{"list":"other","total":51,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"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":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"1906.07155","title":"MMDetection: Open MMLab Detection Toolbox and Benchmark","created":"2019-06-17","cited_by_count":1385},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"id":"1608.02192","title":"Playing for Data: Ground Truth from Computer Games","created":"2016-08-07","cited_by_count":818},{"id":"1806.02446","title":"Deep Ordinal Regression Network for Monocular Depth Estimation","created":"2018-06-06","cited_by_count":723},{"id":"1901.07518","title":"Hybrid Task Cascade for Instance Segmentation","created":"2019-01-22","cited_by_count":481},{"id":"1906.09756","title":"Cascade R-CNN: High Quality Object Detection and Instance Segmentation","created":"2019-06-24","cited_by_count":429},{"id":"1805.06561","title":"DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Images","created":"2018-05-17","cited_by_count":277},{"id":"1903.00241","title":"Mask Scoring R-CNN","created":"2019-03-01","cited_by_count":266},{"id":"1803.06184","title":"The ApolloScape Open Dataset for Autonomous Driving and its Application","created":"2018-03-16","cited_by_count":190},{"id":"2011.12172","title":"VIGOR: Cross-View Image Geo-localization beyond One-to-one Retrieval","created":"2020-11-24","cited_by_count":189},{"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":"1903.09254","title":"CityFlow: A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-Identification","created":"2019-03-21","cited_by_count":119},{"id":"1905.02188","title":"CARAFE: Content-Aware ReAssembly of FEatures","created":"2019-05-06","cited_by_count":119},{"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":"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":"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":"1612.02709","title":"Predicting Ground-Level Scene Layout from Aerial Imagery","created":"2016-12-08","cited_by_count":90},{"id":"2203.13608","title":"Rope3D: TheRoadside Perception Dataset for Autonomous Driving and Monocular 3D Object Detection Task","created":"2022-03-25","cited_by_count":81},{"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":"2102.04420","title":"The Multi-Temporal Urban Development SpaceNet Dataset","created":"2021-02-08","cited_by_count":62},{"id":"1805.07193","title":"The EuroCity Persons Dataset: A Novel Benchmark for Object Detection","created":"2018-05-18","cited_by_count":57},{"id":"1811.08739","title":"Semantic Stereo for Incidental Satellite Images","created":"2018-11-21","cited_by_count":53},{"id":"1907.06023","title":"Structure-Aware Residual Pyramid Network for Monocular Depth Estimation","created":"2019-07-13","cited_by_count":49},{"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":"1802.09026","title":"Building Instance Classification Using Street View Images","created":"2018-02-25","cited_by_count":33},{"id":"2012.12160","title":"Convolutional Recurrent Network for Road Boundary Extraction","created":"2020-12-21","cited_by_count":33},{"id":"1903.12239","title":"SpaceNet MVOI: a Multi-View Overhead Imagery Dataset","created":"2019-03-28","cited_by_count":29},{"id":"2008.03286","title":"HoliCity: A City-Scale Data Platform for Learning Holistic 3D Structures","created":"2020-08-07","cited_by_count":29},{"id":"1905.01752","title":"Understanding urban landuse from the above and ground perspectives: a deep learning, multimodal solution","created":"2019-05-05","cited_by_count":26},{"id":"2012.06628","title":"Sat2Vid: Street-view Panoramic Video Synthesis from a Single Satellite Image","created":"2020-12-11","cited_by_count":25},{"id":"1612.00423","title":"TorontoCity: Seeing the World with a Million Eyes","created":"2016-12-01","cited_by_count":24},{"id":"1709.05932","title":"Multi-Task Learning for Segmentation of Building Footprints with Deep Neural Networks","created":"2017-09-18","cited_by_count":24},{"id":"2007.06102","title":"SkyScapes -- Fine-Grained Semantic Understanding of Aerial Scenes","created":"2020-07-12","cited_by_count":22},{"id":"2007.00729","title":"Learning Geocentric Object Pose in Oblique Monocular Images","created":"2020-07-01","cited_by_count":16},{"id":"1708.03035","title":"A Unified Model for Near and Remote Sensing","created":"2017-08-09","cited_by_count":14},{"id":"2204.01807","title":"Revisiting Near/Remote Sensing with Geospatial Attention","created":"2022-04-04","cited_by_count":12},{"id":"1802.02668","title":"Fine-Grained Land Use Classification at the City Scale Using Ground-Level Images","created":"2018-02-07","cited_by_count":8},{"id":"2008.10041","title":"Holistic Multi-View Building Analysis in the Wild with Projection Pooling","created":"2020-08-23","cited_by_count":5},{"id":"2002.02634","title":"SideInfNet: A Deep Neural Network for Semi-Automatic Semantic Segmentation with Side Information","created":"2020-02-07","cited_by_count":3}],"next_cursor":null}