{"list":"other","total":94,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2508.10104","title":"DINOv3","created":"2025-08-13","cited_by_count":1414},{"id":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322},{"id":"1803.05407","title":"Averaging Weights Leads to Wider Optima and Better Generalization","created":"2018-03-14","cited_by_count":1209},{"id":"2111.09886","title":"SimMIM: A Simple Framework for Masked Image Modeling","created":"2021-11-18","cited_by_count":1153},{"id":"2301.08243","title":"Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture","created":"2023-01-19","cited_by_count":1039},{"id":"2111.07832","title":"iBOT: Image BERT Pre-Training with Online Tokenizer","created":"2021-11-15","cited_by_count":903},{"id":"1904.00962","title":"Large Batch Optimization for Deep Learning: Training BERT in 76 minutes","created":"2019-04-01","cited_by_count":674},{"id":"2207.08051","title":"SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery","created":"2022-07-17","cited_by_count":408},{"id":"2212.14532","title":"Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning","created":"2022-12-30","cited_by_count":308},{"id":"2311.07113","title":"SpectralGPT: Spectral Remote Sensing Foundation Model","created":"2023-11-13","cited_by_count":252},{"id":"2103.16607","title":"Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing Data","created":"2021-03-30","cited_by_count":215},{"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},{"id":"2011.09980","title":"Geography-Aware Self-Supervised Learning","created":"2020-11-19","cited_by_count":190},{"id":"2311.00566","title":"CROMA: Remote Sensing Representations with Contrastive Radar-Optical Masked Autoencoders","created":"2023-11-01","cited_by_count":169},{"id":"2211.15660","title":"SatlasPretrain: A Large-Scale Dataset for Remote Sensing Image Understanding","created":"2022-11-28","cited_by_count":167},{"id":"2208.03987","title":"Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model","created":"2022-08-08","cited_by_count":149},{"id":"2310.18660","title":"Foundation Models for Generalist Geospatial Artificial Intelligence","created":"2023-10-28","cited_by_count":149},{"id":"2412.02732","title":"Prithvi-EO-2.0: A Versatile Multi-Temporal Foundation Model for Earth Observation Applications","created":"2024-12-03","cited_by_count":144},{"id":"2107.07933","title":"Panoptic Segmentation of Satellite Image Time Series with Convolutional Temporal Attention Networks","created":"2021-07-16","cited_by_count":143},{"id":"2401.08541","title":"Scalable Pre-training of Large Autoregressive Image Models","created":"2024-01-16","cited_by_count":115},{"id":"2302.04476","title":"Towards Geospatial Foundation Models via Continual Pretraining","created":"2023-02-09","cited_by_count":109},{"id":"2205.10287","title":"On the SDEs and Scaling Rules for Adaptive Gradient Algorithms","created":"2022-05-20","cited_by_count":104},{"id":"2403.15356","title":"Neural Plasticity-Inspired Multimodal Foundation Model for Earth Observation","created":"2024-03-22","cited_by_count":104},{"id":"2504.11171","title":"TerraMind: Large-Scale Generative Multimodality for Earth Observation","created":"2025-04-15","cited_by_count":104},{"id":"2304.14065","title":"Lightweight, Pre-trained Transformers for Remote Sensing Timeseries","created":"2023-04-27","cited_by_count":103},{"id":"2403.05419","title":"Rethinking Transformers Pre-training for Multi-Spectral Satellite Imagery","created":"2024-03-08","cited_by_count":83},{"id":"2402.01444","title":"Mission Critical -- Satellite Data is a Distinct Modality in Machine Learning","created":"2024-02-02","cited_by_count":77},{"id":"2405.02771","title":"MMEarth: Exploring Multi-Modal Pretext Tasks For Geospatial Representation Learning","created":"2024-05-04","cited_by_count":77},{"id":"2412.14123","title":"AnySat: One Earth Observation Model for Many Resolutions, Scales, and Modalities","created":"2024-12-18","cited_by_count":74},{"id":"2406.11519","title":"HyperSIGMA: