{"total":243,"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":"2102.12219","title":"Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges","created":"2021-02-24","cited_by_count":204,"area":null},{"id":"2211.15660","title":"SatlasPretrain: A Large-Scale Dataset for Remote Sensing Image Understanding","created":"2022-11-28","cited_by_count":167,"area":null},{"id":"2208.03987","title":"Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model","created":"2022-08-08","cited_by_count":149,"area":null},{"id":"2110.14378","title":"Towards artificial general intelligence via a multimodal foundation model","created":"2021-10-27","cited_by_count":112,"area":null},{"id":"2204.02825","title":"An Empirical Study of Remote Sensing Pretraining","created":"2022-04-06","cited_by_count":105,"area":null},{"id":"2304.06798","title":"On the Opportunities and Challenges of Foundation Models for Geospatial Artificial Intelligence","created":"2023-04-13","cited_by_count":88,"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":"2106.03917","title":"Mixture Outlier Exposure: Towards Out-of-Distribution Detection in Fine-grained Environments","created":"2021-06-07","cited_by_count":66,"area":null},{"id":"2209.01206","title":"Transformers in Remote Sensing: A Survey","created":"2022-09-02","cited_by_count":61,"area":null},{"id":"2104.07070","title":"Self-Supervised Learning of Remote Sensing Scene Representations Using Contrastive Multiview Coding","created":"2021-04-14","cited_by_count":58,"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":"2408.09110","title":"Locate Anything on Earth: Advancing Open-Vocabulary Object Detection for Remote Sensing Community","created":"2024-08-17","cited_by_count":50,"area":null},{"id":"2401.15855","title":"Cross-Scale MAE: A Tale of Multi-Scale Exploitation in Remote Sensing","created":"2024-01-29","cited_by_count":47,"area":null},{"id":"2403.11735","title":"LSKNet: A Foundation Lightweight Backbone for Remote Sensing","created":"2024-03-18","cited_by_count":44,"area":null},{"id":"2210.04936","title":"EarthNets: Empowering AI in Earth Observation","created":"2022-10-10","cited_by_count":40,"area":null},{"id":"2205.03147","title":"From Easy to Hard: Learning Language-guided Curriculum for Visual Question Answering on Remote Sensing Data","created":"2022-05-06","cited_by_count":39,"area":null},{"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":"2306.03900","title":"Model Spider: Learning to Rank Pre-Trained Models Efficiently","created":"2023-06-06","cited_by_count":32,"area":null},{"id":"2209.00727","title":"Enabling Country-Scale Land Cover Mapping with Meter-Resolution Satellite Imagery","created":"2022-09-01","cited_by_count":31,"area":null},{"id":"2112.10948","title":"Task-Oriented Image Transmission for Scene Classification in Unmanned Aerial Systems","created":"2021-12-21","cited_by_count":30,"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":"2202.07054","title":"Universal Adversarial Examples in Remote Sensing: Methodology and Benchmark","created":"2022-02-14","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":"2207.03860","title":"Consecutive Pretraining: A Knowledge Transfer Learning Strategy with Relevant Unlabeled Data for Remote Sensing Domain","created":"2022-07-08","cited_by_count":22,"area":null},{"id":"2308.16572","title":"CL-MAE: Curriculum-Learned Masked Autoencoders","created":"2023-08-31","cited_by_count":22,"area":null},{"id":"2408.01946","title":"Masked Angle-Aware Autoencoder for Remote Sensing Images","created":"2024-08-04","cited_by_count":22,"area":null},{"id":"2203.07845","title":"Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy","created":"2022-03-15","cited_by_count":21,"area":null},{"id":"2211.11812","title":"RIC-CNN: Rotation-Invariant Coordinate Convolutional Neural Network","created":"2022-11-21","cited_by_count":21,"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":"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":"2207.11166","title":"METER-ML: A Multi-Sensor Earth Observation Benchmark for Automated Methane Source Mapping","created":"2022-07-22","cited_by_count":18,"area":null},{"id":"2302.08046","title":"Continuous Remote Sensing Image Super-Resolution based on Context Interaction in Implicit Function Space","created":"2023-02-16","cited_by_count":18,"area":null},{"id":"2606.02572","title":"VISReg: