{"total":77,"rows":[{"id":"2306.11029","title":"RemoteCLIP: A Vision Language Foundation Model for Remote Sensing","created":"2023-06-19","cited_by_count":363,"area":"mllm"},{"id":"2307.15266","title":"RSGPT: A Remote Sensing Vision Language Model and Benchmark","created":"2023-07-28","cited_by_count":207,"area":"mllm"},{"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":"2306.11300","title":"RS5M and GeoRSCLIP: A Large Scale Vision-Language Dataset and A Large Vision-Language Model for Remote Sensing","created":"2023-06-20","cited_by_count":151,"area":"mllm"},{"id":"2402.02544","title":"LHRS-Bot: Empowering Remote Sensing with VGI-Enhanced Large Multimodal Language Model","created":"2024-02-04","cited_by_count":138,"area":"mllm"},{"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":"2401.09712","title":"SkyEyeGPT: Unifying Remote Sensing Vision-Language Tasks via Instruction Tuning with Large Language Model","created":"2024-01-18","cited_by_count":113,"area":"mllm"},{"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":"2305.05726","title":"Vision-Language Models in Remote Sensing: Current Progress and Future Trends","created":"2023-05-09","cited_by_count":93,"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":"2210.04936","title":"EarthNets: Empowering AI in Earth Observation","created":"2022-10-10","cited_by_count":40,"area":null},{"id":"2307.01003","title":"Visual Instruction Tuning with Polite Flamingo","created":"2023-07-03","cited_by_count":38,"area":"mllm"},{"id":"2406.09385","title":"Towards Vision-Language Geo-Foundation Model: A Survey","created":"2024-06-13","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":"2407.13596","title":"EarthMarker: A Visual Prompting Multi-modal Large Language Model for Remote Sensing","created":"2024-07-18","cited_by_count":29,"area":"mllm"},{"id":"2412.05679","title":"RSUniVLM: A Unified Vision Language Model for Remote Sensing via Granularity-oriented Mixture of Experts","created":"2024-12-07","cited_by_count":29,"area":"mllm"},{"id":"2503.11070","title":"Falcon: A Remote Sensing Vision-Language Foundation Model (Technical Report)","created":"2025-03-14","cited_by_count":28,"area":"mllm"},{"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":"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":"2504.03254","title":"SARLANG-1M: A Benchmark for Vision-Language Modeling in SAR Image Understanding","created":"2025-04-04","cited_by_count":16,"area":"mllm"},{"id":"2310.08276","title":"Direction-Oriented Visual-semantic Embedding Model for Remote Sensing Image-text Retrieval","created":"2023-10-12","cited_by_count":14,"area":null},{"id":"2405.15587","title":"Composed Image Retrieval for Remote Sensing","created":"2024-05-24","cited_by_count":14,"area":null},{"id":"2505.02829","title":"LISAT: Language-Instructed Segmentation Assistant for Satellite Imagery","created":"2025-05-05","cited_by_count":13,"area":"mllm"},{"id":"2209.06515","title":"Learning to Evaluate Performance of Multi-modal Semantic Localization","created":"2022-09-14","cited_by_count":12,"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":"2405.03373","title":"Knowledge-aware Text-Image Retrieval for Remote Sensing Images","created":"2024-05-06","cited_by_count":9,"area":null},{"id":"2503.15969","title":"Beyond the Visible: Multispectral Vision-Language Learning for Earth Observation","created":"2025-03-20","cited_by_count":8,"area":"mllm"},{"id":"2507.16716","title":"Enhancing Remote Sensing Vision-Language Models Through MLLM and LLM-Based High-Quality Image-Text Dataset Generation","created":"2025-07-22","cited_by_count":8,"area":"mllm"},{"id":"2408.14744","title":"RSTeller: Scaling Up Visual Language Modeling in Remote Sensing with Rich