<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2025-sa">
    <titleInfo>
        <title>SA-CLIP: Language Guided Image Spatial and Action Feature Learning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Guanlin</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wenhao</namePart>
        <namePart type="family">Shao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Praboda</namePart>
        <namePart type="family">Rajapaksha</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Noel</namePart>
        <namePart type="family">Crespi</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>We observed that Contrastive Language-Image Pretraining (CLIP) models struggle with real-world downstream tasks such as road traffic anomaly detection, due to their inability to effectively capture spatial and action relationships between objects within images. To address this, we compile and curate a dataset with 1M samples of images using language supervision provided by the common image caption dataset, in which each image is paired with subject-relationship-object descriptions emphasizing spatial and action interactions, and train a Spatial and Action relationship aware CLIP (SA-CLIP) model. We evaluated the proposed model on the Visual Spatial Reasoning (VSR) dataset and further verified its effectiveness on the Detection-of-Traffic-Anomaly (DoTA) dataset. Experiment results show that the proposed SA-CLIP demonstrates strong abilities in understanding spatial relationships while achieving good zero-shot performance on the traffic anomaly detection task.</abstract>
    <identifier type="citekey">li-etal-2025-sa</identifier>
    <identifier type="doi">10.18653/v1/2025.findings-emnlp.1134</identifier>
    <location>
        <url>https://aclanthology.org/2025.findings-emnlp.1134/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>20808</start>
            <end>20814</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T SA-CLIP: Language Guided Image Spatial and Action Feature Learning
%A Li, Guanlin
%A Shao, Wenhao
%A Rajapaksha, Praboda
%A Crespi, Noel
%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 li-etal-2025-sa
%X We observed that Contrastive Language-Image Pretraining (CLIP) models struggle with real-world downstream tasks such as road traffic anomaly detection, due to their inability to effectively capture spatial and action relationships between objects within images. To address this, we compile and curate a dataset with 1M samples of images using language supervision provided by the common image caption dataset, in which each image is paired with subject-relationship-object descriptions emphasizing spatial and action interactions, and train a Spatial and Action relationship aware CLIP (SA-CLIP) model. We evaluated the proposed model on the Visual Spatial Reasoning (VSR) dataset and further verified its effectiveness on the Detection-of-Traffic-Anomaly (DoTA) dataset. Experiment results show that the proposed SA-CLIP demonstrates strong abilities in understanding spatial relationships while achieving good zero-shot performance on the traffic anomaly detection task.
%R 10.18653/v1/2025.findings-emnlp.1134
%U https://aclanthology.org/2025.findings-emnlp.1134/
%U https://doi.org/10.18653/v1/2025.findings-emnlp.1134
%P 20808-20814

Markdown (Informal)

[SA-CLIP: Language Guided Image Spatial and Action Feature Learning](https://aclanthology.org/2025.findings-emnlp.1134/) (Li et al., Findings 2025)

• SA-CLIP: Language Guided Image Spatial and Action Feature Learning (Li et al., Findings 2025)

ACL

• Guanlin Li, Wenhao Shao, Praboda Rajapaksha, and Noel Crespi. 2025. SA-CLIP: Language Guided Image Spatial and Action Feature Learning. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 20808–20814, Suzhou, China. Association for Computational Linguistics.