{"total":97,"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":"2302.04476","title":"Towards Geospatial Foundation Models via Continual Pretraining","created":"2023-02-09","cited_by_count":109,"area":null},{"id":"2412.15190","title":"EarthDial: Turning Multi-sensory Earth Observations to Interactive Dialogues","created":"2024-12-19","cited_by_count":85,"area":"mllm"},{"id":"2111.08872","title":"TorchGeo: Deep Learning With Geospatial Data","created":"2021-11-17","cited_by_count":73,"area":null},{"id":"2411.19325","title":"GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Tasks","created":"2024-11-28","cited_by_count":51,"area":"mllm"},{"id":"2210.04936","title":"EarthNets: Empowering AI in Earth Observation","created":"2022-10-10","cited_by_count":40,"area":null},{"id":"2401.17600","title":"Good at captioning, bad at counting: Benchmarking GPT-4V on Earth observation data","created":"2024-01-31","cited_by_count":39,"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":"2204.04716","title":"TOV: The Original Vision Model for Optical Remote Sensing Image Understanding via Self-supervised Learning","created":"2022-04-10","cited_by_count":35,"area":null},{"id":"2303.07110","title":"Upcycling Models under Domain and Category Shift","created":"2023-03-13","cited_by_count":29,"area":null},{"id":"2408.14471","title":"A Practitioner's Guide to Continual Multimodal Pretraining","created":"2024-08-26","cited_by_count":23,"area":null},{"id":"2310.07730","title":"Domain-Controlled Prompt Learning","created":"2023-09-30","cited_by_count":22,"area":"mllm"},{"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":"2207.07189","title":"Current Trends in Deep Learning for Earth Observation: An Open-source Benchmark Arena for Image Classification","created":"2022-07-14","cited_by_count":18,"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":"2312.08878","title":"Domain Prompt Learning with Quaternion Networks","created":"2023-12-12","cited_by_count":17,"area":"mllm"},{"id":"2502.18495","title":"A Comprehensive Survey on Composed Image Retrieval","created":"2025-02-19","cited_by_count":17,"area":null},{"id":"2304.11619","title":"SATIN: A Multi-Task Metadataset for Classifying Satellite Imagery using Vision-Language Models","created":"2023-04-23","cited_by_count":15,"area":"mllm"},{"id":"2405.15587","title":"Composed Image Retrieval for Remote Sensing","created":"2024-05-24","cited_by_count":14,"area":null},{"id":"2403.01966","title":"Enhancing Information Maximization with Distance-Aware Contrastive Learning for Source-Free Cross-Domain Few-Shot Learning","created":"2024-03-04","cited_by_count":13,"area":null},{"id":"2509.20234","title":"ImageNet-trained CNNs are not biased towards texture: Revisiting feature reliance through controlled suppression","created":"2025-09-24","cited_by_count":13,"area":null},{"id":"2110.02580","title":"Deep Transfer Learning for Land Use and Land Cover Classification: A Comparative Study","created":"2021-10-06","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":"2408.04224","title":"Cross-View Meets Diffusion: Aerial Image Synthesis with Geometry and Text Guidance","created":"2024-08-08","cited_by_count":9,"area":null},{"id":"2201.01953","title":"Aerial Scene Parsing: From Tile-level Scene Classification to Pixel-wise Semantic Labeling","created":"2022-01-06","cited_by_count":8,"area":null},{"id":"2409.00698","title":"Enhancing Remote Sensing Vision-Language Models for Zero-Shot Scene Classification","created":"2024-09-01","cited_by_count":8,"area":"mllm"},{"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":"2505.23248","title":"Advancing Image Super-resolution Techniques in Remote Sensing: A Comprehensive Survey","created":"2025-05-29","cited_by_count":8,"area":null},{"id":"2201.08789","title":"AiTLAS: Artificial Intelligence Toolbox for Earth Observation","created":"2022-01-21","cited_by_count":7,"area":null},{"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":"2506.13723","title":"SOTA: Self-adaptive Optimal Transport for Zero-Shot Classification with Multiple Foundation Models","created":"2025-06-16","cited_by_count":6,"area":null},{"id":"2411.10070","title":"Step-wise Distribution Alignment Guided Style Prompt Tuning for Source-free Cross-domain Few-shot Learning","created":"2024-11-15","cited_by_count":5,"area":null},{"id":"2504.21487","title":"DGSolver: Diffusion Generalist Solver with Universal Posterior Sampling for Image Restoration","created":"2025-04-30","cited_by_count":5,"area":"diffusion"},{"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":"2104.00704","title":"Remote