Hyperspectral Intelligence Comprehension Foundation Model","created":"2024-06-17","cited_by_count":73},{"id":"2411.18704","title":"Exponential Moving Average of Weights in Deep Learning: Dynamics and Benefits","created":"2024-11-27","cited_by_count":71},{"id":"2403.13430","title":"MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining","created":"2024-03-20","cited_by_count":66},{"id":"2404.08351","title":"OmniSat: Self-Supervised Modality Fusion for Earth Observation","created":"2024-04-12","cited_by_count":63},{"id":"2304.05215","title":"A Billion-scale Foundation Model for Remote Sensing Images","created":"2023-04-11","cited_by_count":62},{"id":"2304.07213","title":"Very high resolution canopy height maps from RGB imagery using self-supervised vision transformer and convolutional decoder trained on Aerial Lidar","created":"2023-04-14","cited_by_count":60},{"id":"2301.04944","title":"ViTs for SITS: Vision Transformers for Satellite Image Time Series","created":"2023-01-12","cited_by_count":56},{"id":"2007.00586","title":"Lightweight Temporal Self-Attention for Classifying Satellite Image Time Series","created":"2020-07-01","cited_by_count":55},{"id":"2503.11849","title":"Towards a Unified Copernicus Foundation Model for Earth Vision","created":"2025-03-14","cited_by_count":53},{"id":"2405.15613","title":"Automatic Data Curation for Self-Supervised Learning: A Clustering-Based Approach","created":"2024-05-24","cited_by_count":50},{"id":"2112.07558","title":"Multi-Modal Temporal Attention Models for Crop Mapping from Satellite Time Series","created":"2021-12-14","cited_by_count":49},{"id":"2304.09670","title":"CMID: A Unified Self-Supervised Learning Framework for Remote Sensing Image Understanding","created":"2023-04-19","cited_by_count":48},{"id":"2310.18653","title":"Feature Guided Masked Autoencoder for Self-supervised Learning in Remote Sensing","created":"2023-10-28","cited_by_count":48},{"id":"2205.13137","title":"MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers","created":"2022-05-26","cited_by_count":47},{"id":"2401.15855","title":"Cross-Scale MAE: A Tale of Multi-Scale Exploitation in Remote Sensing","created":"2024-01-29","cited_by_count":47},{"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},{"id":"2404.01260","title":"Bridging Remote Sensors with Multisensor Geospatial Foundation Models","created":"2024-04-01","cited_by_count":46},{"id":"2502.09356","title":"Galileo: Learning Global & Local Features of Many Remote Sensing Modalities","created":"2025-02-13","cited_by_count":43},{"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},{"id":"2204.05381","title":"Self-supervised Vision Transformers for Joint SAR-optical Representation Learning","created":"2022-04-11","cited_by_count":40},{"id":"2309.05300","title":"Decoupling Common and Unique Representations for Multimodal Self-supervised Learning","created":"2023-09-11","cited_by_count":36},{"id":"2503.10845","title":"Panopticon: Advancing Any-Sensor Foundation Models for Earth Observation","created":"2025-03-13","cited_by_count":34},{"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},{"id":"2312.02199","title":"USat: A Unified Self-Supervised Encoder for Multi-Sensor Satellite Imagery","created":"2023-12-02","cited_by_count":28},{"id":"2405.20462","title":"Multi-Label Guided Soft Contrastive Learning for Efficient Earth Observation Pretraining","created":"2024-05-30","cited_by_count":28},{"id":"2507.13812","title":"SkySense V2: A Unified Foundation Model for Multi-modal Remote Sensing","created":"2025-07-18","cited_by_count":26},{"id":"2506.06281","title":"TerraFM: A Scalable Foundation Model for Unified Multisensor Earth Observation","created":"2025-06-06","cited_by_count":25},{"id":"2311.04442","title":"SS-MAE: Spatial-Spectral Masked Auto-Encoder for Multi-Source Remote Sensing Image Classification","created":"2023-11-08","cited_by_count":24},{"id":"2411.02796","title":"Specialized Foundation Models Struggle to Beat