{"total":181,"rows":[{"id":"2311.15826","title":"GeoChat: Grounded Large Vision-Language Model for Remote Sensing","created":"2023-11-24","cited_by_count":328,"area":"mllm"},{"id":"2303.11797","title":"CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation","created":"2023-03-21","cited_by_count":219,"area":null},{"id":"2401.16822","title":"EarthGPT: A Universal Multi-modal Large Language Model for Multi-sensor Image Comprehension in Remote Sensing Domain","created":"2024-01-30","cited_by_count":184,"area":"mllm"},{"id":"2311.00566","title":"CROMA: Remote Sensing Representations with Contrastive Radar-Optical Masked Autoencoders","created":"2023-11-01","cited_by_count":169,"area":null},{"id":"2406.10100","title":"SkySenseGPT: A Fine-Grained Instruction Tuning Dataset and Model for Remote Sensing Vision-Language Understanding","created":"2024-06-14","cited_by_count":104,"area":"mllm"},{"id":"2412.15190","title":"EarthDial: Turning Multi-sensory Earth Observations to Interactive Dialogues","created":"2024-12-19","cited_by_count":85,"area":"mllm"},{"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":"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":"2501.02341","title":"UAVs Meet LLMs: Overviews and Perspectives Toward Agentic Low-Altitude Mobility","created":"2025-01-04","cited_by_count":49,"area":"agents"},{"id":"2307.01909","title":"ClimateLearn: Benchmarking Machine Learning for Weather and Climate Modeling","created":"2023-07-04","cited_by_count":47,"area":null},{"id":"2505.23752","title":"ThinkGeo: Evaluating Tool-Augmented Agents for Remote Sensing Tasks","created":"2025-05-29","cited_by_count":46,"area":"lr"},{"id":"2501.06019","title":"BRIGHT: A globally distributed multimodal building damage assessment dataset with very-high-resolution for all-weather disaster response","created":"2025-01-10","cited_by_count":41,"area":null},{"id":"2202.12361","title":"RescueNet: A High Resolution UAV Semantic Segmentation Benchmark Dataset for Natural Disaster Damage Assessment","created":"2022-02-24","cited_by_count":40,"area":null},{"id":"2210.04936","title":"EarthNets: Empowering AI in Earth Observation","created":"2022-10-10","cited_by_count":40,"area":null},{"id":"2305.13608","title":"VDD: Varied Drone Dataset for Semantic Segmentation","created":"2023-05-23","cited_by_count":40,"area":null},{"id":"2406.09385","title":"Towards Vision-Language Geo-Foundation Model: A Survey","created":"2024-06-13","cited_by_count":36,"area":"mllm"},{"id":"2505.21089","title":"DisasterM3: A Remote Sensing Vision-Language Dataset for Disaster Damage Assessment and Response","created":"2025-05-27","cited_by_count":36,"area":"mllm"},{"id":"2405.04285","title":"On the Foundations of Earth and Climate Foundation Models","created":"2024-05-07","cited_by_count":33,"area":null},{"id":"2211.04324","title":"Machine Learning-Aided Operations and Communications of Unmanned Aerial Vehicles: A Contemporary Survey","created":"2022-11-07","cited_by_count":28,"area":null},{"id":"2310.16069","title":"CPSeg: Finer-grained Image Semantic Segmentation via Chain-of-Thought Language Prompting","created":"2023-10-24","cited_by_count":28,"area":"lr"},{"id":"2507.22412","title":"UAVScenes: A Multi-Modal Dataset for UAVs","created":"2025-07-30","cited_by_count":27,"area":null},{"id":"2201.04236","title":"Incidents1M: a large-scale dataset of images with natural disasters, damage, and incidents","created":"2022-01-11","cited_by_count":26,"area":null},{"id":"2506.06281","title":"TerraFM: A Scalable Foundation Model for Unified Multisensor Earth Observation","created":"2025-06-06","cited_by_count":25,"area":null},{"id":"2306.15521","title":"What a MESS: Multi-Domain Evaluation of Zero-Shot Semantic