VIR-Bench: Evaluating Geospatial and Temporal Understanding of MLLMs via Travel Video Itinerary Reconstruction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Hao, Murata, Eiki, Zhang, Lingfang, Sato, Ayako, Fukuda, So, Yin, Ziqi, Hu, Wentao, Nakao, Keisuke, Nakamura, Yusuke, Zwirner, Sebastian, Chen, Yi-Chia, Otomo, Hiroyuki, Ouchi, Hiroki, Kawahara, Daisuke
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908655677341696
author Wang, Hao
Murata, Eiki
Zhang, Lingfang
Sato, Ayako
Fukuda, So
Yin, Ziqi
Hu, Wentao
Nakao, Keisuke
Nakamura, Yusuke
Zwirner, Sebastian
Chen, Yi-Chia
Otomo, Hiroyuki
Ouchi, Hiroki
Kawahara, Daisuke
author_facet Wang, Hao
Murata, Eiki
Zhang, Lingfang
Sato, Ayako
Fukuda, So
Yin, Ziqi
Hu, Wentao
Nakao, Keisuke
Nakamura, Yusuke
Zwirner, Sebastian
Chen, Yi-Chia
Otomo, Hiroyuki
Ouchi, Hiroki
Kawahara, Daisuke
contents Recent advances in multimodal large language models (MLLMs) have significantly enhanced video understanding capabilities, opening new possibilities for practical applications. Yet current video benchmarks focus largely on indoor scenes or short-range outdoor activities, leaving the challenges associated with long-distance travel largely unexplored. Mastering extended geospatial-temporal trajectories is critical for next-generation MLLMs, underpinning real-world tasks such as embodied-AI planning and navigation. To bridge this gap, we present VIR-Bench, a novel benchmark consisting of 200 travel videos that frames itinerary reconstruction as a challenging task designed to evaluate and push forward MLLMs' geospatial-temporal intelligence. Experimental results reveal that state-of-the-art MLLMs, including proprietary ones, struggle to achieve high scores, underscoring the difficulty of handling videos that span extended spatial and temporal scales. Moreover, we conduct an in-depth case study in which we develop a prototype travel-planning agent that leverages the insights gained from VIR-Bench. The agent's markedly improved itinerary recommendations verify that our evaluation protocol not only benchmarks models effectively but also translates into concrete performance gains in user-facing applications.
format Preprint
id arxiv_https___arxiv_org_abs_2509_19002
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle VIR-Bench: Evaluating Geospatial and Temporal Understanding of MLLMs via Travel Video Itinerary Reconstruction
Wang, Hao
Murata, Eiki
Zhang, Lingfang
Sato, Ayako
Fukuda, So
Yin, Ziqi
Hu, Wentao
Nakao, Keisuke
Nakamura, Yusuke
Zwirner, Sebastian
Chen, Yi-Chia
Otomo, Hiroyuki
Ouchi, Hiroki
Kawahara, Daisuke
Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Machine Learning
Recent advances in multimodal large language models (MLLMs) have significantly enhanced video understanding capabilities, opening new possibilities for practical applications. Yet current video benchmarks focus largely on indoor scenes or short-range outdoor activities, leaving the challenges associated with long-distance travel largely unexplored. Mastering extended geospatial-temporal trajectories is critical for next-generation MLLMs, underpinning real-world tasks such as embodied-AI planning and navigation. To bridge this gap, we present VIR-Bench, a novel benchmark consisting of 200 travel videos that frames itinerary reconstruction as a challenging task designed to evaluate and push forward MLLMs' geospatial-temporal intelligence. Experimental results reveal that state-of-the-art MLLMs, including proprietary ones, struggle to achieve high scores, underscoring the difficulty of handling videos that span extended spatial and temporal scales. Moreover, we conduct an in-depth case study in which we develop a prototype travel-planning agent that leverages the insights gained from VIR-Bench. The agent's markedly improved itinerary recommendations verify that our evaluation protocol not only benchmarks models effectively but also translates into concrete performance gains in user-facing applications.
title VIR-Bench: Evaluating Geospatial and Temporal Understanding of MLLMs via Travel Video Itinerary Reconstruction
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Machine Learning
url https://arxiv.org/abs/2509.19002