Metraipolis › archive › dc_5563f9f2ff79
REFRAMED: Towards Realistic Audio Description Generation for Movies — arXiv:2608.09765
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.09765
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T08:50:28.248Z
- SHA-256 of the archived text
75d39826a12d2ceff6477307f1f0c7bfef1152e2ee32adf3a35397f2243c7794- Stable URL of this page
https://metraipolis.com/documento/dc_5563f9f2ff79
How to cite
REFRAMED: Towards Realistic Audio Description Generation for Movies — arXiv:2608.09765 — arXiv (en), https://arxiv.org/abs/2608.09765 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5563f9f2ff79 (Metraipolis archive dc_5563f9f2ff79, sha256 75d39826a12d2ceff6477307f1f0c7bfef1152e2ee32adf3a35397f2243c7794)
BibTeX
@misc{dc5563f9f2ff79,
title = {REFRAMED: Towards Realistic Audio Description Generation for Movies — arXiv:2608.09765},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.09765},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5563f9f2ff79; sha256 75d39826a12d2ceff6477307f1f0c7bfef1152e2ee32adf3a35397f2243c7794},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.09765. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Audio Description (AD) is a verbal narration of key visual content in videos, enabling access for visually impaired audiences. Unlike standard video captioning, AD is a structured editorial task: descriptions must be inserted into gaps in dialogue and must convey only what is needed to understand the narrative being told. However, existing approaches formulate AD generation in an artificial setting where both the content and timing of descriptions are pre-specified, reducing the task to clip-level captioning. They further rely on noisy transcription and alignment pipelines, and lack the rich parallel data required for modeling narrative context. We introduce a new formulation of AD generation in which models must jointly decide what to describe and when to do it. To support this, we present REFRAMED, a high-quality dataset of 2,023 videos that span 3,302 scenes from 206 movies, with professional AD transcripts (both American and British versions), professional subtitles and aligned screenplays. We also provide a manually curated challenge set that pairs full movies with multiple AD references, together with evaluation protocols that leverage dialogue gaps and multi-reference comparisons. Experiments with state-of-the-art AD systems and multimodal LLMs show that they outperform trivial baselines but fall far short of expert human performance. Our dataset and benchmark establish a new foundation for research on video understanding. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-11 in cs.CL). Categorie arXiv: Computation and Language (cs.CL) ; Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.09765 — 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 2026-10-19T08:49:41.939Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).