Salvato in:
Dettagli Bibliografici
Autori principali: Do, Lana, Jung, Gio, Barajas, Juvenal Francisco, Scott, Andrew Taylor, Ihorn, Shasta, Blum, Alexander Mario, Athitsos, Vassilis, Yoon, Ilmi
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2602.01390
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909018990051328
author Do, Lana
Jung, Gio
Barajas, Juvenal Francisco
Scott, Andrew Taylor
Ihorn, Shasta
Blum, Alexander Mario
Athitsos, Vassilis
Yoon, Ilmi
author_facet Do, Lana
Jung, Gio
Barajas, Juvenal Francisco
Scott, Andrew Taylor
Ihorn, Shasta
Blum, Alexander Mario
Athitsos, Vassilis
Yoon, Ilmi
contents Digital video is central to communication, education, and entertainment, but without audio description (AD), blind and low-vision users are excluded. While crowdsourced platforms and vision-language models (VLMs) expand AD production, quality is rarely checked systematically. Existing evaluations rely on NLP metrics and short-clip guidelines, leaving open the question of how to assess long-form AD quality at scale. To address this, we developed a methodological workflow using Item Response Theory to evaluate VLM and human rater proficiency against expert-established ground truth. Evaluations were based on a six-dimensional framework, grounded in professional guidelines and shaped by insights from our accessibility experts and blind consultants. Findings suggest that top-performing VLMs can approximate ground-truth ratings at levels comparable to human raters. However, qualitative analysis reveals that VLM reasoning is less reliable and actionable than that of human respondents. These insights underscore the potential of hybrid evaluation systems that leverage VLMs alongside human oversight, offering a path toward scalable AD quality control.
format Preprint
id arxiv_https___arxiv_org_abs_2602_01390
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Toward Scalable Audio Description Quality Control: A Workflow for Evaluating Human and VLM Raters
Do, Lana
Jung, Gio
Barajas, Juvenal Francisco
Scott, Andrew Taylor
Ihorn, Shasta
Blum, Alexander Mario
Athitsos, Vassilis
Yoon, Ilmi
Human-Computer Interaction
Artificial Intelligence
Digital video is central to communication, education, and entertainment, but without audio description (AD), blind and low-vision users are excluded. While crowdsourced platforms and vision-language models (VLMs) expand AD production, quality is rarely checked systematically. Existing evaluations rely on NLP metrics and short-clip guidelines, leaving open the question of how to assess long-form AD quality at scale. To address this, we developed a methodological workflow using Item Response Theory to evaluate VLM and human rater proficiency against expert-established ground truth. Evaluations were based on a six-dimensional framework, grounded in professional guidelines and shaped by insights from our accessibility experts and blind consultants. Findings suggest that top-performing VLMs can approximate ground-truth ratings at levels comparable to human raters. However, qualitative analysis reveals that VLM reasoning is less reliable and actionable than that of human respondents. These insights underscore the potential of hybrid evaluation systems that leverage VLMs alongside human oversight, offering a path toward scalable AD quality control.
title Toward Scalable Audio Description Quality Control: A Workflow for Evaluating Human and VLM Raters
topic Human-Computer Interaction
Artificial Intelligence
url https://arxiv.org/abs/2602.01390