@inproceedings{hiray-etal-2026-cheaper,
title = "Cheaper Than Frames: An {OCR}+{K}eyframe Index as a Perception Layer for {GUI}-Video Question Answering",
author = "Hiray, Rushikesh and
Srivastava, Shubham and
Rahman, Azizur and
Hasan, Laraib and
Hijjawi, Mohammad and
Taneja, Harshit",
editor = "Atanasova, Pepa and
Haffari, Gholamreza and
Wang, Minghan",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-industry.148/",
pages = "2489--2499",
ISBN = "979-8-89176-460-6",
abstract = "Multimodal models that interpret screen recordings are usually fed raw sampled video frames,, a faithful but costly perception layer: each frame is a large image input, and dense coverage multiplies token usage. We ask whether a cheap, text-first index (on-screen OCR text plus per-state change descriptions, built once by a small local pipeline) is a better-value perception layer for the same model. On GUI-World, a released benchmark of GUI recordings with human-annotated multiple-choice questions and an objective exact-match metric, we compare the two in a controlled setting (same model, same questions), and replicate across two flagship models. On Claude Opus 4.8, answering from the index reaches 0.850 accuracy vs.0.902 for an 8-frame baseline ($n{=}286$) at 44.6{\%} lower cost, and a lossless content compression cuts cost to 75.6{\%} below frames with no measurable accuracy loss. On GPT-5.5 the trade-off is even stronger: the compressed index trails frames by only about 3{\%} (0.874 vs.0.895) while using 82.8{\%} fewer input tokens. The index is also stable across models, the compressed result differing by only about three points between them (0.843 on Opus 4.8, 0.874 on GPT-5.5). The honest summary is comparable accuracy at a fraction of the cost."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hiray-etal-2026-cheaper">
<titleInfo>
<title>Cheaper Than Frames: An OCR+Keyframe Index as a Perception Layer for GUI-Video Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rushikesh</namePart>
<namePart type="family">Hiray</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shubham</namePart>
<namePart type="family">Srivastava</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Azizur</namePart>
<namePart type="family">Rahman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laraib</namePart>
<namePart type="family">Hasan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="family">Hijjawi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harshit</namePart>
<namePart type="family">Taneja</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pepa</namePart>
<namePart type="family">Atanasova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gholamreza</namePart>
<namePart type="family">Haffari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minghan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-460-6</identifier>
</relatedItem>
<abstract>Multimodal models that interpret screen recordings are usually fed raw sampled video frames,, a faithful but costly perception layer: each frame is a large image input, and dense coverage multiplies token usage. We ask whether a cheap, text-first index (on-screen OCR text plus per-state change descriptions, built once by a small local pipeline) is a better-value perception layer for the same model. On GUI-World, a released benchmark of GUI recordings with human-annotated multiple-choice questions and an objective exact-match metric, we compare the two in a controlled setting (same model, same questions), and replicate across two flagship models. On Claude Opus 4.8, answering from the index reaches 0.850 accuracy vs.0.902 for an 8-frame baseline (n=286) at 44.6% lower cost, and a lossless content compression cuts cost to 75.6% below frames with no measurable accuracy loss. On GPT-5.5 the trade-off is even stronger: the compressed index trails frames by only about 3% (0.874 vs.0.895) while using 82.8% fewer input tokens. The index is also stable across models, the compressed result differing by only about three points between them (0.843 on Opus 4.8, 0.874 on GPT-5.5). The honest summary is comparable accuracy at a fraction of the cost.</abstract>
<identifier type="citekey">hiray-etal-2026-cheaper</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-industry.148/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>2489</start>
<end>2499</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cheaper Than Frames: An OCR+Keyframe Index as a Perception Layer for GUI-Video Question Answering
%A Hiray, Rushikesh
%A Srivastava, Shubham
%A Rahman, Azizur
%A Hasan, Laraib
%A Hijjawi, Mohammad
%A Taneja, Harshit
%Y Atanasova, Pepa
%Y Haffari, Gholamreza
%Y Wang, Minghan
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-460-6
%F hiray-etal-2026-cheaper
%X Multimodal models that interpret screen recordings are usually fed raw sampled video frames,, a faithful but costly perception layer: each frame is a large image input, and dense coverage multiplies token usage. We ask whether a cheap, text-first index (on-screen OCR text plus per-state change descriptions, built once by a small local pipeline) is a better-value perception layer for the same model. On GUI-World, a released benchmark of GUI recordings with human-annotated multiple-choice questions and an objective exact-match metric, we compare the two in a controlled setting (same model, same questions), and replicate across two flagship models. On Claude Opus 4.8, answering from the index reaches 0.850 accuracy vs.0.902 for an 8-frame baseline (n=286) at 44.6% lower cost, and a lossless content compression cuts cost to 75.6% below frames with no measurable accuracy loss. On GPT-5.5 the trade-off is even stronger: the compressed index trails frames by only about 3% (0.874 vs.0.895) while using 82.8% fewer input tokens. The index is also stable across models, the compressed result differing by only about three points between them (0.843 on Opus 4.8, 0.874 on GPT-5.5). The honest summary is comparable accuracy at a fraction of the cost.
%U https://aclanthology.org/2026.emnlp-industry.148/
%P 2489-2499
Markdown (Informal)
[Cheaper Than Frames: An OCR+Keyframe Index as a Perception Layer for GUI-Video Question Answering](https://aclanthology.org/2026.emnlp-industry.148/) (Hiray et al., EMNLP 2026)
ACL