# ViDscribe: Multimodal AI for Customizing Audio Description and Question Answering in Online Videos

Source: [ViDscribe: Multimodal AI for Customizing Audio Description and Question Answering in Online Videos](<https://www.sota2.com/research/paper/69b8e0200636e5bf4afbebd3>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-18T05:00:11.457Z

Authors: Maryam Cheema, Sina Elahimanesh, Pooyan Fazli, Hasti Seifi

Published: 2026-03-15T23:35:09.000Z

## Abstract

Advances in multimodal large language models enable automatic video narration and question answering (VQA), offering scalable alternatives to labor-intensive, human-authored audio descriptions (ADs) for blind and low vision (BLV) viewers. However, prior AI-driven AD systems rarely adapt to the diverse needs and preferences of BLV individuals across videos and are typically evaluated in controlled, single-session settings. We present ViDscribe, a web-based platform that integrates AI-generated ADs with six types of user customizations and a conversational VQA interface for YouTube videos. Through a longitudinal, in-the-wild study with eight BLV participants, we examine how users engage with customization and VQA features over time. Our results show sustained engagement with both features and that customized ADs improve effectiveness, enjoyment, and immersion compared to default ADs, highlighting the value of personalized, interactive video access for BLV users.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.14662>)

[PDF](<https://arxiv.org/pdf/2603.14662.pdf>)