@inproceedings{duan-etal-2025-brainloc,
title = "{B}rain{L}oc: Brain Signal-Based Object Detection with Multi-modal Alignment",
author = "Duan, Jiaqi and
Yang, Xiaoda and
Luan, Kaixuan and
Qiu, Hongshun and
Yan, Weicai and
Zhang, Xueyi and
Zhang, Youliang and
Li, Zhaoyang and
Huang, Donglin and
Lu, JunYu and
Jiang, Ziyue and
Yang, Xifeng",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-emnlp.1180/",
doi = "10.18653/v1/2025.findings-emnlp.1180",
pages = "21652--21662",
ISBN = "979-8-89176-335-7",
abstract = "Object detection is a core challenge in computer vision. Traditional methods primarily rely on intermediate modalities such as text, speech, or visual cues to interpret user intent, leading to inefficient and potentially distorted expressions of intent. Brain signals, particularly fMRI signals, emerge as a novel modality that can directly reflect user intent, eliminating ambiguities introduced during modality conversion. However, brain signal-based object detection still faces challenges in accuracy and robustness. To address these challenges, we present BrainLoc, a lightweight object detection model guided by fMRI signals. First, we employ a multi-modal alignment strategy that enhances fMRI signal feature extraction by incorporating various modalities including images and text. Second, we propose a cross-domain fusion module that promotes interaction between fMRI features and category features, improving the representation of category information in fMRI signals. Extensive experiments demonstrate that BrainLoc achieves state-of-the-art performance in brain signal-based object detection tasks, showing significant advantages in both accuracy and convenience."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="duan-etal-2025-brainloc">
<titleInfo>
<title>BrainLoc: Brain Signal-Based Object Detection with Multi-modal Alignment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiaqi</namePart>
<namePart type="family">Duan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoda</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kaixuan</namePart>
<namePart type="family">Luan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongshun</namePart>
<namePart type="family">Qiu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weicai</namePart>
<namePart type="family">Yan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xueyi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Youliang</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhaoyang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Donglin</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">JunYu</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ziyue</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xifeng</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-335-7</identifier>
</relatedItem>
<abstract>Object detection is a core challenge in computer vision. Traditional methods primarily rely on intermediate modalities such as text, speech, or visual cues to interpret user intent, leading to inefficient and potentially distorted expressions of intent. Brain signals, particularly fMRI signals, emerge as a novel modality that can directly reflect user intent, eliminating ambiguities introduced during modality conversion. However, brain signal-based object detection still faces challenges in accuracy and robustness. To address these challenges, we present BrainLoc, a lightweight object detection model guided by fMRI signals. First, we employ a multi-modal alignment strategy that enhances fMRI signal feature extraction by incorporating various modalities including images and text. Second, we propose a cross-domain fusion module that promotes interaction between fMRI features and category features, improving the representation of category information in fMRI signals. Extensive experiments demonstrate that BrainLoc achieves state-of-the-art performance in brain signal-based object detection tasks, showing significant advantages in both accuracy and convenience.</abstract>
<identifier type="citekey">duan-etal-2025-brainloc</identifier>
<identifier type="doi">10.18653/v1/2025.findings-emnlp.1180</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.1180/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>21652</start>
<end>21662</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BrainLoc: Brain Signal-Based Object Detection with Multi-modal Alignment
%A Duan, Jiaqi
%A Yang, Xiaoda
%A Luan, Kaixuan
%A Qiu, Hongshun
%A Yan, Weicai
%A Zhang, Xueyi
%A Zhang, Youliang
%A Li, Zhaoyang
%A Huang, Donglin
%A Lu, JunYu
%A Jiang, Ziyue
%A Yang, Xifeng
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F duan-etal-2025-brainloc
%X Object detection is a core challenge in computer vision. Traditional methods primarily rely on intermediate modalities such as text, speech, or visual cues to interpret user intent, leading to inefficient and potentially distorted expressions of intent. Brain signals, particularly fMRI signals, emerge as a novel modality that can directly reflect user intent, eliminating ambiguities introduced during modality conversion. However, brain signal-based object detection still faces challenges in accuracy and robustness. To address these challenges, we present BrainLoc, a lightweight object detection model guided by fMRI signals. First, we employ a multi-modal alignment strategy that enhances fMRI signal feature extraction by incorporating various modalities including images and text. Second, we propose a cross-domain fusion module that promotes interaction between fMRI features and category features, improving the representation of category information in fMRI signals. Extensive experiments demonstrate that BrainLoc achieves state-of-the-art performance in brain signal-based object detection tasks, showing significant advantages in both accuracy and convenience.
%R 10.18653/v1/2025.findings-emnlp.1180
%U https://aclanthology.org/2025.findings-emnlp.1180/
%U https://doi.org/10.18653/v1/2025.findings-emnlp.1180
%P 21652-21662
Markdown (Informal)
[BrainLoc: Brain Signal-Based Object Detection with Multi-modal Alignment](https://aclanthology.org/2025.findings-emnlp.1180/) (Duan et al., Findings 2025)
ACL
- Jiaqi Duan, Xiaoda Yang, Kaixuan Luan, Hongshun Qiu, Weicai Yan, Xueyi Zhang, Youliang Zhang, Zhaoyang Li, Donglin Huang, JunYu Lu, Ziyue Jiang, and Xifeng Yang. 2025. BrainLoc: Brain Signal-Based Object Detection with Multi-modal Alignment. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 21652–21662, Suzhou, China. Association for Computational Linguistics.