{"list":"other","total":55,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"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":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"2104.02057","title":"An Empirical Study of Training Self-Supervised Vision Transformers","created":"2021-04-05","cited_by_count":1616},{"id":"2508.10104","title":"DINOv3","created":"2025-08-13","cited_by_count":1414},{"id":"1807.10221","title":"Unified Perceptual Parsing for Scene Understanding","created":"2018-07-26","cited_by_count":1271},{"id":"1809.02983","title":"Dual Attention Network for Scene Segmentation","created":"2018-09-09","cited_by_count":1003},{"id":"1711.10398","title":"DOTA: A Large-scale Dataset for Object Detection in Aerial Images","created":"2017-11-28","cited_by_count":623},{"id":"2207.08051","title":"SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery","created":"2022-07-17","cited_by_count":408},{"id":"2212.00794","title":"Scaling Language-Image Pre-training via Masking","created":"2022-12-01","cited_by_count":317},{"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":"2103.07733","title":"ReDet: A Rotation-equivariant Detector for Aerial Object Detection","created":"2021-03-13","cited_by_count":203},{"id":"1908.07678","title":"Asymmetric Non-local Neural Networks for Semantic Segmentation","created":"2019-08-21","cited_by_count":196},{"id":"1908.05612","title":"R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object","created":"2019-08-15","cited_by_count":194},{"id":"2311.00566","title":"CROMA: Remote Sensing Representations with Contrastive Radar-Optical Masked Autoencoders","created":"2023-11-01","cited_by_count":169},{"id":"2208.03987","title":"Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model","created":"2022-08-08","cited_by_count":149},{"id":"2406.11519","title":"HyperSIGMA: Hyperspectral Intelligence Comprehension Foundation Model","created":"2024-06-17","cited_by_count":73},{"id":"2303.13496","title":"The effectiveness of MAE pre-pretraining for billion-scale pretraining","created":"2023-03-23","cited_by_count":68},{"id":"2403.13430","title":"MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining","created":"2024-03-20","cited_by_count":66},{"id":"2006.10027","title":"Deep Learning Meets SAR","created":"2020-06-17","cited_by_count":60},{"id":"1807.08407","title":"Occlusion-aware R-CNN: Detecting Pedestrians in a Crowd","created":"2018-07-23","cited_by_count":58},{"id":"2503.11849","title":"Towards a Unified Copernicus Foundation Model for Earth Vision","created":"2025-03-14","cited_by_count":53},{"id":"2403.06534","title":"SARDet-100K: Towards Open-Source Benchmark and ToolKit for Large-Scale SAR Object Detection","created":"2024-03-11","cited_by_count":48},{"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":"1807.01569","title":"The SEN1-2 Dataset for Deep Learning in SAR-Optical Data Fusion","created":"2018-07-04","cited_by_count":42},{"id":"2501.06019","title":"BRIGHT: A globally distributed multimodal building damage assessment dataset with very-high-resolution for all-weather disaster response","created":"2025-01-10","cited_by_count":41},{"id":"1812.00155","title":"Learning RoI Transformer for Detecting Oriented Objects in Aerial Images","created":"2018-12-01","cited_by_count":37},{"id":"2303.04989","title":"ARS-DETR: Aspect Ratio-Sensitive Detection Transformer for Aerial Oriented Object Detection","created":"2023-03-09","cited_by_count":32},{"id":"2201.02873","title":"LoMar: A Local Defense Against Poisoning Attack on Federated Learning","created":"2022-01-08","cited_by_count":31},{"id":"2410.22629","title":"CrossEarth: Geospatial Vision Foundation Model for Domain Generalizable Remote Sensing Semantic Segmentation","created":"2024-10-30","cited_by_count":27},{"id":"2405.09365","title":"SARATR-X: Toward Building A Foundation Model for SAR Target Recognition","created":"2024-05-15","cited_by_count":25},{"id":"2205.14949","title":"HiViT: Hierarchical Vision Transformer Meets Masked Image Modeling","created":"2022-05-30","cited_by_count":23},{"id":"2510.23116","title":"Residual Diffusion Bridge Model for Image Restoration","created":"2025-10-27","cited_by_count":15},{"id":"2501.10891","title":"OpenEarthMap-SAR: A Benchmark Synthetic Aperture Radar Dataset for Global High-Resolution Land Cover Mapping","created":"2025-01-18","cited_by_count":13},{"id":"2406.11933","title":"Harnessing Massive Satellite Imagery with Efficient Masked Image Modeling","created":"2024-06-17","cited_by_count":12},{"id":"2501.04440","title":"RSAR: Restricted State Angle Resolver and Rotated SAR Benchmark","created":"2025-01-08","cited_by_count":12},{"id":"2503.10392","title":"RoMA: Scaling up Mamba-based Foundation Models for Remote Sensing","created":"2025-03-13","cited_by_count":11},{"id":"2505.10931","title":"M4-SAR: A Multi-Resolution, Multi-Polarization, Multi-Scene, Multi-Source Dataset and Benchmark for optical-SAR Object Detection","created":"2025-05-16","cited_by_count":10},{"id":"2411.15770","title":"Text-Guided Coarse-to-Fine Fusion Network for Robust Remote Sensing Visual Question Answering","created":"2024-11-24","cited_by_count":5},{"id":"2504.21487","title":"DGSolver: Diffusion Generalist Solver with Universal Posterior Sampling for Image Restoration","created":"2025-04-30","cited_by_count":5},{"id":"2505.08723","title":"TiMo: Spatiotemporal Foundation Model for Satellite Image Time Series","created":"2025-05-13","cited_by_count":5},{"id":"2006.12485","title":"On Creating Benchmark Dataset for Aerial Image Interpretation: Reviews, Guidances and Million-AID","created":"2020-06-22","cited_by_count":3},{"id":"2408.03627","title":"Weakly Contrastive Learning via Batch Instance Discrimination and Feature Clustering for Small Sample SAR ATR","created":"2024-08-07","cited_by_count":3},{"id":"2508.10208","title":"CATNet: A geometric deep learning approach for CAT bond spread prediction in the primary market","created":"2025-08-13","cited_by_count":1}],"next_cursor":null}