Sensing Image Classification with the SEN12MS Dataset","created":"2021-04-01","cited_by_count":4,"area":null},{"id":"2111.03690","title":"Do we still need ImageNet pre-training in remote sensing scene classification?","created":"2021-11-05","cited_by_count":4,"area":null},{"id":"2206.09386","title":"Scalable Neural Data Server: A Data Recommender for Transfer Learning","created":"2022-06-19","cited_by_count":4,"area":"moe"},{"id":"2302.01793","title":"Self-Supervised In-Domain Representation Learning for Remote Sensing Image Scene Classification","created":"2023-02-03","cited_by_count":4,"area":null},{"id":"2305.17520","title":"USIM-DAL: Uncertainty-aware Statistical Image Modeling-based Dense Active Learning for Super-resolution","created":"2023-05-27","cited_by_count":4,"area":null},{"id":"2503.11219","title":"MEET: A Million-Scale Dataset for Fine-Grained Geospatial Scene Classification with Zoom-Free Remote Sensing Imagery","created":"2025-03-14","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":"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":"2505.03299","title":"Towards Efficient Benchmarking of Foundation Models in Remote Sensing: A Capabilities Encoding Approach","created":"2025-05-06","cited_by_count":3,"area":null},{"id":"2201.05772","title":"Asymmetric Hash Code Learning for Remote Sensing Image Retrieval","created":"2022-01-15","cited_by_count":2,"area":null},{"id":"2405.08668","title":"Promoting AI Equity in Science: Generalized Domain Prompt Learning for Accessible VLM Research","created":"2024-05-14","cited_by_count":2,"area":"mllm"},{"id":"2409.17370","title":"The Overfocusing Bias of Convolutional Neural Networks: A Saliency-Guided Regularization Approach","created":"2024-09-25","cited_by_count":2,"area":null},{"id":"2503.01334","title":"Composed Multi-modal Retrieval: A Survey of Approaches and Applications","created":"2025-03-03","cited_by_count":2,"area":null},{"id":"2510.15615","title":"Deep Learning Based Domain Adaptation Methods in Remote Sensing: A Comprehensive Survey","created":"2025-10-17","cited_by_count":2,"area":null},{"id":"2102.13392","title":"Unifying Remote Sensing Image Retrieval and Classification with Robust Fine-tuning","created":"2021-02-26","cited_by_count":1,"area":null},{"id":"2112.03456","title":"RSBNet: One-Shot Neural Architecture Search for A Backbone Network in Remote Sensing Image Recognition","created":"2021-12-07","cited_by_count":1,"area":null},{"id":"2202.10693","title":"Universal adversarial perturbation for remote sensing images","created":"2022-02-22","cited_by_count":1,"area":null},{"id":"2303.05240","title":"Intriguing Property and Counterfactual Explanation of GAN for Remote Sensing Image Generation","created":"2023-03-09","cited_by_count":1,"area":null},{"id":"2303.16616","title":"Nearest Neighbor Based Out-of-Distribution Detection in Remote Sensing Scene Classification","created":"2023-03-29","cited_by_count":1,"area":null},{"id":"2402.09962","title":"ViGEO: an Assessment of Vision GNNs in Earth Observation","created":"2024-02-15","cited_by_count":1,"area":null},{"id":"2406.00348","title":"An Effective Weight Initialization Method for Deep Learning: Application to Satellite Image Classification","created":"2024-06-01","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":"2409.07582","title":"Minimizing Embedding Distortion for Robust Out-of-Distribution Performance","created":"2024-09-11","cited_by_count":1,"area":null},{"id":"2504.03700","title":"SAFE: Self-Adjustment Federated Learning Framework for Remote Sensing Collaborative Perception","created":"2025-03-25","cited_by_count":1,"area":null},{"id":"2508.03745","title":"Tobler's First Law in GeoAI: A Spatially Explicit Deep Learning Model for Terrain Feature Detection Under Weak Supervision","created":"2025-08-01","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":"2510.07135","title":"Few-Shot Adaptation Benchmark for Remote Sensing Vision-Language Models","created":"2025-10-08","cited_by_count":1,"area":"mllm"},{"id":"2510.22665","title":"SARVLM: A Vision Language Foundation Model for Semantic Understanding in SAR Imagery","created":"2025-10-26","cited_by_count":1,"area":"mllm"},{"id":"2511.10834","title":"EarthSight: A Distributed Framework for Low-Latency Satellite Intelligence","created":"2025-11-13","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":"2601.16419","title":"Learning Domain Knowledge in Multimodal Large Language Models through Reinforcement