{"total":93,"rows":[{"id":"2210.12634","title":"RSVG: Exploring Data and Models for Visual Grounding on Remote Sensing Data","created":"2022-10-23","cited_by_count":123,"area":null},{"id":"2306.16623","title":"The Segment Anything Model (SAM) for Remote Sensing Applications: From Zero to One Shot","created":"2023-06-29","cited_by_count":83,"area":null},{"id":"2410.06234","title":"TEOChat: A Large Vision-Language Assistant for Temporal Earth Observation Data","created":"2024-10-08","cited_by_count":70,"area":null},{"id":"2405.09798","title":"Many-Shot In-Context Learning in Multimodal Foundation Models","created":"2024-05-16","cited_by_count":67,"area":null},{"id":"2306.08625","title":"RRSIS: Referring Remote Sensing Image Segmentation","created":"2023-06-14","cited_by_count":59,"area":null},{"id":"2312.12222","title":"EarthVQA: Towards Queryable Earth via Relational Reasoning-Based Remote Sensing Visual Question Answering","created":"2023-12-19","cited_by_count":52,"area":null},{"id":"2503.13436","title":"Unified Autoregressive Visual Generation and Understanding with Continuous Tokens","created":"2025-03-17","cited_by_count":51,"area":null},{"id":"2112.08359","title":"3D Question Answering","created":"2021-12-15","cited_by_count":41,"area":null},{"id":"2210.04936","title":"EarthNets: Empowering AI in Earth Observation","created":"2022-10-10","cited_by_count":40,"area":null},{"id":"2205.03147","title":"From Easy to Hard: Learning Language-guided Curriculum for Visual Question Answering on Remote Sensing Data","created":"2022-05-06","cited_by_count":39,"area":null},{"id":"2405.04285","title":"On the Foundations of Earth and Climate Foundation Models","created":"2024-05-07","cited_by_count":33,"area":null},{"id":"2208.04441","title":"Txt2Img-MHN: Remote Sensing Image Generation from Text Using Modern Hopfield Networks","created":"2022-08-08","cited_by_count":30,"area":null},{"id":"2402.06475","title":"Large Language Models for Captioning and Retrieving Remote Sensing Images","created":"2024-02-09","cited_by_count":30,"area":null},{"id":"2404.15500","title":"GeoLLM-Engine: A Realistic Environment for Building Geospatial Copilots","created":"2024-04-23","cited_by_count":30,"area":null},{"id":"2112.06343","title":"Change Detection Meets Visual Question Answering","created":"2021-12-12","cited_by_count":29,"area":null},{"id":"2202.09195","title":"A Review on Methods and Applications in Multimodal Deep Learning","created":"2022-02-18","cited_by_count":29,"area":null},{"id":"2305.08413","title":"Artificial intelligence to advance Earth observation: : A review of models, recent trends, and pathways forward","created":"2023-05-15","cited_by_count":28,"area":null},{"id":"2104.05107","title":"Towards a Collective Agenda on AI for Earth Science Data Analysis","created":"2021-04-11","cited_by_count":27,"area":null},{"id":"2105.11087","title":"Recent Advances and Trends in Multimodal Deep Learning: A Review","created":"2021-05-24","cited_by_count":26,"area":null},{"id":"2105.09392","title":"Geographic Question Answering: Challenges, Uniqueness, Classification, and Future Directions","created":"2021-05-19","cited_by_count":24,"area":null},{"id":"2308.12509","title":"Parameter-Efficient Transfer Learning for Remote Sensing Image-Text Retrieval","created":"2023-08-24","cited_by_count":24,"area":null},{"id":"2402.11325","title":"ChatEarthNet: A Global-Scale Image-Text Dataset Empowering Vision-Language Geo-Foundation Models","created":"2024-02-17","cited_by_count":24,"area":null},{"id":"2212.09360","title":"AI Security for Geoscience and Remote Sensing: Challenges and Future Trends","created":"2022-12-19","cited_by_count":23,"area":null},{"id":"2301.09460","title":"HRVQA: A Visual Question Answering Benchmark for High-Resolution Aerial Images","created":"2023-01-23","cited_by_count":21,"area":null},{"id":"2209.02700","title":"Language-aware Domain