Metraipolis › archive › dc_706fd9c4cb97
From Visual Cues to Spoken Narration: Rethinking Audio Description — arXiv:2609.01725
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.01725
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T05:49:41.660Z
- SHA-256 of the archived text
d339d6480b91d8a33ad009314298b32482ec5b302c6534542fe6c9230709e1ca- Stable URL of this page
https://metraipolis.com/documento/dc_706fd9c4cb97
How to cite
From Visual Cues to Spoken Narration: Rethinking Audio Description — arXiv:2609.01725 — arXiv (en), https://arxiv.org/abs/2609.01725 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_706fd9c4cb97 (Metraipolis archive dc_706fd9c4cb97, sha256 d339d6480b91d8a33ad009314298b32482ec5b302c6534542fe6c9230709e1ca)
BibTeX
@misc{dc706fd9c4cb97,
title = {From Visual Cues to Spoken Narration: Rethinking Audio Description — arXiv:2609.01725},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.01725},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_706fd9c4cb97; sha256 d339d6480b91d8a33ad009314298b32482ec5b302c6534542fe6c9230709e1ca},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01725. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Audio Description (AD) provides spoken narration of visual events during dialogue gaps, making movies accessible to visually impaired audiences. The problem requires determining both what (which visual event) and when (position for inserting the AD) to narrate, to achieve the best user experience. Prior work has largely reduced the problem to video captioning of pre-segmented video clips, i.e., what is largely predefined and when is ignored entirely. We propose Cue2Narrate, a two-stage pipeline that jointly predicts what and when to narrate in longer untrimmed movie clips. A dual-head audio-visual localizer predicts two temporally distinct windows per AD utterance: a visual cue window and a spoken narration window. A LoRA-adapted VLM then generates concise ADs from the predicted visual evidence, trained with a Description Ranking Loss that ranks captions (negative samples) of the same frames lower than the GT AD. To benchmark this new problem statement, we introduce the LongLSMDC benchmark with up to 8-min movie clips (~6.5min on average). On LongLSMDC, Cue2Narrate outperforms video-only and audio-only localization baselines by 5--12 points in avg. mAP. Under both predicted- and GT-window evaluation, Cue2Narrate improves AD generation over the corresponding fine-tuned base VLM. These results establish the first benchmark for multi-segment AD generation on long-form clips. Data & Code: this https URL Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-03 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.01725 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T05:25:58.003Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).