{"list":"other","total":52,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"id":"1608.02192","title":"Playing for Data: Ground Truth from Computer Games","created":"2016-08-07","cited_by_count":818},{"id":"1611.07759","title":"Multi-View 3D Object Detection Network for Autonomous Driving","created":"2016-11-23","cited_by_count":724},{"id":"1904.01766","title":"VideoBERT: A Joint Model for Video and Language Representation Learning","created":"2019-04-03","cited_by_count":703},{"id":"1812.03079","title":"ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worst","created":"2018-12-07","cited_by_count":397},{"id":"1912.12294","title":"Learning by Cheating","created":"2019-12-27","cited_by_count":383},{"id":"1904.08980","title":"Exploring the Limitations of Behavior Cloning for Autonomous Driving","created":"2019-04-18","cited_by_count":346},{"id":"1605.06457","title":"Virtual Worlds as Proxy for Multi-Object Tracking Analysis","created":"2016-05-20","cited_by_count":341},{"id":"1712.02294","title":"Joint 3D Proposal Generation and Object Detection from View Aggregation","created":"2017-12-06","cited_by_count":326},{"id":"1806.01482","title":"SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraints","created":"2018-06-05","cited_by_count":298},{"id":"2012.10992","title":"Deep Continuous Fusion for Multi-Sensor 3D Object Detection","created":"2020-12-20","cited_by_count":263},{"id":"1907.03395","title":"Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networks","created":"2019-07-04","cited_by_count":229},{"id":"2012.12395","title":"Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Net","created":"2020-12-22","cited_by_count":228},{"id":"2012.12397","title":"Multi-Task Multi-Sensor Fusion for 3D Object Detection","created":"2020-12-22","cited_by_count":203},{"id":"1906.06310","title":"Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving","created":"2019-06-14","cited_by_count":188},{"id":"1905.01296","title":"PRECOG: PREdiction Conditioned On Goals in Visual Multi-Agent Settings","created":"2019-05-03","cited_by_count":179},{"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":"2101.07907","title":"IntentNet: Learning to Predict Intention from Raw Sensor Data","created":"2021-01-20","cited_by_count":158},{"id":"1911.10868","title":"End-to-End Model-Free Reinforcement Learning for Urban Driving using Implicit Affordances","created":"2019-11-25","cited_by_count":149},{"id":"1612.01079","title":"End-to-end Learning of Driving Models from Large-scale Video Datasets","created":"2016-12-04","cited_by_count":148},{"id":"2005.14711","title":"PnPNet: End-to-End Perception and Prediction with Tracking in the Loop","created":"2020-05-29","cited_by_count":144},{"id":"2006.14911","title":"Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?","created":"2020-06-26","cited_by_count":139},{"id":"2001.07966","title":"ImageBERT: Cross-modal Pre-training with Large-scale Weak-supervised Image-Text Data","created":"2020-01-22","cited_by_count":137},{"id":"1903.08701","title":"LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Driving","created":"2019-03-20","cited_by_count":133},{"id":"1906.03199","title":"Multimodal End-to-End Autonomous Driving","created":"2019-06-07","cited_by_count":110},{"id":"1910.06727","title":"Depth Completion from Sparse LiDAR Data with Depth-Normal Constraints","created":"2019-10-15","cited_by_count":108},{"id":"1910.08233","title":"Spatially-Aware Graph Neural Networks for Relational Behavior Forecasting from Sensor Data","created":"2019-10-18","cited_by_count":104},{"id":"1810.06544","title":"Deep Imitative Models for Flexible Inference, Planning, and Control","created":"2018-10-15","cited_by_count":76},{"id":"2010.14876","title":"Fighting Copycat Agents in Behavioral Cloning from Observation Histories","created":"2020-10-28","cited_by_count":71},{"id":"1905.12887","title":"Does computer vision matter for action?","created":"2019-05-30","cited_by_count":64},{"id":"2008.05927","title":"End-to-end Contextual Perception and Prediction with Interaction Transformer","created":"2020-08-13","cited_by_count":54},{"id":"1804.10992","title":"Semi-parametric Image Synthesis","created":"2018-04-29","cited_by_count":50},{"id":"1904.11466","title":"Sensor Fusion for Joint 3D Object Detection and Semantic Segmentation","created":"2019-04-25","cited_by_count":48},{"id":"2008.11901","title":"Multi-View Fusion of Sensor Data for Improved Perception and Prediction in Autonomous Driving","created":"2020-08-27","cited_by_count":41},{"id":"1905.06937","title":"Monocular Plan View Networks for Autonomous Driving","created":"2019-05-16","cited_by_count":37},{"id":"1711.10061","title":"CAR-Net: Clairvoyant Attentive Recurrent Network","created":"2017-11-28","cited_by_count":34},{"id":"2005.10091","title":"Label Efficient Visual Abstractions for Autonomous Driving","created":"2020-05-20","cited_by_count":33},{"id":"2006.02000","title":"MultiXNet: Multiclass Multistage Multimodal Motion Prediction","created":"2020-06-03","cited_by_count":31},{"id":"2011.01153","title":"Perceive, Attend, and Drive: Learning Spatial Attention for Safe Self-Driving","created":"2020-11-02","cited_by_count":24},{"id":"1905.08855","title":"Looking to Relations for Future Trajectory Forecast","created":"2019-05-21","cited_by_count":23},{"id":"2003.05982","title":"LaserFlow: Efficient and Probabilistic Object Detection and Motion Forecasting","created":"2020-03-12","cited_by_count":22},{"id":"2005.04255","title":"STINet: Spatio-Temporal-Interactive Network for Pedestrian Detection and Trajectory Prediction","created":"2020-05-08","cited_by_count":22},{"id":"2009.01875","title":"Depth Completion via Inductive Fusion of Planar LIDAR and Monocular Camera","created":"2020-09-03","cited_by_count":22},{"id":"2006.05518","title":"MVLidarNet: Real-Time Multi-Class Scene Understanding for Autonomous Driving Using Multiple Views","created":"2020-06-09","cited_by_count":20},{"id":"1702.05596","title":"Brain Inspired Cognitive Model with Attention for Self-Driving Cars","created":"2017-02-18","cited_by_count":10},{"id":"2009.04554","title":"RoIFusion: 3D Object Detection from LiDAR and Vision","created":"2020-09-09","cited_by_count":6},{"id":"1912.02973","title":"SAM: Squeeze-and-Mimic Networks for Conditional Visual Driving Policy Learning","created":"2019-12-06","cited_by_count":5}],"next_cursor":null}