Generalization Network for Cross-Scene Hyperspectral Image Classification","created":"2022-09-06","cited_by_count":20,"area":null},{"id":"2507.20776","title":"RingMo-Agent: A Unified Remote Sensing Foundation Model for Multi-Platform and Multi-Modal Reasoning","created":"2025-07-28","cited_by_count":20,"area":null},{"id":"2503.22081","title":"A Survey on Remote Sensing Foundation Models: From Vision to Multimodality","created":"2025-03-28","cited_by_count":19,"area":null},{"id":"2410.23828","title":"Show Me What and Where has Changed? Question Answering and Grounding for Remote Sensing Change Detection","created":"2024-10-31","cited_by_count":15,"area":null},{"id":"2310.04698","title":"Tree-GPT: Modular Large Language Model Expert System for Forest Remote Sensing Image Understanding and Interactive Analysis","created":"2023-10-07","cited_by_count":14,"area":null},{"id":"2508.07307","title":"MCITlib: Multimodal Continual Instruction Tuning Library and Benchmark","created":"2025-08-10","cited_by_count":13,"area":null},{"id":"2310.13120","title":"RSAdapter: Adapting Multimodal Models for Remote Sensing Visual Question Answering","created":"2023-10-19","cited_by_count":12,"area":null},{"id":"2410.13384","title":"RescueADI: Adaptive Disaster Interpretation in Remote Sensing Images with Autonomous Agents","created":"2024-10-17","cited_by_count":11,"area":null},{"id":"2304.13009","title":"The Potential of Visual ChatGPT For Remote Sensing","created":"2023-04-25","cited_by_count":10,"area":null},{"id":"2306.00758","title":"LiT-4-RSVQA: Lightweight Transformer-based Visual Question Answering in Remote Sensing","created":"2023-06-01","cited_by_count":10,"area":null},{"id":"2307.15016","title":"How Good is Google Bard's Visual Understanding? An Empirical Study on Open Challenges","created":"2023-07-27","cited_by_count":9,"area":null},{"id":"2405.03373","title":"Knowledge-aware Text-Image Retrieval for Remote Sensing Images","created":"2024-05-06","cited_by_count":9,"area":null},{"id":"2509.17562","title":"Visual Instruction Pretraining for Domain-Specific Foundation Models","created":"2025-09-22","cited_by_count":9,"area":null},{"id":"2501.04974","title":"SensorQA: A Question Answering Benchmark for Daily-Life Monitoring","created":"2025-01-09","cited_by_count":8,"area":null},{"id":"2304.03844","title":"Multilingual Augmentation for Robust Visual Question Answering in Remote Sensing Images","created":"2023-04-07","cited_by_count":7,"area":null},{"id":"2407.08669","title":"Segmentation-guided Attention for Visual Question Answering from Remote Sensing Images","created":"2024-07-11","cited_by_count":7,"area":null},{"id":"2510.09201","title":"Multimodal Prompt Optimization: Why Not Leverage Multiple Modalities for MLLMs","created":"2025-10-10","cited_by_count":7,"area":null},{"id":"2109.11848","title":"How to find a good image-text embedding for remote sensing visual question answering?","created":"2021-09-24","cited_by_count":6,"area":null},{"id":"2411.00172","title":"SeafloorAI: A Large-scale Vision-Language Dataset for Seafloor Geological Survey","created":"2024-10-31","cited_by_count":6,"area":null},{"id":"2505.15401","title":"Visual Question Answering on Multiple Remote Sensing Image Modalities","created":"2025-05-21","cited_by_count":6,"area":null},{"id":"2507.10449","title":"CoralVQA: A Large-Scale Visual Question Answering Dataset for Coral Reef Image Understanding","created":"2025-07-14","cited_by_count":6,"area":null},{"id":"2411.15770","title":"Text-Guided Coarse-to-Fine Fusion Network for Robust Remote Sensing Visual Question Answering","created":"2024-11-24","cited_by_count":5,"area":null},{"id":"2601.02783","title":"EarthVL: A Progressive Earth Vision-Language Understanding and Generation Framework","created":"2026-01-06","cited_by_count":5,"area":null},{"id":"2602.00722","title":"Spectral Imbalance Causes Forgetting in Low-Rank Continual