{"list":"other","total":70,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"1803.09010","title":"Datasheets for Datasets","created":"2018-03-23","cited_by_count":1386},{"id":"1807.10221","title":"Unified Perceptual Parsing for Scene Understanding","created":"2018-07-26","cited_by_count":1271},{"id":"2111.09886","title":"SimMIM: A Simple Framework for Masked Image Modeling","created":"2021-11-18","cited_by_count":1153},{"id":"1703.00121","title":"Remote Sensing Image Scene Classification: Benchmark and State of the Art","created":"2017-03-01","cited_by_count":797},{"id":"2104.10972","title":"ImageNet-21K Pretraining for the Masses","created":"2021-04-22","cited_by_count":613},{"id":"2112.09133","title":"Masked Feature Prediction for Self-Supervised Visual Pre-Training","created":"2021-12-16","cited_by_count":576},{"id":"2204.12484","title":"ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation","created":"2022-04-26","cited_by_count":456},{"id":"2207.08051","title":"SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery","created":"2022-07-17","cited_by_count":408},{"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":"1904.03626","title":"On The Power of Curriculum Learning in Training Deep Networks","created":"2019-04-07","cited_by_count":286},{"id":"2110.08733","title":"LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentation","created":"2021-10-17","cited_by_count":261},{"id":"2311.07113","title":"SpectralGPT: Spectral Remote Sensing Foundation Model","created":"2023-11-13","cited_by_count":252},{"id":"2108.05699","title":"Oriented R-CNN for Object Detection","created":"2021-08-12","cited_by_count":231},{"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":"1807.01232","title":"SpaceNet: A Remote Sensing Dataset and Challenge Series","created":"2018-07-03","cited_by_count":179},{"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":"2312.12856","title":"SkyScript: A Large and Semantically Diverse Vision-Language Dataset for Remote Sensing","created":"2023-12-20","cited_by_count":125},{"id":"2304.05750","title":"Segment Anything Is Not Always Perfect: An Investigation of SAM on Different Real-world Applications","created":"2023-04-12","cited_by_count":121},{"id":"2203.12719","title":"What to Hide from Your Students: Attention-Guided Masked Image Modeling","created":"2022-03-23","cited_by_count":118},{"id":"2202.10108","title":"ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyond","created":"2022-02-21","cited_by_count":117},{"id":"2106.05656","title":"MST: Masked Self-Supervised Transformer for Visual Representation","created":"2021-06-10","cited_by_count":114},{"id":"2206.10207","title":"SemMAE: Semantic-Guided Masking for Learning Masked Autoencoders","created":"2022-06-21","cited_by_count":114},{"id":"2302.04476","title":"Towards Geospatial Foundation Models via Continual Pretraining","created":"2023-02-09","cited_by_count":109},{"id":"2110.01931","title":"Anchor-free Oriented Proposal Generator for Object Detection","created":"2021-10-05","cited_by_count":105},{"id":"2204.02825","title":"An Empirical Study of Remote Sensing Pretraining","created":"2022-04-06","cited_by_count":105},{"id":"2105.11111","title":"Oriented RepPoints for Aerial Object Detection","created":"2021-05-24","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":"2105.07921","title":"BigEarthNet-MM: A Large Scale Multi-Modal Multi-Label Benchmark Archive for Remote Sensing Image Classification and Retrieval","created":"2021-05-17","cited_by_count":92},{"id":"2403.05419","title":"Rethinking Transformers Pre-training for Multi-Spectral Satellite Imagery","created":"2024-03-08","cited_by_count":83},{"id":"2201.13100","title":"Adversarial Masking for Self-Supervised Learning","created":"2022-01-31","cited_by_count":78},{"id":"2305.14344","title":"Siamese Masked Autoencoders","created":"2023-05-23","cited_by_count":76},{"id":"2005.01094","title":"Remote Sensing Image Scene Classification Meets Deep Learning: Challenges, Methods, Benchmarks, and Opportunities","created":"2020-05-03","cited_by_count":71},{"id":"2304.03283","title":"Diffusion Models as Masked Autoencoders","created":"2023-04-06","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":"2212.04246","title":"ViTPose++: Vision Transformer for Generic Body Pose Estimation","created":"2022-12-07","cited_by_count":65},{"id":"2304.05215","title":"A Billion-scale Foundation Model for Remote Sensing Images","created":"2023-04-11","cited_by_count":62},{"id":"2304.05919","title":"Hard Patches Mining for Masked Image Modeling","created":"2023-04-12","cited_by_count":57},{"id":"2306.09424","title":"SSL4EO-L: Datasets and Foundation Models for Landsat Imagery","created":"2023-06-15","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":"2401.15855","title":"Cross-Scale MAE: A Tale of Multi-Scale Exploitation in Remote Sensing","created":"2024-01-29","cited_by_count":47},{"id":"2303.15105","title":"Vision Transformer with Quadrangle Attention","created":"2023-03-27","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":"2303.05251","title":"Masked Image Modeling with Local Multi-Scale Reconstruction","created":"2023-03-09","cited_by_count":43},{"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":"2204.08227","title":"The Devil is in the Frequency: Geminated Gestalt Autoencoder for Self-Supervised Visual Pre-Training","created":"2022-04-18","cited_by_count":33},{"id":"2401.14391","title":"Rethinking Patch Dependence for Masked Autoencoders","created":"2024-01-25","cited_by_count":29},{"id":"2312.02199","title":"USat: A Unified Self-Supervised Encoder for Multi-Sensor Satellite Imagery","created":"2023-12-02","cited_by_count":28},{"id":"2206.00790","title":"Efficient Self-supervised Vision Pretraining with Local Masked Reconstruction","created":"2022-06-01","cited_by_count":27},{"id":"2401.04614","title":"Generic Knowledge Boosted Pre-training For Remote Sensing Images","created":"2024-01-09","cited_by_count":16},{"id":"2103.15813","title":"PixelTransformer: Sample Conditioned Signal Generation","created":"2021-03-29","cited_by_count":12},{"id":"2204.09931","title":"Learning to Purification for Unsupervised Person Re-identification","created":"2022-04-21","cited_by_count":11},{"id":"2303.08438","title":"Learning Accurate Template Matching with Differentiable Coarse-to-Fine Correspondence Refinement","created":"2023-03-15","cited_by_count":9},{"id":"2405.09789","title":"LeMeViT: Efficient Vision Transformer with Learnable Meta Tokens for Remote Sensing Image Interpretation","created":"2024-05-16","cited_by_count":9},{"id":"2403.08271","title":"Efficient Prompt Tuning of Large Vision-Language Model for Fine-Grained Ship Classification","created":"2024-03-13","cited_by_count":8},{"id":"2403.13241","title":"Tackling Noisy Labels with Network Parameter Additive Decomposition","created":"2024-03-20","cited_by_count":8},{"id":"2212.06593","title":"FastMIM: Expediting Masked Image Modeling Pre-training for Vision","created":"2022-12-13","cited_by_count":7},{"id":"2312.13714","title":"Bootstrap Masked Visual Modeling via Hard Patches Mining","created":"2023-12-21","cited_by_count":5},{"id":"2212.13693","title":"Parsing Objects at a Finer Granularity: A Survey","created":"2022-12-28","cited_by_count":2}],"next_cursor":null}