MetaphorVU: Towards Metaphorical Video Understanding

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Li, Zhuoqun, Cao, Boxi, Jiang, Guiping, Lv, Fangrui, Pan, Ruotong, Wang, Jianan, Wu, Xiangyu, Lin, Hongyu, Lu, Yaojie, Du, Yong, Jia, Ruyin, Liyan, Gao, Tingting, Li, Han, Han, Xianpei, Sun, Le
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911715336126464
author Li, Zhuoqun
Cao, Boxi
Jiang, Guiping
Lv, Fangrui
Pan, Ruotong
Wang, Jianan
Wu, Xiangyu
Lin, Hongyu
Lu, Yaojie
Du, Yong
Jia, Ruyin
Liyan
Gao, Tingting
Li, Han
Han, Xianpei
Sun, Le
author_facet Li, Zhuoqun
Cao, Boxi
Jiang, Guiping
Lv, Fangrui
Pan, Ruotong
Wang, Jianan
Wu, Xiangyu
Lin, Hongyu
Lu, Yaojie
Du, Yong
Jia, Ruyin
Liyan
Gao, Tingting
Li, Han
Han, Xianpei
Sun, Le
contents Metaphorical videos are prevalent across various real-world scenarios to convey complex ideas, and understanding them typically requires high-order cognitive capabilities. The lack of systematic studies on metaphorical video understanding not only constrains the real-world applicability of MLLMs but also impedes the thorough assessment of their high-order cognitive capabilities. To bridge this gap, we propose MetaphorVU-Bench, the first systematic and comprehensive benchmark dedicated to metaphorical video understanding. Through experiments, we find current MLLMs struggle with accurate metaphorical video understanding, lagging far behind human level, primarily due to defective cross-domain mapping. Motivated by this finding, we construct a metaphor knowledge graph as mapping augmentation and propose MetaphorBoost, an inference-time enhancement framework achieving consistent performance improvement. Our benchmark, analysis, and method provide useful insights and a foundation for future research on advancing MLLMs.
format Preprint
id arxiv_https___arxiv_org_abs_2605_25461
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MetaphorVU: Towards Metaphorical Video Understanding
Li, Zhuoqun
Cao, Boxi
Jiang, Guiping
Lv, Fangrui
Pan, Ruotong
Wang, Jianan
Wu, Xiangyu
Lin, Hongyu
Lu, Yaojie
Du, Yong
Jia, Ruyin
Liyan
Gao, Tingting
Li, Han
Han, Xianpei
Sun, Le
Computer Vision and Pattern Recognition
Metaphorical videos are prevalent across various real-world scenarios to convey complex ideas, and understanding them typically requires high-order cognitive capabilities. The lack of systematic studies on metaphorical video understanding not only constrains the real-world applicability of MLLMs but also impedes the thorough assessment of their high-order cognitive capabilities. To bridge this gap, we propose MetaphorVU-Bench, the first systematic and comprehensive benchmark dedicated to metaphorical video understanding. Through experiments, we find current MLLMs struggle with accurate metaphorical video understanding, lagging far behind human level, primarily due to defective cross-domain mapping. Motivated by this finding, we construct a metaphor knowledge graph as mapping augmentation and propose MetaphorBoost, an inference-time enhancement framework achieving consistent performance improvement. Our benchmark, analysis, and method provide useful insights and a foundation for future research on advancing MLLMs.
title MetaphorVU: Towards Metaphorical Video Understanding
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.25461