Ye, Xiaojun
Wang, Chun
Song, Yiren
Zhou, Sheng
Li, Liangcheng
Bu, Jiajun
Computer Vision and Pattern Recognition
I.2.10
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 .
title FocusedAD: Character-centric Movie Audio Description
topic Computer Vision and Pattern Recognition
I.2.10
url https://arxiv.org/abs/2504.12157