@inproceedings{bu-etal-2025-walk,
title = "Walk in Others' Shoes with a Single Glance: Human-Centric Visual Grounding with Top-View Perspective Transformation",
author = "Bu, Yuqi and
Wu, Xin and
Zhao, Zirui and
Cai, Yi and
Hsu, David and
Liu, Qiong",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.1306/",
doi = "10.18653/v1/2025.acl-long.1306",
pages = "26904--26923",
ISBN = "979-8-89176-251-0",
abstract = "Visual perspective-taking, an ability to envision others' perspectives from a single self-perspective, is vital in human-robot interactions. Thus, we introduce a human-centric visual grounding task and a dataset to evaluate this ability. Recent advances in vision-language models (VLMs) have shown potential for inferring others' perspectives, yet are insensitive to information differences induced by slight perspective changes. To address this problem, we propose a top-view enhanced perspective transformation (TEP) method, which decomposes the transition from robot to human perspectives through an abstract top-view representation. It unifies perspectives and facilitates the capture of information differences from diverse perspectives. Experimental results show that TEP improves performance by up to 18{\%}, exhibits perspective-taking abilities across various perspectives, and generalizes effectively to robotic and dynamic scenarios."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bu-etal-2025-walk">
<titleInfo>
<title>Walk in Others’ Shoes with a Single Glance: Human-Centric Visual Grounding with Top-View Perspective Transformation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuqi</namePart>
<namePart type="family">Bu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xin</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zirui</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Cai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Hsu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qiong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-251-0</identifier>
</relatedItem>
<abstract>Visual perspective-taking, an ability to envision others’ perspectives from a single self-perspective, is vital in human-robot interactions. Thus, we introduce a human-centric visual grounding task and a dataset to evaluate this ability. Recent advances in vision-language models (VLMs) have shown potential for inferring others’ perspectives, yet are insensitive to information differences induced by slight perspective changes. To address this problem, we propose a top-view enhanced perspective transformation (TEP) method, which decomposes the transition from robot to human perspectives through an abstract top-view representation. It unifies perspectives and facilitates the capture of information differences from diverse perspectives. Experimental results show that TEP improves performance by up to 18%, exhibits perspective-taking abilities across various perspectives, and generalizes effectively to robotic and dynamic scenarios.</abstract>
<identifier type="citekey">bu-etal-2025-walk</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.1306</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.1306/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>26904</start>
<end>26923</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Walk in Others’ Shoes with a Single Glance: Human-Centric Visual Grounding with Top-View Perspective Transformation
%A Bu, Yuqi
%A Wu, Xin
%A Zhao, Zirui
%A Cai, Yi
%A Hsu, David
%A Liu, Qiong
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F bu-etal-2025-walk
%X Visual perspective-taking, an ability to envision others’ perspectives from a single self-perspective, is vital in human-robot interactions. Thus, we introduce a human-centric visual grounding task and a dataset to evaluate this ability. Recent advances in vision-language models (VLMs) have shown potential for inferring others’ perspectives, yet are insensitive to information differences induced by slight perspective changes. To address this problem, we propose a top-view enhanced perspective transformation (TEP) method, which decomposes the transition from robot to human perspectives through an abstract top-view representation. It unifies perspectives and facilitates the capture of information differences from diverse perspectives. Experimental results show that TEP improves performance by up to 18%, exhibits perspective-taking abilities across various perspectives, and generalizes effectively to robotic and dynamic scenarios.
%R 10.18653/v1/2025.acl-long.1306
%U https://aclanthology.org/2025.acl-long.1306/
%U https://doi.org/10.18653/v1/2025.acl-long.1306
%P 26904-26923
Markdown (Informal)
[Walk in Others’ Shoes with a Single Glance: Human-Centric Visual Grounding with Top-View Perspective Transformation](https://aclanthology.org/2025.acl-long.1306/) (Bu et al., ACL 2025)
ACL