Skip to main navigation Skip to search Skip to main content

Beyond Vision: How Language affects Visual Grounding in UAV Imagery

  • Jue Chen
  • , Penghui Huang
  • , Ran Ding
  • , Zhentao Zou
  • , Xue Yang
  • , Xue Jiang
  • , Yue Zhou*
  • , Hongxin Yang
  • , Jonathan Li
  • *Corresponding author for this work
  • East China Normal University
  • Shanghai Jiao Tong University
  • University of Waterloo

Research output: Contribution to journal › Conference article › peer-review

Abstract

Visual Grounding (VG) is a core multimodal task that localizes image targets via natural language descriptions, and it is crucial for Unmanned Aerial Vehicle (UAV) applications. However, existing remote sensing (RS) VG datasets primarily rely on rule-driven explicit descriptions, which are inconsistent with real-world demands for interpreting implicit descriptions based on context, common sense, or domain knowledge. In addition, the cross-lingual robustness of Large Vision-Language Models (LVLMs) in implicit VG remains to be thoroughly investigated. This study evaluates the cross-lingual performance of Qwen2.5-VL-7B and InternVL3.5-8B across nine languages, incorporating analyses of text length dynamics, visual attention, and language structural effects. The results demonstrate that Qwen2.5-VL-7B exhibits outstanding performance in maintaining consistent task paradigm alignment (explicit VG outperforms implicit VG) and balanced text output, which benefits from the syntactic stability and low cognitive load of East Asian languages. In contrast, InternVL3.5-8B presents task paradigm misalignment, uncontrolled text expansion, and generative hallucinations. Furthermore, differences in language structures: East Asian languages depend on word order for semantic expression, whereas Western languages feature complex lexical morphology, significantly affect attention allocation and VG accuracy. This study provides key insights for optimizing cross-lingual vision-language alignment of LVLMs and advancing practical multimodal applications in UAV scenarios.

Original languageEnglish
Pages (from-to)651-656
Number of pages6
JournalInternational Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives
Volume49
Issue numberB2-2026
DOIs
StatePublished - 23 Jul 2026
Event25th ISPRS Congress 2026 �From Imagery to Understanding� - Toronto, Canada
Duration: 4 Jul 2026 → 11 Jul 2026

Keywords

  • Multi-modal large language model (MLLM)
  • Vision language model (VLM)
  • Visual grounding

Fingerprint

Dive into the research topics of 'Beyond Vision: How Language affects Visual Grounding in UAV Imagery'. Together they form a unique fingerprint.

Cite this