Adaptation","created":"2026-01-31","cited_by_count":5,"area":null},{"id":"2311.16782","title":"The curse of language biases in remote sensing VQA: the role of spatial attributes, language diversity, and the need for clear evaluation","created":"2023-11-28","cited_by_count":4,"area":null},{"id":"2506.00238","title":"ZeShot-VQA: Zero-Shot Visual Question Answering Framework with Answer Mapping for Natural Disaster Damage Assessment","created":"2025-05-30","cited_by_count":4,"area":null},{"id":"2408.02348","title":"Earth System Data Cubes: Avenues for advancing Earth system research","created":"2024-08-05","cited_by_count":3,"area":null},{"id":"2408.15642","title":"Can SAR improve RSVQA performance?","created":"2024-08-28","cited_by_count":3,"area":null},{"id":"2501.08131","title":"SAR Strikes Back: A New Hope for RSVQA","created":"2025-01-14","cited_by_count":3,"area":null},{"id":"2507.05731","title":"A Satellite-Ground Synergistic Large Vision-Language Model System for Earth Observation","created":"2025-07-08","cited_by_count":3,"area":null},{"id":"2507.12795","title":"City-VLM: Towards Multidomain Perception Scene Understanding via Multimodal Incomplete Learning","created":"2025-07-17","cited_by_count":3,"area":null},{"id":"2510.22964","title":"Survey of Multimodal Geospatial Foundation Models: Techniques, Applications, and Challenges","created":"2025-10-27","cited_by_count":3,"area":null},{"id":"2105.07141","title":"Show Why the Answer is Correct! Towards Explainable AI using Compositional Temporal Attention","created":"2021-05-15","cited_by_count":2,"area":null},{"id":"2306.14264","title":"Visual Question Answering in Remote Sensing with Cross-Attention and Multimodal Information Bottleneck","created":"2023-06-25","cited_by_count":2,"area":null},{"id":"2602.00117","title":"IC-EO: Interpretable Code-based assistant for Earth Observation","created":"2026-01-27","cited_by_count":2,"area":null},{"id":"2602.19217","title":"Questions beyond Pixels: Integrating Commonsense Knowledge in Visual Question Generation for Remote Sensing","created":"2026-02-22","cited_by_count":2,"area":null},{"id":"2603.16307","title":"NeSy-Route: A Neuro-Symbolic Benchmark for Constrained Route Planning in Remote Sensing","created":"2026-03-17","cited_by_count":2,"area":null},{"id":"2603.29630","title":"BigEarthNet.txt: A Large-Scale Multi-Sensor Image-Text Dataset and Benchmark for Earth Observation","created":"2026-03-31","cited_by_count":2,"area":null},{"id":"2306.00483","title":"Overcoming Language Bias in Remote Sensing Visual Question Answering via Adversarial Training","created":"2023-06-01","cited_by_count":1,"area":null},{"id":"2308.00541","title":"Detecting Cloud Presence in Satellite Images Using the RGB-based CLIP Vision-Language Model","created":"2023-08-01","cited_by_count":1,"area":null},{"id":"2310.19109","title":"Dynamic Task and Weight Prioritization Curriculum Learning for Multimodal Imagery","created":"2023-10-29","cited_by_count":1,"area":null},{"id":"2312.13848","title":"Reducing Hallucinations: Enhancing VQA for Flood Disaster Damage Assessment with Visual Contexts","created":"2023-12-21","cited_by_count":1,"area":null},{"id":"2508.06832","title":"Remote Sensing Image Intelligent Interpretation with the Language-Centered Perspective: Principles, Methods and Challenges","created":"2025-08-09","cited_by_count":1,"area":null},{"id":"2508.08974","title":"Text-conditioned State Space Model For Domain-generalized Change Detection Visual Question Answering","created":"2025-08-12","cited_by_count":1,"area":null},{"id":"2602.18845","title":"Echoes of ownership: Adversarial-guided dual injection for copyright protection in MLLMs","created":"2026-02-21","cited_by_count":1,"area":null},{"id":"2602.19224","title":"Knowledge-aware Visual Question Generation for Remote Sensing Images","created":"2026-02-22","cited_by_count":1,"area":null},{"id":"2603.01758","title":"Unifying