<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sakajo-etal-2025-toward">
    <titleInfo>
        <title>Toward Automatic Safe Driving Instruction: A Large-Scale Vision Language Model Approach</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Haruki</namePart>
        <namePart type="family">Sakajo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hiroshi</namePart>
        <namePart type="family">Takato</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hiroshi</namePart>
        <namePart type="family">Tsutsui</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Komei</namePart>
        <namePart type="family">Soda</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hidetaka</namePart>
        <namePart type="family">Kamigaito</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Taro</namePart>
        <namePart type="family">Watanabe</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 1st Workshop on Multimodal Models for Low-Resource Contexts and Social Impact (MMLoSo 2025)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ankita</namePart>
            <namePart type="family">Shukla</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sandeep</namePart>
            <namePart type="family">Kumar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Amrit</namePart>
            <namePart type="given">Singh</namePart>
            <namePart type="family">Bedi</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>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Mumbai, India</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-311-1</identifier>
    </relatedItem>
    <abstract>Large-scale Vision Language Models (LVLMs) exhibit advanced capabilities in tasks that require visual information, including object detection. These capabilities have promising applications in various industrial domains, such as autonomous driving. For example, LVLMs can generate safety-oriented descriptions of videos captured by road-facing cameras. However, ensuring comprehensive safety requires monitoring driver-facing views as well to detect risky events, such as the use of mobiles while driving. Thus, the ability to process synchronized inputs is necessary from both driver-facing and road-facing cameras. In this study, we develop models and investigate the capabilities of LVLMs by constructing a dataset and evaluating their performance on this dataset. Our experimental results demonstrate that while pre-trained LVLMs have limited effectiveness, fine-tuned LVLMs can generate accurate and safety-aware driving instructions. Nonetheless, several challenges remain, particularly in detecting subtle or complex events in the video. Our findings and error analysis provide valuable insights that can contribute to the improvement of LVLM-based systems in this domain.</abstract>
    <identifier type="citekey">sakajo-etal-2025-toward</identifier>
    <location>
        <url>https://aclanthology.org/2025.mmloso-1.2/</url>
    </location>
    <part>
        <date>2025-12</date>
        <extent unit="page">
            <start>13</start>
            <end>24</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Toward Automatic Safe Driving Instruction: A Large-Scale Vision Language Model Approach
%A Sakajo, Haruki
%A Takato, Hiroshi
%A Tsutsui, Hiroshi
%A Soda, Komei
%A Kamigaito, Hidetaka
%A Watanabe, Taro
%Y Shukla, Ankita
%Y Kumar, Sandeep
%Y Bedi, Amrit Singh
%Y Chakraborty, Tanmoy
%S Proceedings of the 1st Workshop on Multimodal Models for Low-Resource Contexts and Social Impact (MMLoSo 2025)
%D 2025
%8 December
%I Association for Computational Linguistics
%C Mumbai, India
%@ 979-8-89176-311-1
%F sakajo-etal-2025-toward
%X Large-scale Vision Language Models (LVLMs) exhibit advanced capabilities in tasks that require visual information, including object detection. These capabilities have promising applications in various industrial domains, such as autonomous driving. For example, LVLMs can generate safety-oriented descriptions of videos captured by road-facing cameras. However, ensuring comprehensive safety requires monitoring driver-facing views as well to detect risky events, such as the use of mobiles while driving. Thus, the ability to process synchronized inputs is necessary from both driver-facing and road-facing cameras. In this study, we develop models and investigate the capabilities of LVLMs by constructing a dataset and evaluating their performance on this dataset. Our experimental results demonstrate that while pre-trained LVLMs have limited effectiveness, fine-tuned LVLMs can generate accurate and safety-aware driving instructions. Nonetheless, several challenges remain, particularly in detecting subtle or complex events in the video. Our findings and error analysis provide valuable insights that can contribute to the improvement of LVLM-based systems in this domain.
%U https://aclanthology.org/2025.mmloso-1.2/
%P 13-24

Markdown (Informal)

[Toward Automatic Safe Driving Instruction: A Large-Scale Vision Language Model Approach](https://aclanthology.org/2025.mmloso-1.2/) (Sakajo et al., MMLoSo 2025)

• Toward Automatic Safe Driving Instruction: A Large-Scale Vision Language Model Approach (Sakajo et al., MMLoSo 2025)

ACL

• Haruki Sakajo, Hiroshi Takato, Hiroshi Tsutsui, Komei Soda, Hidetaka Kamigaito, and Taro Watanabe. 2025. Toward Automatic Safe Driving Instruction: A Large-Scale Vision Language Model Approach. In Proceedings of the 1st Workshop on Multimodal Models for Low-Resource Contexts and Social Impact (MMLoSo 2025), pages 13–24, Mumbai, India. Association for Computational Linguistics.