Segmentation","created":"2023-06-27","cited_by_count":24,"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":"2501.06932","title":"Harnessing Large Language Models for Disaster Management: A Survey","created":"2025-01-12","cited_by_count":20,"area":null},{"id":"2412.19492","title":"Towards Open-Vocabulary Remote Sensing Image Semantic Segmentation","created":"2024-12-27","cited_by_count":19,"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":"2505.14361","title":"Vision-Language Modeling Meets Remote Sensing: Models, Datasets and Perspectives","created":"2025-05-20","cited_by_count":18,"area":"mllm"},{"id":"2302.09899","title":"A Survey on Semi-Supervised Semantic Segmentation","created":"2023-02-20","cited_by_count":17,"area":null},{"id":"2311.12056","title":"Kuro Siwo: 33 billion $m^2$ under the water. A global multi-temporal satellite dataset for rapid flood mapping","created":"2023-11-18","cited_by_count":16,"area":null},{"id":"2106.10548","title":"VQA-Aid: Visual Question Answering for Post-Disaster Damage Assessment and Analysis","created":"2021-06-19","cited_by_count":15,"area":null},{"id":"2409.13366","title":"RingMo-Aerial: An Aerial Remote Sensing Foundation Model With Affine Transformation Contrastive Learning","created":"2024-09-20","cited_by_count":15,"area":null},{"id":"2602.17665","title":"OpenEarthAgent: A Unified Framework for Tool-Augmented Geospatial Agents","created":"2026-02-19","cited_by_count":15,"area":"lr"},{"id":"2509.01907","title":"RSCC: A Large-Scale Remote Sensing Change Caption Dataset for Disaster Events","created":"2025-09-02","cited_by_count":14,"area":null},{"id":"2312.06719","title":"SkyScenes: A Synthetic Dataset for Aerial Scene Understanding","created":"2023-12-11","cited_by_count":13,"area":null},{"id":"2411.19930","title":"On Domain-Adaptive Post-Training for Multimodal Large Language Models","created":"2024-11-29","cited_by_count":13,"area":"mllm"},{"id":"2505.02829","title":"LISAT: Language-Instructed Segmentation Assistant for Satellite Imagery","created":"2025-05-05","cited_by_count":13,"area":"mllm"},{"id":"2403.01909","title":"Semi-Supervised Semantic Segmentation Based on Pseudo-Labels: A Survey","created":"2024-03-04","cited_by_count":12,"area":null},{"id":"2404.04531","title":"Decomposition-based Unsupervised Domain Adaptation for Remote Sensing Image Semantic Segmentation","created":"2024-04-06","cited_by_count":12,"area":null},{"id":"2505.12108","title":"EarthSynth: Generating Informative Earth Observation with Diffusion Models","created":"2025-05-17","cited_by_count":12,"area":"diffusion"},{"id":"2406.04111","title":"UrbanSARFloods: Sentinel-1 SLC-Based Benchmark Dataset for Urban and Open-Area Flood Mapping","created":"2024-06-06","cited_by_count":11,"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":"2410.23278","title":"OpenSatMap: A Fine-grained High-resolution Satellite Dataset for Large-scale Map Construction","created":"2024-10-30","cited_by_count":11,"area":null},{"id":"2312.01882","title":"Unleashing the Potential of Large Language Model: Zero-shot VQA for Flood Disaster Scenario","created":"2023-12-04","cited_by_count":10,"area":null},{"id":"2406.12479","title":"RS-GPT4V: A Unified Multimodal Instruction-Following Dataset for Remote Sensing Image Understanding","created":"2024-06-18","cited_by_count":10,"area":"mllm"},{"id":"2512.20013","title":"SegEarth-R2: Towards Comprehensive Language-guided Segmentation for Remote Sensing Images","created":"2025-12-23","cited_by_count":10,"area":null},{"id":"2310.01164","title":"Segment Any Building","created":"2023-10-02","cited_by_count":9,"area":null},{"id":"2407.17673","title":"CRASAR-U-DROIDs: A Large Scale Benchmark Dataset for Building Alignment and Damage Assessment in Georectified sUAS Imagery","created":"2024-07-24","cited_by_count":9,"area":null},{"id":"2404.04608","title":"Panoptic