<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shang-etal-2024-traveler">
    <titleInfo>
        <title>TraveLER: A Modular Multi-LMM Agent Framework for Video Question-Answering</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Chuyi</namePart>
        <namePart type="family">Shang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Amos</namePart>
        <namePart type="family">You</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sanjay</namePart>
        <namePart type="family">Subramanian</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Trevor</namePart>
        <namePart type="family">Darrell</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Roei</namePart>
        <namePart type="family">Herzig</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yaser</namePart>
            <namePart type="family">Al-Onaizan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohit</namePart>
            <namePart type="family">Bansal</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yun-Nung</namePart>
            <namePart type="family">Chen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Miami, Florida, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Recently, image-based Large Multimodal Models (LMMs) have made significant progress in video question-answering (VideoQA) using a frame-wise approach by leveraging large-scale pretraining in a zero-shot manner. Nevertheless, these models need to be capable of finding relevant information, extracting it, and answering the question simultaneously. Currently, existing methods perform all of these steps in a single pass without being able to adapt if insufficient or incorrect information is collected. To overcome this, we introduce a modular multi-LMM agent framework based on several agents with different roles, instructed by a Planner agent that updates its instructions using shared feedback from the other agents. Specifically, we propose TraveLER, a method that can create a plan to ”**Trave**rse” through the video, ask questions about individual frames to ”**L**ocate” and store key information, and then ”**E**valuate” if there is enough information to answer the question. Finally, if there is not enough information, our method is able to ”**R**eplan” based on its collected knowledge. Through extensive experiments, we find that the proposed TraveLER approach improves performance on several VideoQA benchmarks without the need to fine-tune on specific datasets. Our code is available at https://github.com/traveler-framework/TraveLER.</abstract>
    <identifier type="citekey">shang-etal-2024-traveler</identifier>
    <location>
        <url>https://aclanthology.org/2024.emnlp-main.544</url>
    </location>
    <part>
        <date>2024-11</date>
        <extent unit="page">
            <start>9740</start>
            <end>9766</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T TraveLER: A Modular Multi-LMM Agent Framework for Video Question-Answering
%A Shang, Chuyi
%A You, Amos
%A Subramanian, Sanjay
%A Darrell, Trevor
%A Herzig, Roei
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F shang-etal-2024-traveler
%X Recently, image-based Large Multimodal Models (LMMs) have made significant progress in video question-answering (VideoQA) using a frame-wise approach by leveraging large-scale pretraining in a zero-shot manner. Nevertheless, these models need to be capable of finding relevant information, extracting it, and answering the question simultaneously. Currently, existing methods perform all of these steps in a single pass without being able to adapt if insufficient or incorrect information is collected. To overcome this, we introduce a modular multi-LMM agent framework based on several agents with different roles, instructed by a Planner agent that updates its instructions using shared feedback from the other agents. Specifically, we propose TraveLER, a method that can create a plan to ”**Trave**rse” through the video, ask questions about individual frames to ”**L**ocate” and store key information, and then ”**E**valuate” if there is enough information to answer the question. Finally, if there is not enough information, our method is able to ”**R**eplan” based on its collected knowledge. Through extensive experiments, we find that the proposed TraveLER approach improves performance on several VideoQA benchmarks without the need to fine-tune on specific datasets. Our code is available at https://github.com/traveler-framework/TraveLER.
%U https://aclanthology.org/2024.emnlp-main.544
%P 9740-9766

Markdown (Informal)

[TraveLER: A Modular Multi-LMM Agent Framework for Video Question-Answering](https://aclanthology.org/2024.emnlp-main.544) (Shang et al., EMNLP 2024)

• TraveLER: A Modular Multi-LMM Agent Framework for Video Question-Answering (Shang et al., EMNLP 2024)

ACL

• Chuyi Shang, Amos You, Sanjay Subramanian, Trevor Darrell, and Roei Herzig. 2024. TraveLER: A Modular Multi-LMM Agent Framework for Video Question-Answering. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 9740–9766, Miami, Florida, USA. Association for Computational Linguistics.