Heterogeneous Multi-Modal Remote Sensing Detection Via Language-Pivoted Pretraining","created":"2026-03-02","cited_by_count":1,"area":null},{"id":"2603.10722","title":"UAV traffic scene understanding: A regulation embedded multi-modal network and a unified benchmark","created":"2026-03-11","cited_by_count":1,"area":null},{"id":"2604.18429","title":"Revisiting Change VQA in Remote Sensing with Structured and Native Multimodal Qwen Models","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2605.04409","title":"UAV as Urban Construction Change Monitor: A New Benchmark and Change Captioning Model","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2412.02575","title":"Copy-Move Forgery Detection and Question Answering for Remote Sensing Image","created":"2024-12-03","cited_by_count":0,"area":null},{"id":"2506.22501","title":"How Can Multimodal Remote Sensing Datasets Transform Classification via SpatialNet-ViT?","created":"2025-06-25","cited_by_count":0,"area":null},{"id":"2509.18177","title":"A Framework for Generating Artificial Datasets to Validate Absolute and Relative Position Concepts","created":"2025-09-17","cited_by_count":0,"area":null},{"id":"2512.11490","title":"VLM2GeoVec: Toward Universal Multimodal Embeddings for Remote Sensing","created":"2025-12-12","cited_by_count":0,"area":null},{"id":"2512.15531","title":"An Efficient and Effective Encoder Model for Vision and Language Tasks in the Remote Sensing Domain","created":"2025-12-17","cited_by_count":0,"area":null},{"id":"2601.12076","title":"CroBIM-V: Memory-Quality Controlled Remote Sensing Referring Video Object Segmentation","created":"2026-01-17","cited_by_count":0,"area":null},{"id":"2602.19146","title":"VIGiA: Instructional Video Guidance via Dialogue Reasoning and Retrieval","created":"2026-02-22","cited_by_count":0,"area":null},{"id":"2605.10772","title":"Towards a Large Language-Vision Question Answering Model for MSTAR Automatic Target Recognition","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.12542","title":"Earth Science Foundation Models: From Perception to Reasoning and Discovery","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.14475","title":"GeoVista: Visually Grounded Active Perception for Vision-Language Understanding of Ultra-High-Resolution Remote Sensing Images","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2606.02747","title":"Plan2Map: A Multimodal Benchmark for Document-Grounded Geospatial Boundary Reconstruction from Planning Records","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.19277","title":"A Unified Framework for Efficient Remote Sensing Visual Question Answering: Adapting Dual, Hybrid, and Encoder-Decoder Architectures","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2608.06959","title":"Summarize First, Download Later: Onboard VLMs for Bandwidth-Efficient Earth Observation","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.15456","title":"AlignJEPA: Predictive Vision-Language Alignment for Remote Sensing Foundation Models","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2609.18210","title":"Understanding Dynamic Scenes at Gigapixel Scale: Wide-Area Spatio-Temporal Perception from UAVs","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.29541","title":"GeoRefer-Bench: A Benchmark from Referring Pixels to Verifiable Geospatial Reasoning","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2610.13535","title":"Knowing Whether, Not Just Where: Anchor-Probing Distillation for Open-Set Remote Sensing Visual Grounding","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.13636","title":"Benchmarking Answer-Grounding Consistency in Remote Sensing Visual Question Answering","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.18323","title":"Omni-RS: Unifying Multi-Task Understanding and Generation in Remote Sensing","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}