Perception: A Novel Task and Fine-grained Dataset for Universal Remote Sensing Image Interpretation","created":"2024-04-06","cited_by_count":8,"area":null},{"id":"2507.12857","title":"SCORE: Scene Context Matters in Open-Vocabulary Remote Sensing Instance Segmentation","created":"2025-07-17","cited_by_count":8,"area":null},{"id":"2602.01990","title":"SAME: Stabilized Mixture-of-Experts for Multimodal Continual Instruction Tuning","created":"2026-02-02","cited_by_count":8,"area":"mllm"},{"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":"2301.06190","title":"BuildSeg: A General Framework for the Segmentation of Buildings","created":"2023-01-15","cited_by_count":6,"area":null},{"id":"2311.15776","title":"Stable Segment Anything Model","created":"2023-11-27","cited_by_count":6,"area":null},{"id":"2403.16677","title":"FOOL: Addressing the Downlink Bottleneck in Satellite Computing with Neural Feature Compression","created":"2024-03-25","cited_by_count":6,"area":null},{"id":"2601.01891","title":"Agentic AI in Remote Sensing: Foundations, Taxonomy, and Emerging Systems","created":"2026-01-05","cited_by_count":6,"area":"agents"},{"id":"2105.14540","title":"Attention Based Semantic Segmentation on UAV Dataset for Natural Disaster Damage Assessment","created":"2021-05-30","cited_by_count":5,"area":null},{"id":"2404.03574","title":"TinyVQA: Compact Multimodal Deep Neural Network for Visual Question Answering on Resource-Constrained Devices","created":"2024-04-04","cited_by_count":5,"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":"2412.11464","title":"High-Quality Mask Tuning Matters for Open-Vocabulary Segmentation","created":"2024-12-16","cited_by_count":5,"area":"mllm"},{"id":"2510.21391","title":"TerraGen: A Unified Multi-Task Layout Generation Framework for Remote Sensing Data Augmentation","created":"2025-10-24","cited_by_count":5,"area":null},{"id":"2512.20770","title":"OccuFly: A 3D Vision Benchmark for Semantic Scene Completion from the Aerial Perspective","created":"2025-12-23","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":"2603.14336","title":"UAVBench and UAVIT-1M: Benchmarking and Enhancing MLLMs for Low-Altitude UAV Vision-Language Understanding","created":"2026-03-15","cited_by_count":5,"area":"mllm"},{"id":"2212.10735","title":"NADBenchmarks -- a compilation of Benchmark Datasets for Machine Learning Tasks related to Natural Disasters","created":"2022-12-21","cited_by_count":4,"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":"2405.13779","title":"Robust Disaster Assessment from Aerial Imagery Using Text-to-Image Synthetic Data","created":"2024-05-22","cited_by_count":4,"area":null},{"id":"2503.19647","title":"Show or Tell? Effectively prompting Vision-Language Models for semantic segmentation","created":"2025-03-25","cited_by_count":4,"area":"mllm"},{"id":"2504.07394","title":"ClimateBench-M: A Multi-Modal Climate Data Benchmark with a Simple Generative Method","created":"2025-04-10","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":"2606.10819","title":"Earth-OneVision: Extending Remote Sensing Multimodal Large Language Models to More Sensor Modalities and Tasks","created":"2026-06-09","cited_by_count":4,"area":"lr"},{"id":"2205.15025","title":"An Efficient Modern Baseline for FloodNet VQA","created":"2022-05-30","cited_by_count":3,"area":null},{"id":"2401.15501","title":"FloodLense: A Framework for ChatGPT-based Real-time Flood Detection","created":"2024-01-27","cited_by_count":3,"area":null},{"id":"2405.00293","title":"MoPEFT: A Mixture-of-PEFTs for the Segment Anything Model","created":"2024-05-01","cited_by_count":3,"area":"moe"},{"id":"2405.06593","title":"Non-Uniform Spatial Alignment Errors in sUAS Imagery From Wide-Area