Linguistic Semantics from Openly Available Data and Large Language Models","created":"2024-08-27","cited_by_count":7,"area":"mllm"},{"id":"2502.09598","title":"GAIA: A Global, Multi-modal, Multi-scale Vision-Language Dataset for Remote Sensing Image Analysis","created":"2025-02-13","cited_by_count":7,"area":"mllm"},{"id":"2503.06312","title":"DOFA-CLIP: Multimodal Vision-Language Foundation Models for Earth Observation","created":"2025-03-08","cited_by_count":7,"area":"mllm"},{"id":"2512.02517","title":"SkyMoE: A Vision-Language Foundation Model for Enhancing Geospatial Interpretation with Mixture of Experts","created":"2025-12-02","cited_by_count":7,"area":"mllm"},{"id":"2212.05752","title":"Scale-Semantic Joint Decoupling Network for Image-text Retrieval in Remote Sensing","created":"2022-12-12","cited_by_count":6,"area":null},{"id":"2306.16950","title":"Alternative Telescopic Displacement: An Efficient Multimodal Alignment Method","created":"2023-06-29","cited_by_count":6,"area":null},{"id":"2601.17089","title":"GRASP: Guided Region-Aware Sparse Prompting for Adapting MLLMs to Remote Sensing","created":"2026-01-23","cited_by_count":6,"area":"mllm"},{"id":"2604.08896","title":"GeoMMBench and GeoMMAgent: Toward Expert-Level Multimodal Intelligence in Geoscience and Remote Sensing","created":"2026-04-10","cited_by_count":6,"area":"mllm"},{"id":"2305.01788","title":"Vision Meets Definitions: Unsupervised Visual Word Sense Disambiguation Incorporating Gloss Information","created":"2023-05-02","cited_by_count":5,"area":null},{"id":"2406.08866","title":"Zoom and Shift are All You Need","created":"2024-06-13","cited_by_count":5,"area":null},{"id":"2405.10160","title":"PriorCLIP: Visual Prior Guided Vision-Language Model for Remote Sensing Image-Text Retrieval","created":"2024-05-16","cited_by_count":4,"area":"mllm"},{"id":"2405.18959","title":"Transcending Fusion: A Multi-Scale Alignment Method for Remote Sensing Image-Text Retrieval","created":"2024-05-29","cited_by_count":4,"area":null},{"id":"2503.19311","title":"DGTRSD & DGTRS-CLIP: A Dual-Granularity Remote Sensing Image-Text Dataset and Vision Language Foundation Model for Alignment","created":"2025-03-25","cited_by_count":4,"area":"mllm"},{"id":"2501.19043","title":"Self-Supervised Cross-Modal Text-Image Time Series Retrieval in Remote Sensing","created":"2025-01-31","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":"2512.24022","title":"FUSE-RSVLM: Feature Fusion Vision-Language Model for Remote Sensing","created":"2025-12-30","cited_by_count":3,"area":"mllm"},{"id":"2411.14704","title":"Cross-Modal Pre-Aligned Method with Global and Local Information for Remote-Sensing Image and Text Retrieval","created":"2024-11-22","cited_by_count":2,"area":null},{"id":"2504.16433","title":"FrogDogNet: Fourier frequency Retained visual prompt Output Guidance for Domain Generalization of CLIP in Remote Sensing","created":"2025-04-23","cited_by_count":2,"area":"mllm"},{"id":"2506.21863","title":"Remote Sensing Large Vision-Language Model: Semantic-augmented Multi-level Alignment and Semantic-aware Expert Modeling","created":"2025-06-27","cited_by_count":2,"area":"mllm"},{"id":"2603.09566","title":"GeoAlignCLIP: Enhancing Fine-Grained Vision-Language Alignment in Remote Sensing via Multi-Granular Consistency Learning","created":"2026-03-10","cited_by_count":2,"area":"mllm"},{"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":"2403.10887","title":"LuoJiaHOG: A Hierarchy Oriented Geo-aware Image Caption Dataset for Remote Sensing Image-Text Retrival","created":"2024-03-16","cited_by_count":1,"area":null},{"id":"2409.07048","title":"Pushing the Limits of Vision-Language Models in Remote Sensing without Human