{"list":"other","total":51,"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":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1612.00593","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","created":"2016-12-02","cited_by_count":5248},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1711.05101","title":"Decoupled Weight Decay Regularization","created":"2017-11-14","cited_by_count":1831},{"id":"1812.05784","title":"PointPillars: Fast Encoders for Object Detection from Point Clouds","created":"2018-12-14","cited_by_count":1715},{"id":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"id":"1902.09630","title":"Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression","created":"2019-02-25","cited_by_count":1368},{"id":"2008.05711","title":"Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D","created":"2020-08-13","cited_by_count":1044},{"id":"1506.03099","title":"Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks","created":"2015-06-09","cited_by_count":803},{"id":"1802.05751","title":"Image Transformer","created":"2018-02-15","cited_by_count":772},{"id":"1911.02620","title":"Argoverse: 3D Tracking and Forecasting with Rich Maps","created":"2019-11-06","cited_by_count":732},{"id":"2110.06922","title":"DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries","created":"2021-10-13","cited_by_count":658},{"id":"2005.04259","title":"VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation","created":"2020-05-08","cited_by_count":530},{"id":"2203.01305","title":"DN-DETR: Accelerate DETR Training by Introducing Query DeNoising","created":"2022-03-02","cited_by_count":488},{"id":"2008.08294","title":"TNT: Target-driveN Trajectory Prediction","created":"2020-08-19","cited_by_count":347},{"id":"1704.03477","title":"A Neural Representation of Sketch Drawings","created":"2017-04-11","cited_by_count":313},{"id":"2002.10880","title":"PolyGen: An Autoregressive Generative Model of 3D Meshes","created":"2020-02-23","cited_by_count":269},{"id":"2205.02833","title":"Cross-view Transformers for real-time Map-view Semantic Segmentation","created":"2022-05-05","cited_by_count":264},{"id":"2101.06806","title":"MP3: A Unified Model to Map, Perceive, Predict and Plan","created":"2021-01-18","cited_by_count":212},{"id":"2103.11624","title":"Multimodal Motion Prediction with Stacked Transformers","created":"2021-03-22","cited_by_count":208},{"id":"2203.10642","title":"FUTR3D: A Unified Sensor Fusion Framework for 3D Detection","created":"2022-03-20","cited_by_count":194},{"id":"1712.06080","title":"Spatial As Deep: Spatial CNN for Traffic Scene Understanding","created":"2017-12-17","cited_by_count":187},{"id":"2003.13402","title":"Predicting Semantic Map Representations from Images using Pyramid Occupancy Networks","created":"2020-03-30","cited_by_count":175},{"id":"1906.03560","title":"Cross-view Semantic Segmentation for Sensing Surroundings","created":"2019-06-09","cited_by_count":174},{"id":"1910.06528","title":"End-to-End Multi-View Fusion for 3D Object Detection in LiDAR Point Clouds","created":"2019-10-15","cited_by_count":171},{"id":"2007.11301","title":"DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation","created":"2020-07-22","cited_by_count":159},{"id":"2008.05930","title":"Perceive, Predict, and Plan: Safe Motion Planning Through Interpretable Semantic Representations","created":"2020-08-13","cited_by_count":153},{"id":"1802.05591","title":"Towards End-to-End Lane Detection: an Instance Segmentation Approach","created":"2018-02-15","cited_by_count":129},{"id":"2005.03778","title":"LGSVL Simulator: A High Fidelity Simulator for Autonomous Driving","created":"2020-05-07","cited_by_count":121},{"id":"1803.09693","title":"Efficient Interactive Annotation of Segmentation Datasets with Polygon-RNN++","created":"2018-03-26","cited_by_count":120},{"id":"2102.02798","title":"Im2Vec: Synthesizing Vector Graphics without Vector Supervision","created":"2021-02-04","cited_by_count":116},{"id":"2110.01997","title":"Structured Bird's-Eye-View Traffic Scene Understanding from Onboard Images","created":"2021-10-05","cited_by_count":98},{"id":"2108.01249","title":"CanvasVAE: Learning to Generate Vector Graphic Documents","created":"2021-08-03","cited_by_count":95},{"id":"1912.02801","title":"PolyTransform: Deep Polygon Transformer for Instance Segmentation","created":"2019-12-05","cited_by_count":92},{"id":"1704.05548","title":"Annotating Object Instances with a Polygon-RNN","created":"2017-04-18","cited_by_count":88},{"id":"2203.02431","title":"Rethinking Efficient Lane Detection via Curve Modeling","created":"2022-03-04","cited_by_count":88},{"id":"1804.02176","title":"Monocular Semantic Occupancy Grid Mapping with Convolutional Variational Encoder-Decoder Networks","created":"2018-04-06","cited_by_count":84},{"id":"2105.02769","title":"Computer-Aided Design as Language","created":"2021-05-06","cited_by_count":82},{"id":"2012.11704","title":"HDNET: Exploiting HD Maps for 3D Object Detection","created":"2020-12-21","cited_by_count":78},{"id":"2101.01909","title":"Line Segment Detection Using Transformers without Edges","created":"2021-01-06","cited_by_count":73},{"id":"1710.06288","title":"VPGNet: Vanishing Point Guided Network for Lane and Road Marking Detection and Recognition","created":"2017-10-17","cited_by_count":56},{"id":"2111.15491","title":"PolyWorld: Polygonal Building Extraction with Graph Neural Networks in Satellite Images","created":"2021-11-30","cited_by_count":43},{"id":"2106.14880","title":"HDMapGen: A Hierarchical Graph Generative Model of High Definition Maps","created":"2021-06-28","cited_by_count":40},{"id":"2012.12314","title":"Hierarchical Recurrent Attention Networks for Structured Online Maps","created":"2020-12-22","cited_by_count":38},{"id":"1902.00293","title":"End-to-end Lane Detection through Differentiable Least-Squares Fitting","created":"2019-02-01","cited_by_count":36},{"id":"2012.12160","title":"Convolutional Recurrent Network for Road Boundary Extraction","created":"2020-12-21","cited_by_count":33},{"id":"1612.00423","title":"TorontoCity: Seeing the World with a Million Eyes","created":"2016-12-01","cited_by_count":24},{"id":"2105.00195","title":"Lane Graph Estimation for Scene Understanding in Urban Driving","created":"2021-05-01","cited_by_count":18}],"next_cursor":null}