Variance-Invariance-Sketching Regularization for JEPA training","created":"2026-06-01","cited_by_count":16,"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":"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":"2303.02460","title":"Extended Agriculture-Vision: An Extension of a Large Aerial Image Dataset for Agricultural Pattern Analysis","created":"2023-03-04","cited_by_count":14,"area":null},{"id":"2303.07035","title":"FireRisk: A Remote Sensing Dataset for Fire Risk Assessment with Benchmarks Using Supervised and Self-supervised Learning","created":"2023-03-13","cited_by_count":14,"area":null},{"id":"2304.09938","title":"LARD -- Landing Approach Runway Detection -- Dataset for Vision Based Landing","created":"2023-04-05","cited_by_count":14,"area":null},{"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":"2301.11387","title":"Universal Domain Adaptation for Remote Sensing Image Scene Classification","created":"2023-01-26","cited_by_count":13,"area":null},{"id":"2401.00897","title":"Masked Modeling for Self-supervised Representation Learning on Vision and Beyond","created":"2023-12-31","cited_by_count":13,"area":null},{"id":"2412.14428","title":"WildSAT: Learning Satellite Image Representations from Wildlife Observations","created":"2024-12-19","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":"2103.10368","title":"MSMatch: Semi-Supervised Multispectral Scene Classification with Few Labels","created":"2021-03-18","cited_by_count":12,"area":null},{"id":"2310.13120","title":"RSAdapter: Adapting Multimodal Models for Remote Sensing Visual Question Answering","created":"2023-10-19","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":"2605.12678","title":"No One Knows the State of the Art in Geospatial Foundation Models","created":"2026-05-12","cited_by_count":12,"area":null},{"id":"2305.15768","title":"High-Similarity-Pass Attention for Single Image Super-Resolution","created":"2023-05-25","cited_by_count":11,"area":null},{"id":"2404.17202","title":"Self-supervised visual learning in the low-data regime: a comparative evaluation","created":"2024-04-26","cited_by_count":11,"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":"2411.17984","title":"RS-vHeat: Heat Conduction Guided Efficient Remote Sensing Foundation Model","created":"2024-11-27","cited_by_count":11,"area":null},{"id":"2304.13009","title":"The Potential of Visual ChatGPT For Remote Sensing","created":"2023-04-25","cited_by_count":10,"area":null},{"id":"2501.10040","title":"LWGANet: Addressing Spatial and Channel Redundancy in Remote Sensing Visual Tasks with Light-Weight Grouped Attention","created":"2025-01-17","cited_by_count":10,"area":null},{"id":"2511.23332","title":"UniGeoSeg: Towards Unified Open-World Segmentation for Geospatial Scenes","created":"2025-11-28","cited_by_count":10,"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":"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":"2409.02146","title":"Brain-Inspired Online Adaptation for Remote Sensing with Spiking Neural Network","created":"2024-09-03","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":"2104.02846","title":"MultiScene: A Large-scale Dataset and Benchmark for Multi-scene Recognition in Single Aerial Images","created":"2021-04-07","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":"2301.05526","title":"Self-Training Guided Disentangled Adaptation for Cross-Domain Remote Sensing Image Semantic Segmentation","created":"2023-01-13","cited_by_count":7,"area":null},{"id":"2304.05104","title":"Approaching Test Time Augmentation in the Context of Uncertainty Calibration for Deep Neural Networks","created":"2023-04-11","cited_by_count":7,"area":null},{"id":"2501.12030","title":"Advancing Earth Observation: A Survey on AI-Powered Image Processing in Satellites","created":"2025-01-21","cited_by_count":7,"area":null},{"id":"2205.03371","title":"All Grains, One Scheme (AGOS): Learning Multi-grain Instance Representation for Aerial Scene Classification","created":"2022-05-06","cited_by_count":6,"area":null},{"id":"2211.08044","title":"Backdoor Attacks for Remote Sensing Data with Wavelet Transform","created":"2022-11-15","cited_by_count":6,"area":null},{"id":"2303.10232","title":"LSwinSR: UAV Imagery Super-Resolution based on Linear