mlsanityData to 7 Oct 2026

EarthVQA: Towards Queryable Earth via Relational Reasoning-Based Remote Sensing Visual Question Answering

arXiv 2312.12222 ↗First posted 19 Dec 2023cs.CVcited by 51

Not on the map. Why?

Cited by 27 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Earth vision research typically focuses on extracting geospatial object locations and categories but neglects the exploration of relations between objects and comprehensive reasoning. Based on city planning needs, we develop a multi-modal multi-task VQA dataset (EarthVQA) to advance relational reasoning-based judging, counting, and comprehensive analysis. The EarthVQA dataset contains 6000 images, corresponding semantic masks, and 208,593 QA pairs with urban and rural governance requirements embedded. As objects are the basis for complex relational reasoning, we propose a Semantic OBject Awareness framework (SOBA) to advance VQA in an object-centric way. To preserve refined spatial locations and semantics, SOBA leverages a segmentation network for object semantics generation. The object-guided attention aggregates object interior features via pseudo masks, and bidirectional cross-attention further models object external relations hierarchically. To optimize object counting, we propose a numerical difference loss that dynamically adds difference penalties, unifying the classification and regression tasks. Experimental results show that SOBA outperforms both advanced general and remote sensing methods. We believe this dataset and framework provide a strong benchmark for Earth vision's complex analysis. The project page is at https://Junjue-Wang.github.io/homepage/EarthVQA.

Key facts. Cited by 51 papers in the map (data through 7 Oct 2026). Builds on 24 of its 41 references that are in the map. First posted on arXiv 19 Dec 2023.

Builds on

24 of 41 references.

References · 24

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2017Squeeze-and-Excitation Networkscited by 4,763
  6. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
  7. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,855
  8. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,646
  9. 2015VQA: Visual Question Answeringcited by 2,489
  10. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  11. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  12. 2019Panoptic Feature Pyramid Networkscited by 644
12 more
  1. 2016Training Region-based Object Detectors with Online Hard Example Miningcited by 577
  2. 2017CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learningcited by 459
  3. 2016AID: A Benchmark Dataset for Performance Evaluation of Aerial Scene Classificationcited by 343
  4. 2019Deep Modular Co-Attention Networks for Visual Question Answeringcited by 338
  5. 2018Bilinear Attention Networkscited by 277
  6. 2015Stacked Attention Networks for Image Question Answeringcited by 273
  7. 2021LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentationcited by 259
  8. 2020RSVQA: Visual Question Answering for Remote Sensing Datacited by 197
  9. 2018Compositional Attention Networks for Machine Reasoningcited by 183
  10. 2020FloodNet: A High Resolution Aerial Imagery Dataset for Post Flood Scene Understandingcited by 181
  11. 2020KRISP: Integrating Implicit and Symbolic Knowledge for Open-Domain Knowledge-Based VQAcited by 124
  12. 2018Recalibrating Fully Convolutional Networks with Spatial and Channel 'Squeeze & Excitation' Blockscited by 75

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 8; 2025: 16; 2026: 27.

51 papers.

Sort:

By area:

  1. 2024SkySenseGPT: A Fine-Grained Instruction Tuning Dataset and Model for Remote Sensing Vision-Language Understandingcited by 101
  2. 2024GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Taskscited by 50
  3. 2024Towards Vision-Language Geo-Foundation Model: A Surveycited by 36
  4. 2025When Large Vision-Language Model Meets Large Remote Sensing Imagery: Coarse-to-Fine Text-Guided Token Pruningcited by 35
  5. 2025DisasterM3: A Remote Sensing Vision-Language Dataset for Disaster Damage Assessment and Responsecited by 35
  6. 2024EarthMarker: A Visual Prompting Multi-modal Large Language Model for Remote Sensingcited by 29
  7. 2025A Survey of Multimodal Hallucination Evaluation and Detectioncited by 26
  8. 2024CHOICE: Benchmarking the Remote Sensing Capabilities of Large Vision-Language Modelscited by 19
  9. 2024Show Me What and Where has Changed? Question Answering and Grounding for Remote Sensing Change Detectioncited by 15
  10. 2025Towards LLM Agents for Earth Observationcited by 13
  11. 2025A Benchmark for Ultra-High-Resolution Remote Sensing MLLMscited by 11
  12. 2025SegEarth-R2: Towards Comprehensive Language-guided Segmentation for Remote Sensing Imagescited by 10
38 more
  1. 2025SensorQA: A Question Answering Benchmark for Daily-Life Monitoringcited by 7
  2. 2025DeltaVLM: Interactive Remote Sensing Image Change Analysis via Instruction-guided Difference Perceptioncited by 6
  3. 2025Asking like Socrates: Socrates helps VLMs understand remote sensing imagescited by 6
  4. 2026VLRS-Bench: A Vision-Language Reasoning Benchmark for Remote Sensingcited by 6
  5. 2026GeoMMBench and GeoMMAgent: Toward Expert-Level Multimodal Intelligence in Geoscience and Remote Sensingcited by 6
  6. 2024DDFAV: Remote Sensing Large Vision Language Models Dataset and Evaluation Benchmarkcited by 5
  7. 2025DescribeEarth: Describe Anything for Remote Sensing Imagescited by 5
  8. 2026EarthVL: A Progressive Earth Vision-Language Understanding and Generation Frameworkcited by 5
  9. 2025SatelliteFormula: Multi-Modal Symbolic Regression from Remote Sensing Imagery for Physics Discoverycited by 3
  10. 2026OmniEarth: A Benchmark for Evaluating Vision-Language Models in Geospatial Taskscited by 3
  11. 2026Earth-OneVision: Extending Remote Sensing Multimodal Large Language Models to More Sensor Modalities and Taskscited by 3
  12. 2025City-VLM: Towards Multidomain Perception Scene Understanding via Multimodal Incomplete Learningcited by 2
  13. 2026RemoteShield: Enable Robust Multimodal Large Language Models for Earth Observationcited by 2
  14. 2024Advancements in Visual Language Models for Remote Sensing: Datasets, Capabilities, and Enhancement Techniquescited by 1
  15. 2025MGCR-Net:Multimodal Graph-Conditioned Vision-Language Reconstruction Network for Remote Sensing Change Detectioncited by 1
  16. 2025Text-conditioned State Space Model For Domain-generalized Change Detection Visual Question Answeringcited by 1
  17. 2025Geo3DVQA: Evaluating Vision-Language Models for 3D Geospatial Reasoning from Aerial Imagerycited by 1
  18. 2026AirSpatialBot: A Spatially-Aware Aerial Agent for Fine-Grained Vehicle Attribute Recognization and Retrievalcited by 1
  19. 2026Reasoning with Pixel-level Precision: QVLM Architecture and SQuID Dataset for Quantitative Geospatial Analyticscited by 1
  20. 2026Vision-Language Model Purified Semi-Supervised Semantic Segmentation for Remote Sensing Imagescited by 1
  21. 2026SGMA: Semantic-Guided Modality-Aware Segmentation for Remote Sensing with Incomplete Multimodal Datacited by 1
  22. 2026UAV traffic scene understanding: A regulation embedded multi-modal network and a unified benchmarkcited by 1
  23. 2026NeSy-Route: A Neuro-Symbolic Benchmark for Constrained Route Planning in Remote Sensingcited by 1
  24. 2026Revisiting Change VQA in Remote Sensing with Structured and Native Multimodal Qwen Modelscited by 1
  25. 2026UAV as Urban Construction Change Monitor: A New Benchmark and Change Captioning Modelcited by 1
  26. 2026GeoX: Mastering Geospatial Reasoning Through Self-Play and Verifiable Rewardscited by 1
  27. 2025GeoGrid-Bench: Can Foundation Models Understand Multimodal Gridded Geo-Spatial Data?cited by 0
  28. 2026AgroOmni: A Large-Scale Multi-view Agricultural Dataset for Cross-Scale Multimodal Reasoningcited by 0
  29. 2026RS-HyRe-R1: A Hybrid Reward Mechanism to Overcome Perceptual Inertia for Remote Sensing Images Understandingcited by 0
  30. 2026ChangeQuery: Advancing Remote Sensing Change Analysis for Natural and Human-Induced Disasters from Visual Detection to Semantic Understandingcited by 0
  31. 2026From Clouds to Hallucinations: Atmospheric Retrieval Hijacking in Remote Sensing Vision-Language RAGcited by 0
  32. 2026LithoBench: Benchmarking Large Multimodal Models for Remote-Sensing Lithology Interpretationcited by 0
  33. 2026Beyond Appearance: Can Multimodal Large Language Models Exploit Vertical Structure for Remote Sensing Natural Scene Understanding?cited by 0
  34. 2026ForestHG-Trace: Traceable Long-Horizon Ecological Reasoning over Large-Scale Forest Scenescited by 0
  35. 2026AeroVerse-SatAgent: UAV-Satellite Collaborative Spatial Reasoning Inspired by the Dual Visual Pathway Theory of Cognitive Neurosciencecited by 0
  36. 2026RRS-10K: A Multitask Vision-Language Model Benchmark for Rare Remote Sensing Image Interpretationcited by 0
  37. 2026The Earth in One Gaze: Training-Free Active Focus for UHR Remote Sensing Understandingcited by 0
  38. 2026ReVA: A Scene-Centric Dataset Beyond Repetition for Remote Sensing Video Question Answeringcited by 0

50 most cited of 51 All 51 (JSON)