{"total":46,"rows":[{"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":"2501.00895","title":"Text2Earth: Unlocking Text-driven Remote Sensing Image Generation with a Global-Scale Dataset and a Foundation Model","created":"2025-01-01","cited_by_count":48,"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":"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":"2405.09365","title":"SARATR-X: Toward Building A Foundation Model for SAR Target Recognition","created":"2024-05-15","cited_by_count":25,"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":"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":"2509.21976","title":"Geo-R1: Improving Few-Shot Geospatial Referring Expression Understanding with Reinforcement Fine-Tuning","created":"2025-09-26","cited_by_count":20,"area":null},{"id":"2312.01191","title":"Bootstrapping Interactive Image-Text Alignment for Remote Sensing Image Captioning","created":"2023-12-02","cited_by_count":18,"area":null},{"id":"2309.06799","title":"When Geoscience Meets Foundation Models: Towards General Geoscience Artificial Intelligence System","created":"2023-09-13","cited_by_count":13,"area":null},{"id":"2309.08379","title":"PatFig: Generating Short and Long Captions for Patent Figures","created":"2023-09-15","cited_by_count":12,"area":null},{"id":"2603.00988","title":"Foundation Models in Remote Sensing: Evolving from Unimodality to Multimodality","created":"2026-03-01","cited_by_count":12,"area":null},{"id":"2412.19237","title":"SeaMo: A Season-Aware Multimodal Foundation Model for Remote Sensing","created":"2024-12-26","cited_by_count":11,"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":"2501.10736","title":"Semi-supervised Semantic Segmentation for Remote Sensing Images via Multi-scale Uncertainty Consistency and Cross-Teacher-Student Attention","created":"2025-01-18","cited_by_count":10,"area":null},{"id":"2409.03901","title":"Onboard Satellite Image Classification for Earth Observation: A Comparative Study of ViT Models","created":"2024-09-05","cited_by_count":8,"area":null},{"id":"2504.02866","title":"OpenFACADES: An Open Framework for Architectural Caption and Attribute Data Enrichment via Street View Imagery","created":"2025-04-01","cited_by_count":8,"area":null},{"id":"2311.15776","title":"Stable Segment Anything Model","created":"2023-11-27","cited_by_count":6,"area":null},{"id":"2312.12735","title":"MetaSegNet: Metadata-collaborative Vision-Language Representation Learning for Semantic Segmentation of Remote Sensing Images","created":"2023-12-20","cited_by_count":6,"area":null},{"id":"2411.07688","title":"ImageRAG: Enhancing Ultra High Resolution Remote Sensing Imagery Analysis with ImageRAG","created":"2024-11-12","cited_by_count":6,"area":null},{"id":"2402.16684","title":"Automated Floodwater Depth Estimation Using Large Multimodal Model for Rapid Flood Mapping","created":"2024-02-26","cited_by_count":4,"area":null},{"id":"2412.16631","title":"Deep Learning for Spatio-Temporal Fusion in Land Surface Temperature Estimation: A Comprehensive Survey, Experimental Analysis, and Future Trends","created":"2024-12-21","cited_by_count":4,"area":null},{"id":"2501.02474","title":"Generalization-Enhanced Few-Shot Object Detection in Remote Sensing","created":"2025-01-05","cited_by_count":4,"area":null},{"id":"2402.09066","title":"Solid Waste Detection, Monitoring and Mapping in Remote Sensing Images: A Survey","created":"2024-02-14","cited_by_count":3,"area":null},{"id":"2405.09922","title":"Cross-sensor self-supervised training and alignment for remote sensing","created":"2024-05-16","cited_by_count":3,"area":null},{"id":"2504.13365","title":"VLLFL: A Vision-Language Model Based Lightweight Federated Learning Framework for Smart Agriculture","created":"2025-04-17","cited_by_count":3,"area":null},{"id":"2506.06176","title":"SatelliteFormula: Multi-Modal Symbolic Regression from Remote Sensing Imagery for Physics Discovery","created":"2025-06-06","cited_by_count":3,"area":null},{"id":"2505.01558","title":"A Sensor Agnostic Domain Generalization Framework for Leveraging Geospatial Foundation Models: Enhancing Semantic Segmentation viaSynergistic Pseudo-Labeling and Generative Learning","created":"2025-05-02","cited_by_count":2,"area":null},{"id":"2505.15870","title":"Satellites Reveal Mobility: A Commuting Origin-destination Flow Generator for Global Cities","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2507.16228","title":"MONITRS: Multimodal Observations of Natural Incidents Through Remote Sensing","created":"2025-07-22","cited_by_count":2,"area":null},{"id":"2508.15930","title":"Semantic-Aware Ship Detection with Vision-Language Integration","created":"2025-08-21","cited_by_count":2,"area":null},{"id":"2601.07795","title":"Vision-Language Model for Accurate Crater Detection","created":"2026-01-12","cited_by_count":2,"area":null},{"id":"2603.06699","title":"Multi-label Instance-level Generalised Visual Grounding in Agriculture","created":"2026-03-05","cited_by_count":2,"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":"2408.00967","title":"Extracting Object Heights From LiDAR & Aerial Imagery","created":"2024-08-02","cited_by_count":0,"area":null},{"id":"2503.13814","title":"FusDreamer: Label-efficient Remote Sensing World Model for Multimodal Data Classification","created":"2025-03-18","cited_by_count":0,"area":null},{"id":"2510.24321","title":"Few-Shot Remote Sensing Image Scene Classification with CLIP and Prompt Learning","created":"2025-10-28","cited_by_count":0,"area":null},{"id":"2511.00269","title":"FedReplay: A Feature Replay Assisted Federated Transfer Learning Framework for Efficient and Privacy-Preserving Smart Agriculture","created":"2025-10-31","cited_by_count":0,"area":null},{"id":"2512.10596","title":"Beyond Pixels: A Training-Free, Text-to-Text Framework for Remote Sensing Image Retrieval","created":"2025-12-11","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":"2601.22809","title":"FarmMind: Reasoning-Query-Driven Dynamic Segmentation for Farmland Remote Sensing Images","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2603.04277","title":"VehAnchor: Metadata-Free Metric Scale Recovery from Vehicle Cues in Aerial Imagery","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2603.13437","title":"Vision-Language Based Expert Reporting for Painting Authentication and Defect Detection","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2608.24935","title":"A Lightweight Multimodal Vision-Language Framework for Early-Stage Anatomical Green Fruit Classification in Commercial Orchards","created":"2026-08-23","cited_by_count":0,"area":null},{"id":"2609.00628","title":"Restrict, Don't Retrain: Inference-Time VLM Guidance for Zero-Shot Aerial Segmentation","created":"2026-09-01","cited_by_count":0,"area":null}],"next_cursor":null}