Swin Transformer","created":"2023-03-17","cited_by_count":6,"area":null},{"id":"2403.02059","title":"Multi-Spectral Remote Sensing Image Retrieval Using Geospatial Foundation Models","created":"2024-03-04","cited_by_count":6,"area":null},{"id":"2408.16265","title":"Low Saturation Confidence Distribution-based Test-Time Adaptation for Cross-Domain Remote Sensing Image Classification","created":"2024-08-29","cited_by_count":6,"area":null},{"id":"2503.04223","title":"Spiking Meets Attention: Efficient Remote Sensing Image Super-Resolution with Attention Spiking Neural Networks","created":"2025-03-06","cited_by_count":6,"area":null},{"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":"2106.07879","title":"A Lightweight ReLU-Based Feature Fusion for Aerial Scene Classification","created":"2021-06-15","cited_by_count":5,"area":null},{"id":"2107.11758","title":"Semantic Attention and Scale Complementary Network for Instance Segmentation in Remote Sensing Images","created":"2021-07-25","cited_by_count":5,"area":null},{"id":"2301.04494","title":"Multi-label Image Classification using Adaptive Graph Convolutional Networks: from a Single Domain to Multiple Domains","created":"2023-01-11","cited_by_count":5,"area":null},{"id":"2306.12111","title":"A Comprehensive Study on the Robustness of Image Classification and Object Detection in Remote Sensing: Surveying and Benchmarking","created":"2023-06-21","cited_by_count":5,"area":null},{"id":"2505.18051","title":"LookWhere? Efficient Visual Recognition by Learning Where to Look and What to See from Self-Supervision","created":"2025-05-23","cited_by_count":5,"area":null},{"id":"2506.09082","title":"AVA-Bench: Atomic Visual Ability Benchmark for Vision Foundation Models","created":"2025-06-10","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":"2104.00704","title":"Remote Sensing Image Classification with the SEN12MS Dataset","created":"2021-04-01","cited_by_count":4,"area":null},{"id":"2104.11200","title":"Aerial Scene Understanding in The Wild: Multi-Scene Recognition via Prototype-based Memory Networks","created":"2021-04-22","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":"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":"2302.13028","title":"A Light-weight Deep Learning Model for Remote Sensing Image Classification","created":"2023-02-25","cited_by_count":4,"area":null},{"id":"2309.09003","title":"RingMo-lite: A Remote Sensing Multi-task Lightweight Network with CNN-Transformer Hybrid Framework","created":"2023-09-16","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":"2403.13575","title":"Leveraging feature communication in federated learning for remote sensing image classification","created":"2024-03-20","cited_by_count":4,"area":null},{"id":"2408.08201","title":"Heavy Labels Out! Dataset Distillation with Label Space Lightening","created":"2024-08-15","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":"2507.14801","title":"Exploring Scalable Unified Modeling for General Low-Level Vision","created":"2025-07-20","cited_by_count":4,"area":null},{"id":"2512.23239","title":"RS-Prune: Training-Free Data Pruning at High Ratios for Efficient Remote Sensing Diffusion Foundation Models","created":"2025-12-29","cited_by_count":4,"area":null},{"id":"2112.05220","title":"Hidden Path Selection Network for Semantic Segmentation of Remote Sensing Images","created":"2021-12-09","cited_by_count":3,"area":null},{"id":"2211.02820","title":"A Robust and Low Complexity Deep Learning Model for Remote Sensing Image Classification","created":"2022-11-05","cited_by_count":3,"area":null},{"id":"2301.10611","title":"Discriminator-free Unsupervised Domain Adaptation for Multi-label Image Classification","created":"2023-01-25","cited_by_count":3,"area":null},{"id":"2305.00679","title":"Enhanced Multi-level Features for Very High Resolution Remote Sensing Scene Classification","created":"2023-05-01","cited_by_count":3,"area":null},{"id":"2402.02094","title":"Deep Semantic-Visual Alignment for Zero-Shot Remote Sensing Image Scene Classification","created":"2024-02-03","cited_by_count":3,"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":"2404.11706","title":"Pretraining Billion-scale Geospatial Foundational Models on Frontier","created":"2024-04-17","cited_by_count":3,"area":null}],"next_cursor":"100"}