<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hui-etal-2026-videonav">
    <titleInfo>
        <title>VideoNav: Cost-Aware Index Navigation for Long Video Understanding</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yulong</namePart>
        <namePart type="family">Hui</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yuchen</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Rui</namePart>
        <namePart type="family">Kong</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xinran</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jinman</namePart>
        <namePart type="family">Zhao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dawei</namePart>
        <namePart type="family">Yin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Huanchen</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-462-0</identifier>
    </relatedItem>
    <abstract>The rising demand for long-video understanding presents significant challenges due to massive information and complex temporal dependencies. Direct processing with Large Visual Language Models (VLMs) incurs high computational costs and risks information loss due to frame sampling. Meanwhile, existing agent-based methods often struggle with fragmented contexts and the high overhead of iterative processing. Therefore, we propose VideoNav, which introduces a new paradigm of index-centric navigation, reformulating video understanding as cost-aware structured query processing. VideoNav decouples heavy perception from online reasoning, including offline index construction and online adaptive navigation. In the offline phase, we transform unstructured video data into a structured, multi-granular index tree. During the online phase, the framework executes a top-down, coarse-to-fine navigating strategy. Leveraging the LLM agents, it efficiently locates relevant information and answers the query with navigating guidance, multi-level navigation, dual-path routing and visual inspection. Crucially, this adaptive mechanism enables early termination when high-level information suffices, minimizing redundant computation. Extensive experiments across different benchmarks demonstrate the effectiveness of our framework. VideoNav achieves decent accuracy while delivering 2.5x-5.7x cost savings and a 2.9x-5.8x speedup.</abstract>
    <identifier type="citekey">hui-etal-2026-videonav</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.1843/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>39346</start>
            <end>39362</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T VideoNav: Cost-Aware Index Navigation for Long Video Understanding
%A Hui, Yulong
%A Li, Yuchen
%A Kong, Rui
%A Chen, Xinran
%A Zhao, Jinman
%A Yin, Dawei
%A Zhang, Huanchen
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F hui-etal-2026-videonav
%X The rising demand for long-video understanding presents significant challenges due to massive information and complex temporal dependencies. Direct processing with Large Visual Language Models (VLMs) incurs high computational costs and risks information loss due to frame sampling. Meanwhile, existing agent-based methods often struggle with fragmented contexts and the high overhead of iterative processing. Therefore, we propose VideoNav, which introduces a new paradigm of index-centric navigation, reformulating video understanding as cost-aware structured query processing. VideoNav decouples heavy perception from online reasoning, including offline index construction and online adaptive navigation. In the offline phase, we transform unstructured video data into a structured, multi-granular index tree. During the online phase, the framework executes a top-down, coarse-to-fine navigating strategy. Leveraging the LLM agents, it efficiently locates relevant information and answers the query with navigating guidance, multi-level navigation, dual-path routing and visual inspection. Crucially, this adaptive mechanism enables early termination when high-level information suffices, minimizing redundant computation. Extensive experiments across different benchmarks demonstrate the effectiveness of our framework. VideoNav achieves decent accuracy while delivering 2.5x-5.7x cost savings and a 2.9x-5.8x speedup.
%U https://aclanthology.org/2026.findings-emnlp.1843/
%P 39346-39362

Markdown (Informal)

[VideoNav: Cost-Aware Index Navigation for Long Video Understanding](https://aclanthology.org/2026.findings-emnlp.1843/) (Hui et al., Findings 2026)

• VideoNav: Cost-Aware Index Navigation for Long Video Understanding (Hui et al., Findings 2026)

ACL

• Yulong Hui, Yuchen Li, Rui Kong, Xinran Chen, Jinman Zhao, Dawei Yin, and Huanchen Zhang. 2026. VideoNav: Cost-Aware Index Navigation for Long Video Understanding. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 39346–39362, Budapest, Hungary. Association for Computational Linguistics.