{"list":"other","total":115,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"2003.04297","title":"Improved Baselines with Momentum Contrastive Learning","created":"2020-03-09","cited_by_count":2287},{"id":"2108.10257","title":"SwinIR: Image Restoration Using Swin Transformer","created":"2021-08-23","cited_by_count":1887},{"id":"1703.06211","title":"Deformable Convolutional Networks","created":"2017-03-17","cited_by_count":1488},{"id":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228},{"id":"1609.05158","title":"Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network","created":"2016-09-16","cited_by_count":1204},{"id":"2111.09886","title":"SimMIM: A Simple Framework for Masked Image Modeling","created":"2021-11-18","cited_by_count":1153},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"1611.01236","title":"Adversarial Machine Learning at Scale","created":"2016-11-04","cited_by_count":936},{"id":"2106.05974","title":"Scaling Vision with Sparse Mixture of Experts","created":"2021-06-10","cited_by_count":747},{"id":"2203.16527","title":"Exploring Plain Vision Transformer Backbones for Object Detection","created":"2022-03-30","cited_by_count":724},{"id":"1711.10398","title":"DOTA: A Large-scale Dataset for Object Detection in Aerial Images","created":"2017-11-28","cited_by_count":623},{"id":"2211.05778","title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","created":"2022-11-10","cited_by_count":482},{"id":"2207.08051","title":"SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery","created":"2022-07-17","cited_by_count":408},{"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":"2311.15826","title":"GeoChat: Grounded Large Vision-Language Model for Remote Sensing","created":"2023-11-24","cited_by_count":328},{"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":"1810.08462","title":"Fully Convolutional Siamese Networks for Change Detection","created":"2018-10-19","cited_by_count":306},{"id":"2103.00208","title":"Remote Sensing Image Change Detection with Transformers","created":"2021-02-27","cited_by_count":306},{"id":"2201.00520","title":"Vision Transformer with Deformable Attention","created":"2022-01-03","cited_by_count":295},{"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":"2201.01293","title":"A Transformer-Based Siamese Network for Change Detection","created":"2022-01-04","cited_by_count":244},{"id":"1902.06148","title":"BigEarthNet: A Large-Scale Benchmark Archive For Remote Sensing Image Understanding","created":"2019-02-16","cited_by_count":234},{"id":"2106.03348","title":"ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias","created":"2021-06-07","cited_by_count":216},{"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":"2102.12219","title":"Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges","created":"2021-02-24","cited_by_count":204},{"id":"1905.12886","title":"iSAID: A Large-scale Dataset for Instance Segmentation in Aerial Images","created":"2019-05-30","cited_by_count":197},{"id":"2011.09980","title":"Geography-Aware Self-Supervised Learning","created":"2020-11-19","cited_by_count":190},{"id":"2309.16020","title":"GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localization","created":"2023-09-27","cited_by_count":187},{"id":"2107.02988","title":"SpectralFormer: Rethinking Hyperspectral Image Classification with Transformers","created":"2021-07-07","cited_by_count":169},{"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":"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":"2404.03425","title":"ChangeMamba: Remote Sensing Change Detection With Spatiotemporal State Space Model","created":"2024-04-04","cited_by_count":120},{"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":"2110.14378","title":"Towards artificial general intelligence via a multimodal foundation model","created":"2021-10-27","cited_by_count":112},{"id":"1810.08468","title":"Urban Change Detection for Multispectral Earth Observation Using Convolutional Neural Networks","created":"2018-10-19","cited_by_count":110},{"id":"2302.04476","title":"Towards Geospatial Foundation Models via Continual Pretraining","created":"2023-02-09","cited_by_count":109},{"id":"2204.02825","title":"An Empirical Study of Remote Sensing Pretraining","created":"2022-04-06","cited_by_count":105},{"id":"1902.06701","title":"HybridSN: Exploring 3D-2D CNN Feature Hierarchy for Hyperspectral Image