Vid2Coach: Transforming How-To Videos into Task Assistants

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Huh, Mina, Xue, Zihui, Das, Ujjaini, Ashutosh, Kumar, Grauman, Kristen, Pavel, Amy
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909704978956288
author Huh, Mina
Xue, Zihui
Das, Ujjaini
Ashutosh, Kumar
Grauman, Kristen
Pavel, Amy
author_facet Huh, Mina
Xue, Zihui
Das, Ujjaini
Ashutosh, Kumar
Grauman, Kristen
Pavel, Amy
contents People use videos to learn new recipes, exercises, and crafts. Such videos remain difficult for blind and low vision (BLV) people to follow as they rely on visual comparison. Our observations of visual rehabilitation therapists (VRTs) guiding BLV people to follow how-to videos revealed that VRTs provide both proactive and responsive support including detailed descriptions, non-visual workarounds, and progress feedback. We propose Vid2Coach, a system that transforms how-to videos into wearable camera-based assistants that provide accessible instructions and mixed-initiative feedback. From the video, Vid2Coach generates accessible instructions by augmenting narrated instructions with demonstration details and completion criteria for each step. It then uses retrieval-augmented-generation to extract relevant non-visual workarounds from BLV-specific resources. Vid2Coach then monitors user progress with a camera embedded in commercial smart glasses to provide context-aware instructions, proactive feedback, and answers to user questions. BLV participants (N=8) using Vid2Coach completed cooking tasks with 58.5\% fewer errors than when using their typical workflow and wanted to use Vid2Coach in their daily lives. Vid2Coach demonstrates an opportunity for AI visual assistance that strengthens rather than replaces non-visual expertise.
format Preprint
id arxiv_https___arxiv_org_abs_2506_00717
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Vid2Coach: Transforming How-To Videos into Task Assistants
Huh, Mina
Xue, Zihui
Das, Ujjaini
Ashutosh, Kumar
Grauman, Kristen
Pavel, Amy
Human-Computer Interaction
Computer Vision and Pattern Recognition
People use videos to learn new recipes, exercises, and crafts. Such videos remain difficult for blind and low vision (BLV) people to follow as they rely on visual comparison. Our observations of visual rehabilitation therapists (VRTs) guiding BLV people to follow how-to videos revealed that VRTs provide both proactive and responsive support including detailed descriptions, non-visual workarounds, and progress feedback. We propose Vid2Coach, a system that transforms how-to videos into wearable camera-based assistants that provide accessible instructions and mixed-initiative feedback. From the video, Vid2Coach generates accessible instructions by augmenting narrated instructions with demonstration details and completion criteria for each step. It then uses retrieval-augmented-generation to extract relevant non-visual workarounds from BLV-specific resources. Vid2Coach then monitors user progress with a camera embedded in commercial smart glasses to provide context-aware instructions, proactive feedback, and answers to user questions. BLV participants (N=8) using Vid2Coach completed cooking tasks with 58.5\% fewer errors than when using their typical workflow and wanted to use Vid2Coach in their daily lives. Vid2Coach demonstrates an opportunity for AI visual assistance that strengthens rather than replaces non-visual expertise.
title Vid2Coach: Transforming How-To Videos into Task Assistants
topic Human-Computer Interaction
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.00717