{"total":92,"rows":[{"id":"2312.10115","title":"SkySense: A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation Imagery","created":"2023-12-15","cited_by_count":205,"area":null},{"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":"2306.03831","title":"GEO-Bench: Toward Foundation Models for Earth Monitoring","created":"2023-06-06","cited_by_count":124,"area":null},{"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":"2405.02771","title":"MMEarth: Exploring Multi-Modal Pretext Tasks For Geospatial Representation Learning","created":"2024-05-04","cited_by_count":77,"area":null},{"id":"2412.04204","title":"PANGAEA: A Global and Inclusive Benchmark for Geospatial Foundation Models","created":"2024-12-05","cited_by_count":68,"area":null},{"id":"2404.08351","title":"OmniSat: Self-Supervised Modality Fusion for Earth Observation","created":"2024-04-12","cited_by_count":63,"area":null},{"id":"2310.18653","title":"Feature Guided Masked Autoencoder for Self-supervised Learning in Remote Sensing","created":"2023-10-28","cited_by_count":48,"area":null},{"id":"2311.15153","title":"Predicting Gradient is Better: Exploring Self-Supervised Learning for SAR ATR with a Joint-Embedding Predictive Architecture","created":"2023-11-26","cited_by_count":46,"area":null},{"id":"2408.08447","title":"SpectralEarth: Training Hyperspectral Foundation Models at Scale","created":"2024-08-15","cited_by_count":42,"area":null},{"id":"2310.13336","title":"FLAIR: a Country-Scale Land Cover Semantic Segmentation Dataset From Multi-Source Optical Imagery","created":"2023-10-20","cited_by_count":41,"area":null},{"id":"2204.05381","title":"Self-supervised Vision Transformers for Joint SAR-optical Representation Learning","created":"2022-04-11","cited_by_count":40,"area":null},{"id":"2309.05300","title":"Decoupling Common and Unique Representations for Multimodal Self-supervised Learning","created":"2023-09-11","cited_by_count":36,"area":null},{"id":"2312.10114","title":"FoMo: Multi-Modal, Multi-Scale and Multi-Task Remote Sensing Foundation Models for Forest Monitoring","created":"2023-12-15","cited_by_count":31,"area":null},{"id":"2402.08565","title":"Artificial Intelligence for Literature Reviews: Opportunities and Challenges","created":"2024-02-13","cited_by_count":30,"area":null},{"id":"2405.20462","title":"Multi-Label Guided Soft Contrastive Learning for Efficient Earth Observation Pretraining","created":"2024-05-30","cited_by_count":28,"area":null},{"id":"2305.13456","title":"Revisiting pre-trained remote sensing model benchmarks: resizing and normalization matters","created":"2023-05-22","cited_by_count":27,"area":null},{"id":"2507.13812","title":"SkySense V2: A Unified Foundation Model for Multi-modal Remote Sensing","created":"2025-07-18","cited_by_count":26,"area":null},{"id":"2108.00688","title":"Self-supervised Audiovisual Representation Learning for Remote Sensing Data","created":"2021-08-02","cited_by_count":24,"area":null},{"id":"2211.08129","title":"Self-supervised remote sensing feature learning: Learning Paradigms, Challenges, and Future Works","created":"2022-11-15","cited_by_count":24,"area":null},{"id":"2205.02049","title":"Self-Supervised Learning for Invariant Representations from Multi-Spectral and SAR Images","created":"2022-05-04","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":"2506.01667","title":"EarthMind: Leveraging Cross-Sensor Data for Advanced Earth Observation Interpretation with a Unified Multimodal LLM","created":"2025-06-02","cited_by_count":18,"area":"mllm"},{"id":"2207.13975","title":"On the Effects of Different Types of Label Noise in Multi-Label Remote Sensing Image Classification","created":"2022-07-28","cited_by_count":17,"area":null},{"id":"2310.19231","title":"There Are No Data Like More Data- Datasets for Deep Learning in Earth Observation","created":"2023-10-30","cited_by_count":16,"area":null},{"id":"2311.00277","title":"OpenForest: A data catalogue for machine learning in forest monitoring","created":"2023-11-01","cited_by_count":15,"area":null},{"id":"2111.09451","title":"Benchmarking and scaling of deep learning models for land cover image classification","created":"2021-11-18","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":"2504.11172","title":"TerraMesh: A Planetary Mosaic of Multimodal Earth Observation Data","created":"2025-04-15","cited_by_count":14,"area":null},{"id":"2401.07782","title":"Exploring Masked Autoencoders for Sensor-Agnostic Image Retrieval in Remote Sensing","created":"2024-01-15","cited_by_count":12,"area":null},{"id":"2406.11933","title":"Harnessing