{"list":"other","total":57,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1503.03832","title":"FaceNet: A Unified Embedding for Face Recognition and Clustering","created":"2015-03-12","cited_by_count":2849},{"id":"1809.11096","title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","created":"2018-09-28","cited_by_count":2626},{"id":"1807.06521","title":"CBAM: Convolutional Block Attention Module","created":"2018-07-17","cited_by_count":2477},{"id":"1306.0895","title":"Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances","created":"2013-06-04","cited_by_count":2316},{"id":"1411.1784","title":"Conditional Generative Adversarial Nets","created":"2014-11-06","cited_by_count":2162},{"id":"1609.04802","title":"Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network","created":"2016-09-15","cited_by_count":1908},{"id":"1809.00219","title":"ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks","created":"2018-09-01","cited_by_count":1254},{"id":"1511.07247","title":"NetVLAD: CNN architecture for weakly supervised place recognition","created":"2015-11-23","cited_by_count":941},{"id":"1511.04587","title":"Accurate Image Super-Resolution Using Very Deep Convolutional Networks","created":"2015-11-14","cited_by_count":903},{"id":"1711.10398","title":"DOTA: A Large-scale Dataset for Object Detection in Aerial Images","created":"2017-11-28","cited_by_count":623},{"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":"1704.02510","title":"DualGAN: Unsupervised Dual Learning for Image-to-Image Translation","created":"2017-04-08","cited_by_count":310},{"id":"1711.11586","title":"Toward Multimodal Image-to-Image Translation","created":"2017-11-30","cited_by_count":296},{"id":"2011.12172","title":"VIGOR: Cross-View Image Geo-localization beyond One-to-one Retrieval","created":"2020-11-24","cited_by_count":189},{"id":"1510.03743","title":"Wide-Area Image Geolocalization with Aerial Reference Imagery","created":"2015-10-13","cited_by_count":186},{"id":"1903.12351","title":"Lending Orientation to Neural Networks for Cross-view Geo-localization","created":"2019-03-29","cited_by_count":180},{"id":"1807.09251","title":"GANimation: Anatomically-aware Facial Animation from a Single Image","created":"2018-07-24","cited_by_count":161},{"id":"2002.12186","title":"University-1652: A Multi-view Multi-source Benchmark for Drone-based Geo-localization","created":"2020-02-27","cited_by_count":157},{"id":"1802.07856","title":"xView: Objects in Context in Overhead Imagery","created":"2018-02-22","cited_by_count":146},{"id":"1509.05909","title":"Modelling Uncertainty in Deep Learning for Camera Relocalization","created":"2015-09-19","cited_by_count":134},{"id":"2005.03860","title":"Where am I looking at? Joint Location and Orientation Estimation by Cross-View Matching","created":"2020-05-08","cited_by_count":126},{"id":"1602.05314","title":"PlaNet - Photo Geolocation with Convolutional Neural Networks","created":"2016-02-17","cited_by_count":115},{"id":"2103.06818","title":"Coming Down to Earth: Satellite-to-Street View Synthesis for Geo-Localization","created":"2021-03-11","cited_by_count":113},{"id":"1707.00143","title":"Fast Approximate Nearest Neighbor Search With The Navigating Spreading-out Graph","created":"2017-07-01","cited_by_count":104},{"id":"1904.06807","title":"Multi-Channel Attention Selection GAN with Cascaded Semantic Guidance for Cross-View Image Translation","created":"2019-04-15","cited_by_count":97},{"id":"2008.11646","title":"Each Part Matters: Local Patterns Facilitate Cross-view Geo-localization","created":"2020-08-26","cited_by_count":97},{"id":"1904.11045","title":"Bridging the Domain Gap for Ground-to-Aerial Image Matching","created":"2019-04-24","cited_by_count":95},{"id":"1608.00161","title":"Localizing and Orienting Street Views Using Overhead Imagery","created":"2016-07-30","cited_by_count":94},{"id":"1907.05021","title":"Optimal Feature Transport for Cross-View Image Geo-Localization","created":"2019-07-11","cited_by_count":91},{"id":"1612.02709","title":"Predicting Ground-Level Scene Layout from Aerial Imagery","created":"2016-12-08","cited_by_count":90},{"id":"1705.04838","title":"Revisiting IM2GPS in the Deep Learning Era","created":"2017-05-13","cited_by_count":80},{"id":"1911.11897","title":"AttentionGAN: Unpaired Image-to-Image Translation using Attention-Guided Generative Adversarial Networks","created":"2019-11-27","cited_by_count":77},{"id":"1703.07815","title":"Cross-View Image Matching for Geo-localization in Urban Environments","created":"2017-03-22","cited_by_count":69},{"id":"1803.03396","title":"Cross-View Image Synthesis using Conditional GANs","created":"2018-03-09","cited_by_count":69},{"id":"1808.02130","title":"CPlaNet: Enhancing Image Geolocalization by Combinatorial Partitioning of Maps","created":"2018-08-06","cited_by_count":68},{"id":"1608.01807","title":"SIFT Meets CNN: A Decade Survey of Instance Retrieval","created":"2016-08-05","cited_by_count":67},{"id":"1812.04098","title":"The Effects of Super-Resolution on Object Detection Performance in Satellite Imagery","created":"2018-12-10","cited_by_count":58},{"id":"2103.01623","title":"Geometry-Guided Street-View Panorama Synthesis from Satellite Imagery","created":"2021-03-02","cited_by_count":41},{"id":"2005.11592","title":"Revisiting Street-to-Aerial View Image Geo-localization and Orientation Estimation","created":"2020-05-23","cited_by_count":36},{"id":"2104.06456","title":"Single Image Depth Estimation: An Overview","created":"2021-04-13","cited_by_count":35},{"id":"1511.00098","title":"Semantic Cross-View Matching","created":"2015-10-31","cited_by_count":31},{"id":"1704.01133","title":"Satellite Image-based Localization via Learned Embeddings","created":"2017-04-04","cited_by_count":22},{"id":"1708.08417","title":"Automatic Discovery and Geotagging of Objects from Street View Imagery","created":"2017-08-28","cited_by_count":17},{"id":"1907.10892","title":"Simultaneous multi-view instance detection with learned geometric soft-constraints","created":"2019-07-25","cited_by_count":11},{"id":"1910.12468","title":"Image-Based Place Recognition on Bucolic Environment Across Seasons From Semantic Edge Description","created":"2019-10-28","cited_by_count":8},{"id":"2107.06257","title":"Object Tracking and Geo-localization from Street Images","created":"2021-07-13","cited_by_count":8},{"id":"1605.08323","title":"Aerial image geolocalization from recognition and matching of roads and intersections","created":"2016-05-26","cited_by_count":3}],"next_cursor":null}