# ProVG: Progressive Visual Grounding via Language Decoupling for Remote Sensing Imagery

arXiv: https://arxiv.org/abs/2604.01893 · HTML: https://mlsanity.com/paper/2604.01893/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 34 references that are in the map.
- First posted on arXiv 2 Apr 2026.

## Builds on (most cited first, 10 of 10)

- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Multi-task Collaborative Network for Joint Referring Expression Comprehension and Segmentation](https://mlsanity.com/paper/2003.08813/) (2020)
- [PolyFormer: Referring Image Segmentation as Sequential Polygon Generation](https://mlsanity.com/paper/2302.07387/) (2023)
- [Referring Transformer: A One-step Approach to Multi-task Visual Grounding](https://mlsanity.com/paper/2106.03089/) (2021)
- [Improving Visual Grounding with Visual-Linguistic Verification and Iterative Reasoning](https://mlsanity.com/paper/2205.00272/) (2022)
- [Shifting More Attention to Visual Backbone: Query-modulated Refinement Networks for End-to-End Visual Grounding](https://mlsanity.com/paper/2203.15442/) (2022)
- [GeoGround: A Unified Large Vision-Language Model for Remote Sensing Visual Grounding](https://mlsanity.com/paper/2411.11904/) (2024)
- [RemoteSAM: Towards Segment Anything for Earth Observation](https://mlsanity.com/paper/2505.18022/) (2025)
- [Context Disentangling and Prototype Inheriting for Robust Visual Grounding](https://mlsanity.com/paper/2312.11967/) (2023)
- [An Efficient and Effective Transformer Decoder-Based Framework for Multi-Task Visual Grounding](https://mlsanity.com/paper/2408.01120/) (2024)

## Built on by (most cited first, 7 of 7)

- [RemoteAgent: Bridging Vague Human Intents and Earth Observation with RL-based Agentic MLLMs](https://mlsanity.com/paper/2604.07765/) (2026)
- [RemoteShield: Enable Robust Multimodal Large Language Models for Earth Observation](https://mlsanity.com/paper/2604.17243/) (2026)
- [RemoteZero: Geospatial Reasoning with Zero Labels](https://mlsanity.com/paper/2605.04451/) (2026)
- [WeaveEarth: Structured Evidence Construction and Reasoning for Training-Free UHR Remote Sensing Understanding](https://mlsanity.com/paper/2607.10120/) (2026)
- [Training-Free Open-Vocabulary Visual Grounding for Remote Sensing Images and Videos](https://mlsanity.com/paper/2606.16124/) (2026)
- [GeoSelect: Spatial-Program Execution for Training-Free Referring Remote Sensing Image Segmentation](https://mlsanity.com/paper/2607.03869/) (2026)
- [GrabVG: Graph-Attentive Binding for Visual Grounding in UAV Imagery](https://mlsanity.com/paper/2608.18996/) (2026)

## Abstract (arXiv)

Remote sensing visual grounding (RSVG) aims to localize objects in remote sensing imagery according to natural language expressions. Previous methods typically rely on sentence-level vision-language alignment, which struggles to exploit fine-grained linguistic cues, such as textitspatial relations and textitobject attributes, that are crucial for distinguishing objects with similar characteristics. Importantly, these cues play distinct roles across different grounding stages and should be leveraged accordingly to provide more explicit guidance. In this work, we propose ProVG, a novel RSVG framework that improves localization accuracy by decoupling language expressions into global context, spatial relations, and object attributes. To integrate these linguistic cues, ProVG employs a simple yet effective progressive cross-modal modulator, which dynamically modulates visual attention through a textitsurvey-locate-verify scheme, enabling coarse-to-fine vision-language alignment. In addition, ProVG incorporates a cross-scale fusion module to mitigate the large-scale variations in remote sensing imagery, along with a language-guided calibration decoder to refine cross-modal alignment during prediction. A unified multi-task head further enables ProVG to support both referring expression comprehension and segmentation tasks. Extensive experiments on two benchmarks, textiti.e., RRSIS-D and RISBench, demonstrate that ProVG consistently outperforms existing methods, achieving new state-of-the-art performance.