{"list":"other","total":65,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"id":"1709.00029","title":"EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification","created":"2017-08-31","cited_by_count":1496},{"id":"2102.08981","title":"Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts","created":"2021-02-17","cited_by_count":1216},{"id":"1703.00121","title":"Remote Sensing Image Scene Classification: Benchmark and State of the Art","created":"2017-03-01","cited_by_count":797},{"id":"1711.10398","title":"DOTA: A Large-scale Dataset for Object Detection in Aerial Images","created":"2017-11-28","cited_by_count":623},{"id":"1910.04867","title":"A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark","created":"2019-10-01","cited_by_count":425},{"id":"1608.05167","title":"AID: A Benchmark Dataset for Performance Evaluation of Aerial Scene Classification","created":"2016-08-18","cited_by_count":347},{"id":"1909.00133","title":"Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark","created":"2019-08-31","cited_by_count":340},{"id":"1711.07846","title":"Functional Map of the World","created":"2017-11-21","cited_by_count":338},{"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":"2103.16607","title":"Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing Data","created":"2021-03-30","cited_by_count":215},{"id":"2103.03098","title":"Accounting for Variance in Machine Learning Benchmarks","created":"2021-03-01","cited_by_count":201},{"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},{"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":"2103.05569","title":"FAIR1M: A Benchmark Dataset for Fine-grained Object Recognition in High-Resolution Remote Sensing Imagery","created":"2021-03-09","cited_by_count":143},{"id":"2507.22291","title":"AlphaEarth Foundations: An embedding field model for accurate and efficient global mapping from sparse label data","created":"2025-07-29","cited_by_count":137},{"id":"2107.07002","title":"The Benchmark Lottery","created":"2021-07-14","cited_by_count":136},{"id":"2306.03831","title":"GEO-Bench: Toward Foundation Models for Earth Monitoring","created":"2023-06-06","cited_by_count":124},{"id":"2302.04476","title":"Towards Geospatial Foundation Models via Continual Pretraining","created":"2023-02-09","cited_by_count":109},{"id":"1807.03341","title":"Troubling Trends in Machine Learning Scholarship","created":"2018-07-09","cited_by_count":108},{"id":"2403.15356","title":"Neural Plasticity-Inspired Multimodal Foundation Model for Earth Observation","created":"2024-03-22","cited_by_count":104},{"id":"2112.01716","title":"Reduced, Reused and Recycled: The Life of a Dataset in Machine Learning Research","created":"2021-12-03","cited_by_count":102},{"id":"1906.07789","title":"SEN12MS -- A Curated Dataset of Georeferenced Multi-Spectral Sentinel-1/2 Imagery for Deep Learning and Data Fusion","created":"2019-06-18","cited_by_count":95},{"id":"2412.15190","title":"EarthDial: Turning Multi-sensory Earth Observations to Interactive Dialogues","created":"2024-12-19","cited_by_count":85},{"id":"2211.07044","title":"SSL4EO-S12: A Large-Scale Multi-Modal, Multi-Temporal Dataset for Self-Supervised Learning in Earth Observation","created":"2022-11-13","cited_by_count":84},{"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":"2111.08872","title":"TorchGeo: Deep Learning With Geospatial Data","created":"2021-11-17","cited_by_count":73},{"id":"2203.04592","title":"Mapping global dynamics of benchmark creation and saturation in artificial intelligence","created":"2022-03-09","cited_by_count":71},{"id":"2410.16602","title":"Foundation Models for Remote Sensing and Earth Observation: A Survey","created":"2024-10-22","cited_by_count":70},{"id":"2412.04204","title":"PANGAEA: A Global and Inclusive Benchmark for Geospatial Foundation Models","created":"2024-12-05","cited_by_count":68},{"id":"2404.08351","title":"OmniSat: Self-Supervised Modality Fusion for Earth Observation","created":"2024-04-12","cited_by_count":63},{"id":"2501.17887","title":"Docling: An Efficient Open-Source Toolkit for AI-driven Document Conversion","created":"2025-01-27","cited_by_count":63},{"id":"2408.03464","title":"Vision Foundation Models in Remote Sensing: A Survey","created":"2024-08-06","cited_by_count":54},{"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":"2204.04716","title":"TOV: The Original Vision Model for Optical Remote Sensing Image Understanding via Self-supervised Learning","created":"2022-04-10","cited_by_count":35},{"id":"2503.10845","title":"Panopticon: Advancing Any-Sensor Foundation Models for Earth Observation","created":"2025-03-13","cited_by_count":34},{"id":"2402.12095","title":"Major TOM: Expandable Datasets for Earth Observation","created":"2024-02-19","cited_by_count":32},{"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":"2305.13456","title":"Revisiting pre-trained remote sensing model benchmarks: resizing and normalization matters","created":"2023-05-22","cited_by_count":27},{"id":"2401.04464","title":"PhilEO Bench: Evaluating Geo-Spatial Foundation Models","created":"2024-01-09","cited_by_count":25},{"id":"2503.20563","title":"TerraTorch: The Geospatial Foundation Models Toolkit","created":"2025-03-26","cited_by_count":25},{"id":"2506.06281","title":"TerraFM: A Scalable Foundation Model for Unified Multisensor Earth Observation","created":"2025-06-06","cited_by_count":25},{"id":"2511.13655","title":"OlmoEarth: Stable Latent Image Modeling for Multimodal Earth Observation","created":"2025-11-17","cited_by_count":24},{"id":"2408.01946","title":"Masked Angle-Aware Autoencoder for Remote Sensing Images","created":"2024-08-04","cited_by_count":22},{"id":"2511.15658","title":"GEO-Bench-2: From Performance to Capability, Rethinking Evaluation in Geospatial AI","created":"2025-11-19","cited_by_count":21},{"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},{"id":"2401.04614","title":"Generic Knowledge Boosted Pre-training For Remote Sensing Images","created":"2024-01-09","cited_by_count":16},{"id":"2406.11933","title":"Harnessing Massive Satellite Imagery with Efficient Masked Image Modeling","created":"2024-06-17","cited_by_count":12},{"id":"2503.07890","title":"Can Generative Geospatial Diffusion Models Excel as Discriminative Geospatial Foundation Models?","created":"2025-03-10","cited_by_count":10},{"id":"2310.00022","title":"CtxMIM: Context-Enhanced Masked Image Modeling for Remote Sensing Image Understanding","created":"2023-09-28","cited_by_count":9},{"id":"2406.18554","title":"Planted: a dataset for planted forest identification from multi-satellite time series","created":"2024-05-24","cited_by_count":9},{"id":"2604.21104","title":"Pretrain Where? Investigating How Pretraining Data Diversity Impacts Geospatial Foundation Model Performance","created":"2026-04-22","cited_by_count":1}],"next_cursor":null}