Massive Satellite Imagery with Efficient Masked Image Modeling","created":"2024-06-17","cited_by_count":12,"area":null},{"id":"2406.08079","title":"A$^{2}$-MAE: A spatial-temporal-spectral unified remote sensing pre-training method based on anchor-aware masked autoencoder","created":"2024-06-12","cited_by_count":11,"area":null},{"id":"2410.19965","title":"OReole-FM: successes and challenges toward billion-parameter foundation models for high-resolution satellite imagery","created":"2024-10-25","cited_by_count":11,"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":"2202.11429","title":"A Novel Self-Supervised Cross-Modal Image Retrieval Method In Remote Sensing","created":"2022-02-23","cited_by_count":10,"area":null},{"id":"2311.06141","title":"Federated Learning Across Decentralized and Unshared Archives for Remote Sensing Image Classification","created":"2023-11-10","cited_by_count":10,"area":null},{"id":"2503.00168","title":"SSL4EO-S12 v1.1: A Multimodal, Multiseasonal Dataset for Pretraining, Updated","created":"2025-02-28","cited_by_count":9,"area":null},{"id":"2306.00792","title":"Learning Across Decentralized Multi-Modal Remote Sensing Archives with Federated Learning","created":"2023-06-01","cited_by_count":8,"area":null},{"id":"2507.09081","title":"From Physics to Foundation Models: A Review of AI-Driven Quantitative Remote Sensing Inversion","created":"2025-07-11","cited_by_count":8,"area":null},{"id":"2106.00506","title":"A Novel Graph-Theoretic Deep Representation Learning Method for Multi-Label Remote Sensing Image Retrieval","created":"2021-06-01","cited_by_count":7,"area":null},{"id":"2201.08789","title":"AiTLAS: Artificial Intelligence Toolbox for Earth Observation","created":"2022-01-21","cited_by_count":7,"area":null},{"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":"2401.02764","title":"Fus-MAE: A cross-attention-based data fusion approach for Masked Autoencoders in remote sensing","created":"2024-01-05","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":"2506.07080","title":"FLAIR-HUB: Large-scale Multimodal Dataset for Land Cover and Crop Mapping","created":"2025-06-08","cited_by_count":6,"area":null},{"id":"2212.01261","title":"Generative Reasoning Integrated Label Noise Robust Deep Image Representation Learning","created":"2022-12-02","cited_by_count":5,"area":null},{"id":"2301.01200","title":"Common Practices and Taxonomy in Deep Multi-view Fusion for Remote Sensing Applications","created":"2022-12-20","cited_by_count":5,"area":null},{"id":"2307.01741","title":"Ben-ge: Extending BigEarthNet with Geographical and Environmental Data","created":"2023-07-04","cited_by_count":5,"area":null},{"id":"2405.15405","title":"Transformer-based Federated Learning for Multi-Label Remote Sensing Image Classification","created":"2024-05-24","cited_by_count":5,"area":null},{"id":"2306.01523","title":"Transformer-based Multi-Modal Learning for Multi Label Remote Sensing Image Classification","created":"2023-06-02","cited_by_count":4,"area":null},{"id":"2504.03169","title":"REJEPA: A Novel Joint-Embedding Predictive Architecture for Efficient Remote Sensing Image Retrieval","created":"2025-04-04","cited_by_count":4,"area":null},{"id":"2511.02831","title":"GeoCrossBench: Cross-Band Generalization for Remote Sensing","created":"2025-11-04","cited_by_count":4,"area":null},{"id":"2406.18179","title":"DeepExtremeCubes: Integrating Earth system spatio-temporal data for impact assessment of climate extremes","created":"2024-06-26","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":"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":"2507.05916","title":"On the Effectiveness of Methods and Metrics for Explainable AI in Remote Sensing Image Scene Classification","created":"2025-07-08","cited_by_count":3,"area":null},{"id":"2507.07527","title":"MAPEX: Modality-Aware Pruning of Experts for Remote Sensing Foundation Models","created":"2025-07-10","cited_by_count":3,"area":null},{"id":"2509.14104","title":"CSMoE: An Efficient Remote Sensing Foundation Model with Soft Mixture-of-Experts","created":"2025-09-17","cited_by_count":3,"area":"moe"},{"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":"2512.17224","title":"Any-Optical-Model: A Universal Foundation Model for Optical Remote Sensing","created":"2025-12-19","cited_by_count":3,"area":null},{"id":"2504.16173","title":"FPGA-Based Neural Network Accelerators for Space Applications: A Survey","created":"2025-04-22","cited_by_count":2,"area":null},{"id":"2506.09327","title":"MSSDF: