{"list":"other","total":53,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"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":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"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":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"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":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519},{"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":"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":"2306.00989","title":"Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles","created":"2023-06-01","cited_by_count":290},{"id":"2311.07113","title":"SpectralGPT: Spectral Remote Sensing Foundation Model","created":"2023-11-13","cited_by_count":252},{"id":"2106.03348","title":"ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias","created":"2021-06-07","cited_by_count":216},{"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":"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":"2205.09911","title":"Can Foundation Models Wrangle Your Data?","created":"2022-05-20","cited_by_count":175},{"id":"2211.15660","title":"SatlasPretrain: A Large-Scale Dataset for Remote Sensing Image Understanding","created":"2022-11-28","cited_by_count":167},{"id":"2311.17179","title":"SatCLIP: Global, General-Purpose Location Embeddings with Satellite Imagery","created":"2023-11-28","cited_by_count":151},{"id":"2208.03987","title":"Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model","created":"2022-08-08","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":"2306.00258","title":"Towards Foundation Models for Scientific Machine Learning: Characterizing Scaling and Transfer Behavior","created":"2023-06-01","cited_by_count":131},{"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":"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":"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":"2305.01118","title":"CSP: Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual Representations","created":"2023-05-01","cited_by_count":69},{"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":"1802.02080","title":"Multi-Temporal Land Cover Classification with Sequential Recurrent Encoders","created":"2018-02-06","cited_by_count":61},{"id":"2301.04944","title":"ViTs for SITS: Vision Transformers for Satellite Image Time Series","created":"2023-01-12","cited_by_count":56},{"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":"2401.15855","title":"Cross-Scale MAE: A Tale of Multi-Scale Exploitation in Remote Sensing","created":"2024-01-29","cited_by_count":47},{"id":"2404.01260","title":"Bridging Remote Sensors with Multisensor Geospatial Foundation Models","created":"2024-04-01","cited_by_count":46},{"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":"2312.02199","title":"USat: A Unified Self-Supervised Encoder for Multi-Sensor Satellite Imagery","created":"2023-12-02","cited_by_count":28},{"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":"2408.01946","title":"Masked Angle-Aware Autoencoder for Remote Sensing Images","created":"2024-08-04","cited_by_count":22},{"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":"2311.12056","title":"Kuro Siwo: 33 billion $m^2$ under the water. A global multi-temporal satellite dataset for rapid flood mapping","created":"2023-11-18","cited_by_count":16},{"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":"2306.04738","title":"MultiEarth 2023 -- Multimodal Learning for Earth and Environment Workshop and Challenge","created":"2023-06-07","cited_by_count":6}],"next_cursor":null}