{"list":"other","total":67,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"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":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"2006.09882","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","created":"2020-06-17","cited_by_count":2857},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"1803.07728","title":"Unsupervised Representation Learning by Predicting Image Rotations","created":"2018-03-21","cited_by_count":1591},{"id":"1511.00561","title":"SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation","created":"2015-11-02","cited_by_count":1487},{"id":"1603.09246","title":"Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles","created":"2016-03-30","cited_by_count":1382},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"2111.09886","title":"SimMIM: A Simple Framework for Masked Image Modeling","created":"2021-11-18","cited_by_count":1153},{"id":"1603.08511","title":"Colorful Image Colorization","created":"2016-03-28","cited_by_count":1114},{"id":"2301.08243","title":"Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture","created":"2023-01-19","cited_by_count":1039},{"id":"2202.03555","title":"data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language","created":"2022-02-07","cited_by_count":727},{"id":"2109.13410","title":"KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D","created":"2021-09-28","cited_by_count":575},{"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":"2103.16607","title":"Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing Data","created":"2021-03-30","cited_by_count":215},{"id":"2201.08377","title":"Omnivore: A Single Model for Many Visual Modalities","created":"2022-01-20","cited_by_count":215},{"id":"2107.14222","title":"Rethinking and Improving Relative Position Encoding for Vision Transformer","created":"2021-07-29","cited_by_count":207},{"id":"2011.09980","title":"Geography-Aware Self-Supervised Learning","created":"2020-11-19","cited_by_count":190},{"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":"2107.07933","title":"Panoptic Segmentation of Satellite Image Time Series with Convolutional Temporal Attention Networks","created":"2021-07-16","cited_by_count":143},{"id":"2008.05457","title":"More Diverse Means Better: Multimodal Deep Learning Meets Remote Sensing Imagery Classification","created":"2020-08-12","cited_by_count":126},{"id":"1803.10409","title":"3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation","created":"2018-03-28","cited_by_count":118},{"id":"2403.15356","title":"Neural Plasticity-Inspired Multimodal Foundation Model for Earth Observation","created":"2024-03-22","cited_by_count":104},{"id":"2304.14065","title":"Lightweight, Pre-trained Transformers for Remote Sensing Timeseries","created":"2023-04-27","cited_by_count":103},{"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":"2010.08168","title":"A Generalizable and Accessible Approach to Machine Learning with Global Satellite Imagery","created":"2020-10-16","cited_by_count":88},{"id":"2304.06798","title":"On the Opportunities and Challenges of Foundation Models for Geospatial Artificial Intelligence","created":"2023-04-13","cited_by_count":88},{"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":"1910.10536","title":"Self-attention for raw optical Satellite Time Series Classification","created":"2019-10-23","cited_by_count":75},{"id":"2205.01380","title":"Deep Learning in Multimodal Remote Sensing Data Fusion: A Comprehensive Review","created":"2022-05-03","cited_by_count":73},{"id":"1911.07757","title":"Satellite Image Time Series Classification with Pixel-Set Encoders and Temporal Self-Attention","created":"2019-11-18","cited_by_count":71},{"id":"2212.08071","title":"MAViL: Masked Audio-Video Learners","created":"2022-12-15","cited_by_count":59},{"id":"2304.01008","title":"Self-Supervised Multimodal Learning: A Survey","created":"2023-03-31","cited_by_count":58},{"id":"2301.04944","title":"ViTs for SITS: Vision Transformers for Satellite Image Time Series","created":"2023-01-12","cited_by_count":56},{"id":"2007.00586","title":"Lightweight Temporal Self-Attention for Classifying Satellite Image Time Series","created":"2020-07-01","cited_by_count":55},{"id":"2112.07558","title":"Multi-Modal Temporal Attention Models for Crop Mapping from Satellite Time Series","created":"2021-12-14","cited_by_count":49},{"id":"2004.06500","title":"SpaceNet 6: Multi-Sensor All Weather Mapping Dataset","created":"2020-04-14","cited_by_count":47},{"id":"2204.07548","title":"Learning Multi-View Aggregation In the Wild for Large-Scale 3D Semantic Segmentation","created":"2022-04-15","cited_by_count":47},{"id":"2307.16184","title":"UnIVAL: Unified Model for Image, Video, Audio and Language Tasks","created":"2023-07-30","cited_by_count":45},{"id":"2311.05709","title":"OmniVec: Learning robust representations with cross modal sharing","created":"2023-11-07","cited_by_count":44},{"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":"1912.08487","title":"FuseSeg: LiDAR Point Cloud Segmentation Fusing Multi-Modal Data","created":"2019-12-18","cited_by_count":33},{"id":"2201.09613","title":"SEN12MS-CR-TS: A Remote Sensing Data Set for Multi-modal Multi-temporal Cloud Removal","created":"2022-01-24","cited_by_count":32},{"id":"2312.02199","title":"USat: A Unified Self-Supervised Encoder for Multi-Sensor Satellite Imagery","created":"2023-12-02","cited_by_count":28},{"id":"2305.13456","title":"Revisiting pre-trained remote sensing model benchmarks: resizing and normalization matters","created":"2023-05-22","cited_by_count":27},{"id":"2112.00570","title":"Toward Foundation Models for Earth Monitoring: Proposal for a Climate Change Benchmark","created":"2021-12-01","cited_by_count":22},{"id":"2301.09595","title":"Zorro: the masked multimodal transformer","created":"2023-01-23","cited_by_count":13},{"id":"2401.07782","title":"Exploring Masked Autoencoders for Sensor-Agnostic Image Retrieval in Remote Sensing","created":"2024-01-15","cited_by_count":12},{"id":"2204.07052","title":"CroCo: Cross-Modal Contrastive learning for localization of Earth Observation data","created":"2022-04-14","cited_by_count":4},{"id":"2212.02265","title":"MapInWild: A Remote Sensing Dataset to Address the Question What Makes Nature Wild","created":"2022-12-05","cited_by_count":1}],"next_cursor":null}