Modality-Shared Self-supervised Distillation for High-Resolution Multi-modal Remote Sensing Image Learning","created":"2025-06-11","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":"2606.20523","title":"SARLO-80: Worldwide Slant SAR Language Optic Dataset 80cm","created":"2026-06-18","cited_by_count":2,"area":null},{"id":"2208.10830","title":"Satellite Image Search in AgoraEO","created":"2022-08-23","cited_by_count":1,"area":null},{"id":"2209.05251","title":"Spotting Virus from Satellites: Modeling the Circulation of West Nile Virus Through Graph Neural Networks","created":"2022-09-07","cited_by_count":1,"area":null},{"id":"2306.15836","title":"A generic self-supervised learning (SSL) framework for representation learning from spectra-spatial feature of unlabeled remote sensing imagery","created":"2023-06-27","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":"2405.13451","title":"A Label Propagation Strategy for CutMix in Multi-Label Remote Sensing Image Classification","created":"2024-05-22","cited_by_count":1,"area":null},{"id":"2503.10262","title":"A Multi-Modal Federated Learning Framework for Remote Sensing Image Classification","created":"2025-03-13","cited_by_count":1,"area":null},{"id":"2507.00356","title":"CGEarthEye:A High-Resolution Remote Sensing Vision Foundation Model Based on the Jilin-1 Satellite Constellation","created":"2025-07-01","cited_by_count":1,"area":null},{"id":"2507.08683","title":"MoSAiC: Multi-Modal Multi-Label Supervision-Aware Contrastive Learning for Remote Sensing","created":"2025-07-11","cited_by_count":1,"area":null},{"id":"2508.06256","title":"FedX: Explanation-Guided Pruning for Communication-Efficient Federated Learning in Remote Sensing","created":"2025-08-08","cited_by_count":1,"area":null},{"id":"2602.12652","title":"CBEN -- A Multimodal Machine Learning Dataset for Cloud Robust Remote Sensing Image Understanding","created":"2026-02-13","cited_by_count":1,"area":null},{"id":"2603.26751","title":"Survey on Remote Sensing Scene Classification: From Traditional Methods to Large Generative AI Models","created":"2026-03-23","cited_by_count":1,"area":null},{"id":"2604.16952","title":"Better with Less: Tackling Heterogeneous Multi-Modal Image Joint Pretraining via Conditioned and Degraded Masked Autoencoder","created":"2026-04-18","cited_by_count":1,"area":null},{"id":"2606.12595","title":"Emerging Flexible Designs for Geospatial Multimodal Foundation Models","created":"2026-06-10","cited_by_count":1,"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":"2501.06720","title":"Multi-Label Scene Classification in Remote Sensing Benefits from Image Super-Resolution","created":"2025-01-12","cited_by_count":0,"area":null},{"id":"2501.11493","title":"Communication-Efficient Federated Learning Based on Explanation-Guided Pruning for Remote Sensing Image Classification","created":"2025-01-20","cited_by_count":0,"area":null},{"id":"2503.14109","title":"Operational Change Detection for Geographical Information: Overview and Challenges","created":"2025-03-18","cited_by_count":0,"area":null},{"id":"2505.17782","title":"Thalia: A Global, Multi-Modal Dataset for Volcanic Activity Monitoring","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2508.06966","title":"Can Multitask Learning Enhance Model Explainability?","created":"2025-08-09","cited_by_count":0,"area":null},{"id":"2510.08269","title":"Adaptive Gradient Calibration for Single-Positive Multi-Label Learning in Remote Sensing Image Scene Classification","created":"2025-10-09","cited_by_count":0,"area":null},{"id":"2511.11659","title":"DWFF-Net: A Multi-Scale Farmland System Habitat Identification Method with Adaptive Dynamic Weight Feature Fusion","created":"2025-11-11","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":"2601.02289","title":"Rank-based Geographical Regularization: Revisiting Contrastive Self-Supervised Learning for Multispectral Remote Sensing Imagery","created":"2026-01-05","cited_by_count":0,"area":null},{"id":"2605.06990","title":"TrajGANR: Trajectory-Centric Urban Multimodal Learning via Geospatially Aligned Neural Representations","created":"2026-05-07","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":"2606.00706","title":"CR-JEPA: Cross-Modal Joint-Embedding Predictive Learning for Remote Sensing Image Retrieval","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2610.05790","title":"FairRSFM: A Biome-Aware Benchmark and Debiasing Framework for Remote Sensing Foundation Models","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}