Disasters","created":"2024-05-10","cited_by_count":3,"area":null},{"id":"2407.05007","title":"BlessemFlood21: Advancing Flood Analysis with a High-Resolution Georeferenced Dataset for Humanitarian Aid Support","created":"2024-07-06","cited_by_count":3,"area":null},{"id":"2407.05986","title":"KidSat: satellite imagery to map childhood poverty dataset and benchmark","created":"2024-07-08","cited_by_count":3,"area":null},{"id":"2410.13663","title":"DiRecNetV2: A Transformer-Enhanced Network for Aerial Disaster Recognition","created":"2024-10-17","cited_by_count":3,"area":null},{"id":"2501.04696","title":"Test-Time Optimization for Domain Adaptive Open Vocabulary Segmentation","created":"2025-01-08","cited_by_count":3,"area":null},{"id":"2502.13990","title":"Remote Sensing Semantic Segmentation Quality Assessment based on Vision Language Model","created":"2025-02-19","cited_by_count":3,"area":"mllm"},{"id":"2503.15816","title":"A Vision Centric Remote Sensing Benchmark","created":"2025-03-20","cited_by_count":3,"area":"mllm"},{"id":"2508.16016","title":"DRespNeT: A UAV Dataset and YOLOv8-DRN Model for Aerial Instance Segmentation of Building Access Points for Post-Earthquake Search-and-Rescue Missions","created":"2025-08-22","cited_by_count":3,"area":null},{"id":"2509.11097","title":"3DAeroRelief: The first 3D Benchmark UAV Dataset for Post-Disaster Assessment","created":"2025-09-14","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":"2602.13239","title":"CrisiSense-RAG: Crisis Sensing Multimodal Retrieval-Augmented Generation for Rapid Disaster Impact Assessment","created":"2026-01-30","cited_by_count":3,"area":"rag"},{"id":"2605.26110","title":"Prism: A Plug-in Reproducible Infrastructure for Scalable Multimodal Continual Instruction Tuning","created":"2026-05-25","cited_by_count":3,"area":"mllm"},{"id":"2105.08655","title":"Semi-Supervised Classification and Segmentation on High Resolution Aerial Images","created":"2021-05-16","cited_by_count":2,"area":null},{"id":"2209.10320","title":"Continual VQA for Disaster Response Systems","created":"2022-09-21","cited_by_count":2,"area":null},{"id":"2406.02780","title":"LADI v2: Multi-label Dataset and Classifiers for Low-Altitude Disaster Imagery","created":"2024-06-04","cited_by_count":2,"area":null},{"id":"2409.03245","title":"UAV (Unmanned Aerial Vehicles): Diverse Applications of UAV Datasets in Segmentation, Classification, Detection, and Tracking","created":"2024-09-05","cited_by_count":2,"area":null},{"id":"2411.15921","title":"A Tunable Despeckling Neural Network Stabilized via Diffusion Equation","created":"2024-11-24","cited_by_count":2,"area":null},{"id":"2502.20668","title":"OpenEarthSensing: Large-Scale Fine-Grained Benchmark for Open-World Remote Sensing","created":"2025-02-28","cited_by_count":2,"area":null},{"id":"2503.12843","title":"Towards Scalable Foundation Model for Multi-modal and Hyperspectral Geospatial Data","created":"2025-03-17","cited_by_count":2,"area":null},{"id":"2505.08117","title":"Now you see it, Now you don't: Damage Label Agreement in Drone & Satellite Post-Disaster Imagery","created":"2025-05-12","cited_by_count":2,"area":null},{"id":"2506.04281","title":"Uncovering Insights of Compound Flooding with Data-Driven AI","created":"2025-06-04","cited_by_count":2,"area":null},{"id":"2508.13086","title":"Checkmate: interpretable and explainable RSVQA is the endgame","created":"2025-08-18","cited_by_count":2,"area":null},{"id":"2509.17808","title":"Remote Sensing-Oriented World Model","created":"2025-09-22","cited_by_count":2,"area":"wm"},{"id":"2509.20628","title":"Recov-Vision: Linking Street View Imagery and Vision-Language Models for Post-Disaster Recovery","created":"2025-09-25","cited_by_count":2,"area":"mllm"}],"next_cursor":"100"}