Annotations","created":"2024-09-11","cited_by_count":1,"area":"mllm"},{"id":"2504.05644","title":"iEBAKER: Improved Remote Sensing Image-Text Retrieval Framework via Eliminate Before Align and Keyword Explicit Reasoning","created":"2025-04-08","cited_by_count":1,"area":null},{"id":"2505.11121","title":"Redundancy-Aware Pretraining of Vision-Language Foundation Models in Remote Sensing","created":"2025-05-16","cited_by_count":1,"area":"mllm"},{"id":"2505.16756","title":"Representation Discrepancy Bridging Method for Remote Sensing Image-Text Retrieval","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2505.22627","title":"Chain-of-Talkers (CoTalk): Fast Human Annotation of Dense Image Captions","created":"2025-05-28","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":"2510.10180","title":"TCMA: Text-Conditioned Multi-granularity Alignment for Drone Cross-Modal Text-Video Retrieval","created":"2025-10-11","cited_by_count":1,"area":null},{"id":"2511.14901","title":"FarSLIP: Discovering Effective CLIP Adaptation for Fine-Grained Remote Sensing Understanding","created":"2025-11-18","cited_by_count":1,"area":null},{"id":"2512.02505","title":"GeoDiT: A Diffusion-based Vision-Language Model for Geospatial Understanding","created":"2025-12-02","cited_by_count":1,"area":"mllm"},{"id":"2512.14102","title":"Neurosymbolic Inference On Foundation Models For Remote Sensing Text-to-image Retrieval With Complex Queries","created":"2025-12-16","cited_by_count":1,"area":"mllm"},{"id":"2603.12659","title":"AVION: Aerial Vision-Language Instruction from Offline Teacher to Prompt-Tuned Network","created":"2026-03-13","cited_by_count":1,"area":"mllm"},{"id":"2501.10638","title":"A Resource-Efficient Training Framework for Remote Sensing Text--Image Retrieval","created":"2025-01-18","cited_by_count":0,"area":null},{"id":"2505.00738","title":"XeMap: Contextual Referring in Large-Scale Remote Sensing Environments","created":"2025-04-30","cited_by_count":0,"area":null},{"id":"2507.08590","title":"Visual Semantic Description Generation with MLLMs for Image-Text Matching","created":"2025-07-11","cited_by_count":0,"area":null},{"id":"2507.10403","title":"CLOSP: A Unified Semantic Space for SAR, MSI, and Text in Remote Sensing","created":"2025-07-14","cited_by_count":0,"area":null},{"id":"2509.05374","title":"A Synthetic-to-Real Dehazing Method based on Domain Unification","created":"2025-09-04","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":"2512.11490","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":"2601.18190","title":"Multi-Perspective Subimage CLIP with Keyword Guidance for Remote Sensing Image-Text Retrieval","created":"2026-01-26","cited_by_count":0,"area":"mllm"},{"id":"2603.28134","title":"Robust Remote Sensing Image-Text Retrieval with Noisy Correspondence","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2605.03189","title":"Sentinel2Cap: A Human-Annotated Benchmark Dataset for Multimodal Remote Sensing Image Captioning","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2605.24442","title":"Benchmarking Composed Image Retrieval for Applied Earth Observation","created":"2026-05-23","cited_by_count":0,"area":null},{"id":"2607.06485","title":"AirflowAttack: Thermal-Airflow Adversarial Perturbations against Infrared Remote-Sensing Vision-Language Models","created":"2026-07-07","cited_by_count":0,"area":"mllm"},{"id":"2607.06552","title":"MonoIR-RS: Infrared Remote Sensing Vision-Language Learning with CLIP and VLM Adaptation","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2609.03391","title":"Exploring the Potential of Contrastive Language-Image Pre-training for Multi-Source Remote Sensing Data","created":"2026-09-03","cited_by_count":0,"area":null}],"next_cursor":null}