Classification","created":"2019-02-18","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":"2306.13653","title":"ProRes: Exploring Degradation-aware Visual Prompt for Universal Image Restoration","created":"2023-06-23","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":"2403.13430","title":"MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining","created":"2024-03-20","cited_by_count":66},{"id":"2304.05215","title":"A Billion-scale Foundation Model for Remote Sensing Images","created":"2023-04-11","cited_by_count":62},{"id":"2112.01715","title":"Self-Supervised Material and Texture Representation Learning for Remote Sensing Tasks","created":"2021-12-03","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":"2005.08752","title":"Learning Spatial-Spectral Prior for Super-Resolution of Hyperspectral Imagery","created":"2020-05-18","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":"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":"2003.04547","title":"3D Quasi-Recurrent Neural Network for Hyperspectral Image Denoising","created":"2020-03-10","cited_by_count":44},{"id":"2204.08446","title":"VSA: Learning Varied-Size Window Attention in Vision Transformers","created":"2022-04-18","cited_by_count":43},{"id":"1812.04243","title":"Non-local Meets Global: An Integrated Paradigm for Hyperspectral Denoising","created":"2018-12-11","cited_by_count":39},{"id":"1905.01662","title":"GETNET: A General End-to-end Two-dimensional CNN Framework for Hyperspectral Image Change Detection","created":"2019-05-05","cited_by_count":37},{"id":"2404.08489","title":"SpectralMamba: Efficient Mamba for Hyperspectral Image Classification","created":"2024-04-12","cited_by_count":36},{"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":"2211.14090","title":"Spatial-Spectral Transformer for Hyperspectral Image Denoising","created":"2022-11-25","cited_by_count":34},{"id":"2303.06682","title":"DDS2M: Self-Supervised Denoising Diffusion Spatio-Spectral Model for Hyperspectral Image Restoration","created":"2023-03-12","cited_by_count":33},{"id":"1902.10858","title":"Cascaded Recurrent Neural Networks for Hyperspectral Image Classification","created":"2019-02-28","cited_by_count":31},{"id":"2404.09178","title":"HANet: A Hierarchical Attention Network for Change Detection With Bitemporal Very-High-Resolution Remote Sensing Images","created":"2024-04-14","cited_by_count":30},{"id":"2105.10194","title":"Endmember-Guided Unmixing Network (EGU-Net): A General Deep Learning Framework for Self-Supervised Hyperspectral Unmixing","created":"2021-05-21","cited_by_count":29},{"id":"2011.05670","title":"FPGA: Fast Patch-Free Global Learning Framework for Fully End-to-End Hyperspectral Image Classification","created":"2020-11-11","cited_by_count":28},{"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":"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":"2203.17076","title":"Deep Hyperspectral Unmixing using Transformer Network","created":"2022-03-31","cited_by_count":22},{"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},{"id":"2108.12611","title":"Stagewise Unsupervised Domain Adaptation with Adversarial Self-Training for Road Segmentation of Remote Sensing Images","created":"2021-08-28","cited_by_count":20},{"id":"2310.00689","title":"Exchange means change: an unsupervised single-temporal change detection framework based on intra- and inter-image patch exchange","created":"2023-10-01","cited_by_count":20},{"id":"2405.01726","title":"SSUMamba: Spatial-Spectral Selective State Space Model for Hyperspectral Image Denoising","created":"2024-05-02","cited_by_count":20},{"id":"2005.11977","title":"Hyperspectral Image Classification with Attention Aided CNNs","created":"2020-05-25","cited_by_count":18},{"id":"2401.04614","title":"Generic Knowledge Boosted Pre-training For Remote Sensing Images","created":"2024-01-09","cited_by_count":16},{"id":"1812.11501","title":"CoSpace: Common Subspace Learning from Hyperspectral-Multispectral Correspondences","created":"2018-12-30","cited_by_count":15},{"id":"1912.08837","title":"Learning Shared Cross-modality Representation Using Multispectral-LiDAR and Hyperspectral Data","created":"2019-12-18","cited_by_count":12},{"id":"2102.12310","title":"Hyperspectral Denoising Using Unsupervised Disentangled Spatio-Spectral Deep Priors","created":"2021-02-24","cited_by_count":12}],"next_cursor":"100"}