Fine-Tuning","created":"2026-01-23","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":"2605.07562","title":"Beyond GSD-as-Token: Continuous Scale Conditioning for Remote Sensing VLMs","created":"2026-05-08","cited_by_count":1,"area":"mllm"},{"id":"2607.29192","title":"Locally Consistent Transductive Information Maximization for Few-Shot Remote Sensing Scene Classification","created":"2026-07-31","cited_by_count":1,"area":null},{"id":"2107.05948","title":"Clustering-Based Representation Learning through Output Translation and Its Application to Remote--Sensing Images","created":"2021-07-13","cited_by_count":0,"area":null},{"id":"2209.12621","title":"Improving Image Clustering through Sample Ranking and Its Application to remote--sensing images","created":"2022-09-26","cited_by_count":0,"area":null},{"id":"2301.12541","title":"Supervised and Contrastive Self-Supervised In-Domain Representation Learning for Dense Prediction Problems in Remote Sensing","created":"2023-01-29","cited_by_count":0,"area":null},{"id":"2309.01050","title":"Efficient Curriculum based Continual Learning with Informative Subset Selection for Remote Sensing Scene Classification","created":"2023-09-03","cited_by_count":0,"area":null},{"id":"2401.02424","title":"Mapping of Land Use and Land Cover (LULC) using EuroSAT and Transfer Learning","created":"2023-11-06","cited_by_count":0,"area":null},{"id":"2402.02141","title":"Zero-shot sketch-based remote sensing image retrieval based on multi-level and attention-guided tokenization","created":"2024-02-03","cited_by_count":0,"area":null},{"id":"2402.16486","title":"Intelligent Known and Novel Aircraft Recognition -- A Shift from Classification to Similarity Learning for Combat Identification","created":"2024-02-26","cited_by_count":0,"area":null},{"id":"2406.16129","title":"UDHF2-Net: Uncertainty-diffusion-model-based High-Frequency TransFormer Network for Remotely Sensed Imagery Interpretation","created":"2024-06-23","cited_by_count":0,"area":null},{"id":"2409.03938","title":"Deep Clustering of Remote Sensing Scenes through Heterogeneous Transfer Learning","created":"2024-09-05","cited_by_count":0,"area":null},{"id":"2507.22576","title":"COOkeD: Ensemble-based OOD detection in the era of zero-shot CLIP","created":"2025-07-30","cited_by_count":0,"area":null},{"id":"2509.18693","title":"MVT: Mask-Grounded Vision-Language Models for Taxonomy-Aligned Land-Cover Tagging","created":"2025-09-23","cited_by_count":0,"area":"mllm"},{"id":"2512.02441","title":"Basis-Oriented Low-rank Transfer for Few-Shot and Test-Time Adaptation","created":"2025-12-02","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":"2512.17492","title":"MMLANDMARKS: a Cross-View Instance-Level Benchmark for Geo-Spatial Understanding","created":"2025-12-19","cited_by_count":0,"area":null},{"id":"2601.20526","title":"IOTA: Corrective Knowledge-Guided Prompt Learning via Black-White Box Framework","created":"2026-01-28","cited_by_count":0,"area":null},{"id":"2601.22195","title":"Multitask Learning for Earth Observation Data Classification with Hybrid Quantum Network","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2604.16518","title":"On-Orbit Space AI: Federated, Multi-Agent, and Collaborative Algorithms for Satellite Constellations","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2605.05344","title":"Open-SAT: LLM-Guided Query Embedding Refinement for Open-Vocabulary Object Retrieval in Satellite Imagery","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2605.14518","title":"ArcGate: Adaptive Arctangent Gated Activation","created":"2026-05-14","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":"2606.08126","title":"One Stone, Three Birds: Self-adaptive Optimal Transport for Multi-VLM Selection, Adaptation, and Ensembling","created":"2026-06-06","cited_by_count":0,"area":"mllm"},{"id":"2606.20702","title":"Beyond Templates: Revisiting Zero-Shot Remote Sensing through Meta-Prompting","created":"2026-06-15","cited_by_count":0,"area":"mllm"},{"id":"2607.13541","title":"When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2609.14690","title":"LIMODENet: Attention-Free Compact Encoders for Information-Preserving Onboard Satellite Image Restoration","created":"2026-09-13","cited_by_count":0,"area":null},{"id":"2609.37481","title":"Label Less, Learn More: Resource-Efficient Active Semi-Supervised Learning for Onboard Satellite Image Annotation","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2610.19013","title":"Data Density Scaling Laws for Image Self-Distillation","created":"2026-10-13","cited_by_count":0,"area":"distill"}],"next_cursor":null}