Supervised Baselines","created":"2024-11-05","cited_by_count":24},{"id":"2503.23844","title":"FlexiMo: A Flexible Remote Sensing Foundation Model","created":"2025-03-31","cited_by_count":24},{"id":"2405.14578","title":"Surge Phenomenon in Optimal Learning Rate and Batch Size Scaling","created":"2024-05-23","cited_by_count":22},{"id":"2408.01946","title":"Masked Angle-Aware Autoencoder for Remote Sensing Images","created":"2024-08-04","cited_by_count":22},{"id":"2412.01505","title":"Scaling Law for Language Models Training Considering Batch Size","created":"2024-12-02","cited_by_count":22},{"id":"2205.02049","title":"Self-Supervised Learning for Invariant Representations from Multi-Spectral and SAR Images","created":"2022-05-04","cited_by_count":20},{"id":"2303.06670","title":"Extending global-local view alignment for self-supervised learning with remote sensing imagery","created":"2023-03-12","cited_by_count":20},{"id":"2408.11000","title":"SenPa-MAE: Sensor Parameter Aware Masked Autoencoder for Multi-Satellite Self-Supervised Pretraining","created":"2024-08-20","cited_by_count":18},{"id":"2503.21841","title":"HyperFree: A Channel-adaptive and Tuning-free Foundation Model for Hyperspectral Remote Sensing Imagery","created":"2025-03-27","cited_by_count":17},{"id":"2407.09392","title":"Open-Canopy: Towards Very High Resolution Forest Monitoring","created":"2024-07-12","cited_by_count":16},{"id":"2504.03166","title":"RingMoE: Mixture-of-Modality-Experts Multi-Modal Foundation Models for Universal Remote Sensing Image Interpretation","created":"2025-04-04","cited_by_count":16},{"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},{"id":"2309.07207","title":"EarthPT: a time series foundation model for Earth Observation","created":"2023-09-13","cited_by_count":14},{"id":"2401.05093","title":"SwiMDiff: Scene-wide Matching Contrastive Learning with Diffusion Constraint for Remote Sensing Image","created":"2024-01-10","cited_by_count":14},{"id":"2412.14428","title":"WildSAT: Learning Satellite Image Representations from Wildlife Observations","created":"2024-12-19","cited_by_count":13},{"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},{"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},{"id":"2411.17984","title":"RS-vHeat: Heat Conduction Guided Efficient Remote Sensing Foundation Model","created":"2024-11-27","cited_by_count":11},{"id":"2501.08111","title":"EarthView: A Large Scale Remote Sensing Dataset for Self-Supervision","created":"2025-01-14","cited_by_count":11},{"id":"2503.10392","title":"RoMA: Scaling up Mamba-based Foundation Models for Remote Sensing","created":"2025-03-13","cited_by_count":11},{"id":"2211.12979","title":"FLAIR #1: semantic segmentation and domain adaptation dataset","created":"2022-11-23","cited_by_count":10},{"id":"2305.14467","title":"FLAIR #2: textural and temporal information for semantic segmentation from multi-source optical imagery","created":"2023-05-23","cited_by_count":9},{"id":"2411.17000","title":"SatVision-TOA: A Geospatial Foundation Model for Coarse-Resolution All-Sky Remote Sensing Imagery","created":"2024-11-26","cited_by_count":7},{"id":"2504.06962","title":"Efficient Self-Supervised Learning for Earth Observation via Dynamic Dataset Curation","created":"2025-04-09","cited_by_count":7},{"id":"2506.07080","title":"FLAIR-HUB: Large-scale Multimodal Dataset for Land Cover and Crop Mapping","created":"2025-06-08","cited_by_count":6},{"id":"2502.00435","title":"SatMamba: Development of Foundation Models for Remote Sensing Imagery Using State Space Models","created":"2025-02-01","cited_by_count":5},{"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},{"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},{"id":"2311.18082","title":"Zooming Out on Zooming In: Advancing Super-Resolution for Remote Sensing","created":"2023-11-29","cited_by_count":3},{"id":"1307.2434","title":"Major Limitations of Satellite images","created":"2013-07-09","cited_by_count":2}],"next_cursor":null}