@inproceedings{shang-etal-2024-traveler,
title = "{T}rave{LER}: A Modular Multi-{LMM} Agent Framework for Video Question-Answering",
author = "Shang, Chuyi and
You, Amos and
Subramanian, Sanjay and
Darrell, Trevor and
Herzig, Roei",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-main.544",
doi = "10.18653/v1/2024.emnlp-main.544",
pages = "9740--9766",
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.",
}
<?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>
<identifier type="doi">10.18653/v1/2024.emnlp-main.544</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.
%R 10.18653/v1/2024.emnlp-main.544
%U https://aclanthology.org/2024.emnlp-main.544
%U https://doi.org/10.18653/v1/2024.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)
ACL