@inproceedings{zhang-etal-2026-wearertext,
title = "{W}earer{T}ext: Benchmarking Wearer-Centered Scene Text Understanding in {AI}-Glasses Videos",
author = "Zhang, Yaping and
Tu, Mei and
Wu, Jinting and
Zhang, Qixuan and
Chen, Xiaoyu and
Zhang, Mengchao and
Huang, Yuchen and
Chen, Junshen and
Zhang, Fan and
Xiang, Lu and
Zhu, Junnan and
Zhao, Yang and
Zhou, Yu and
Zong, Chengqing",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.2184/",
pages = "49653--49669",
ISBN = "979-8-89176-459-0",
abstract = "Recent MLLMs have shown promise in scene-text-aware video understanding, yet their ability to understand scene text from the wearer{'}s perspective in AI-glasses videos remains underexplored. AI-glasses videos are passively captured without a camera-frame preview, limiting the wearer{'}s ability to adjust framing during recording. As a result, relevant text may be unstable, and the recorded view may not fully reflect the wearer{'}s attention. The challenge is thus not merely to read visible text, but to identify and read the right text given the wearer{'}s position, viewpoint trajectory, and goal. To systematically evaluate this capability, we introduce **WearerText**, a benchmark for **Wearer**-Centered Scene **Text** Understanding, comprising 1,101 real-world AI-glasses videos and 15,336 QA pairs spanning 13 tasks. These tasks are organized into a three-level diagnostic hierarchy: *L1 Text Perception*, *L2 Contextual Understanding*, and *L3 Wearer-Grounded Reasoning*, targeting unstable text perception, wearer-view alignment, and goal-oriented text reasoning, respectively. To ensure reliable construction and evaluation, we develop **MAH-V**, a multi-agent hybrid verification pipeline for QA construction, and propose **VerEval**, a Verified-evidence metric for open-ended Evaluation. Benchmarking 20 recent MLLMs shows that current models still struggle with wearer-centered scene text understanding, particularly on tasks requiring wearer-view alignment and goal-oriented text reasoning."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2026-wearertext">
<titleInfo>
<title>WearerText: Benchmarking Wearer-Centered Scene Text Understanding in AI-Glasses Videos</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaping</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mei</namePart>
<namePart type="family">Tu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinting</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qixuan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoyu</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mengchao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuchen</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junshen</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Xiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junnan</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</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</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</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">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Recent MLLMs have shown promise in scene-text-aware video understanding, yet their ability to understand scene text from the wearer’s perspective in AI-glasses videos remains underexplored. AI-glasses videos are passively captured without a camera-frame preview, limiting the wearer’s ability to adjust framing during recording. As a result, relevant text may be unstable, and the recorded view may not fully reflect the wearer’s attention. The challenge is thus not merely to read visible text, but to identify and read the right text given the wearer’s position, viewpoint trajectory, and goal. To systematically evaluate this capability, we introduce **WearerText**, a benchmark for **Wearer**-Centered Scene **Text** Understanding, comprising 1,101 real-world AI-glasses videos and 15,336 QA pairs spanning 13 tasks. These tasks are organized into a three-level diagnostic hierarchy: *L1 Text Perception*, *L2 Contextual Understanding*, and *L3 Wearer-Grounded Reasoning*, targeting unstable text perception, wearer-view alignment, and goal-oriented text reasoning, respectively. To ensure reliable construction and evaluation, we develop **MAH-V**, a multi-agent hybrid verification pipeline for QA construction, and propose **VerEval**, a Verified-evidence metric for open-ended Evaluation. Benchmarking 20 recent MLLMs shows that current models still struggle with wearer-centered scene text understanding, particularly on tasks requiring wearer-view alignment and goal-oriented text reasoning.</abstract>
<identifier type="citekey">zhang-etal-2026-wearertext</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.2184/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>49653</start>
<end>49669</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T WearerText: Benchmarking Wearer-Centered Scene Text Understanding in AI-Glasses Videos
%A Zhang, Yaping
%A Tu, Mei
%A Wu, Jinting
%A Zhang, Qixuan
%A Chen, Xiaoyu
%A Zhang, Mengchao
%A Huang, Yuchen
%A Chen, Junshen
%A Zhang, Fan
%A Xiang, Lu
%A Zhu, Junnan
%A Zhao, Yang
%A Zhou, Yu
%A Zong, Chengqing
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F zhang-etal-2026-wearertext
%X Recent MLLMs have shown promise in scene-text-aware video understanding, yet their ability to understand scene text from the wearer’s perspective in AI-glasses videos remains underexplored. AI-glasses videos are passively captured without a camera-frame preview, limiting the wearer’s ability to adjust framing during recording. As a result, relevant text may be unstable, and the recorded view may not fully reflect the wearer’s attention. The challenge is thus not merely to read visible text, but to identify and read the right text given the wearer’s position, viewpoint trajectory, and goal. To systematically evaluate this capability, we introduce **WearerText**, a benchmark for **Wearer**-Centered Scene **Text** Understanding, comprising 1,101 real-world AI-glasses videos and 15,336 QA pairs spanning 13 tasks. These tasks are organized into a three-level diagnostic hierarchy: *L1 Text Perception*, *L2 Contextual Understanding*, and *L3 Wearer-Grounded Reasoning*, targeting unstable text perception, wearer-view alignment, and goal-oriented text reasoning, respectively. To ensure reliable construction and evaluation, we develop **MAH-V**, a multi-agent hybrid verification pipeline for QA construction, and propose **VerEval**, a Verified-evidence metric for open-ended Evaluation. Benchmarking 20 recent MLLMs shows that current models still struggle with wearer-centered scene text understanding, particularly on tasks requiring wearer-view alignment and goal-oriented text reasoning.
%U https://aclanthology.org/2026.emnlp-main.2184/
%P 49653-49669
Markdown (Informal)
[WearerText: Benchmarking Wearer-Centered Scene Text Understanding in AI-Glasses Videos](https://aclanthology.org/2026.emnlp-main.2184/) (Zhang et al., EMNLP 2026)
ACL
- Yaping Zhang, Mei Tu, Jinting Wu, Qixuan Zhang, Xiaoyu Chen, Mengchao Zhang, Yuchen Huang, Junshen Chen, Fan Zhang, Lu Xiang, Junnan Zhu, Yang Zhao, Yu Zhou, and Chengqing Zong. 2026. WearerText: Benchmarking Wearer-Centered Scene Text Understanding in AI-Glasses Videos. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 49653–49669, Budapest, Hungary. Association for Computational Linguistics.