{"list":"other","total":101,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"id":"1812.05784","title":"PointPillars: Fast Encoders for Object Detection from Point Clouds","created":"2018-12-14","cited_by_count":1715},{"id":"2203.17270","title":"BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers","created":"2022-03-31","cited_by_count":1218},{"id":"1904.07850","title":"Objects as Points","created":"2019-04-16","cited_by_count":1175},{"id":"2003.13678","title":"Designing Network Design Spaces","created":"2020-03-30","cited_by_count":960},{"id":"2205.13542","title":"BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation","created":"2022-05-26","cited_by_count":850},{"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":"1711.08488","title":"Frustum PointNets for 3D Object Detection from RGB-D Data","created":"2017-11-22","cited_by_count":640},{"id":"2203.11496","title":"TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers","created":"2022-03-22","cited_by_count":466},{"id":"1911.10150","title":"PointPainting: Sequential Fusion for 3D Object Detection","created":"2019-11-22","cited_by_count":449},{"id":"2002.10187","title":"3DSSD: Point-based 3D Single Stage Object Detector","created":"2020-02-24","cited_by_count":440},{"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":"2103.14023","title":"AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecasting","created":"2021-03-25","cited_by_count":331},{"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":"1612.00496","title":"3D Bounding Box Estimation Using Deep Learning and Geometry","created":"2016-12-01","cited_by_count":278},{"id":"2205.02833","title":"Cross-view Transformers for real-time Map-view Semantic Segmentation","created":"2022-05-05","cited_by_count":264},{"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":"2108.08265","title":"End-to-End Urban Driving by Imitating a Reinforcement Learning Coach","created":"2021-08-18","cited_by_count":194},{"id":"2203.10642","title":"FUTR3D: A Unified Sensor Fusion Framework for 3D Detection","created":"2022-03-20","cited_by_count":194},{"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":"2109.04456","title":"NEAT: Neural Attention Fields for End-to-End Autonomous Driving","created":"2021-09-09","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":"1711.10871","title":"PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation","created":"2017-11-29","cited_by_count":170},{"id":"2106.08417","title":"Scene Transformer: A unified architecture for predicting multiple agent trajectories","created":"2021-06-15","cited_by_count":165},{"id":"2101.07907","title":"IntentNet: Learning to Predict Intention from Raw Sensor Data","created":"2021-01-20","cited_by_count":158},{"id":"2204.05088","title":"M$^2$BEV: Multi-Camera Joint 3D Detection and Segmentation with Unified Birds-Eye View Representation","created":"2022-04-11","cited_by_count":156},{"id":"2008.05930","title":"Perceive, Predict, and Plan: Safe Motion Planning Through Interpretable Semantic Representations","created":"2020-08-13","cited_by_count":153},{"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":"2009.00784","title":"CLOCs: Camera-LiDAR Object Candidates Fusion for 3D Object Detection","created":"2020-09-02","cited_by_count":147},{"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":"2112.05077","title":"Generating Useful Accident-Prone Driving Scenarios via a Learned Traffic Prior","created":"2021-12-09","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":"2101.06549","title":"AdvSim: Generating Safety-Critical Scenarios for Self-Driving Vehicles","created":"2021-01-16","cited_by_count":137},{"id":"2203.11934","title":"Learning from All Vehicles","created":"2022-03-22","cited_by_count":135},{"id":"1903.08701","title":"LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Driving","created":"2019-03-20","cited_by_count":133},{"id":"2203.04050","title":"BEVSegFormer: Bird's Eye View Semantic Segmentation From Arbitrary Camera Rigs","created":"2022-03-08","cited_by_count":123},{"id":"2110.00966","title":"Translating Images into Maps","created":"2021-10-03","cited_by_count":115},{"id":"2105.00636","title":"Learning to drive from a world on rails","created":"2021-05-03","cited_by_count":114},{"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":"2108.10723","title":"Improving 3D Object Detection with Channel-wise Transformer","created":"2021-08-23","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":"2101.06547","title":"LookOut: Diverse Multi-Future Prediction and Planning for Self-Driving","created":"2021-01-16","cited_by_count":96},{"id":"2204.13683","title":"KING: Generating Safety-Critical Driving Scenarios for Robust Imitation via Kinematics Gradients","created":"2022-04-28","cited_by_count":96},{"id":"1810.06544","title":"Deep Imitative Models for Flexible Inference, Planning, and Control","created":"2018-10-15","cited_by_count":76},{"id":"2201.04123","title":"gDNA: Towards Generative Detailed Neural Avatars","created":"2022-01-11","cited_by_count":72},{"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":"2111.08575","title":"GRI: General Reinforced Imitation and its Application to Vision-Based Autonomous Driving","created":"2021-11-16","cited_by_count":60},{"id":"2004.04699","title":"Scalable Active Learning for Object Detection","created":"2020-04-09","cited_by_count":58},{"id":"2011.13628","title":"Temporal-Channel Transformer for 3D Lidar-Based Video Object Detection in Autonomous Driving","created":"2020-11-27","cited_by_count":55},{"id":"2008.05927","title":"End-to-end Contextual Perception and Prediction with Interaction Transformer","created":"2020-08-13","cited_by_count":54},{"id":"1704.06244","title":"Towards Large-Pose Face Frontalization in the Wild","created":"2017-04-20","cited_by_count":50},{"id":"1804.10992","title":"Semi-parametric Image Synthesis","created":"2018-04-29","cited_by_count":50},{"id":"2112.11088","title":"EPNet++: Cascade Bi-directional Fusion for Multi-Modal 3D Object Detection","created":"2021-12-21","cited_by_count":49},{"id":"1904.11466","title":"Sensor Fusion for Joint 3D Object Detection and Semantic Segmentation","created":"2019-04-25","cited_by_count":48},{"id":"2003.06409","title":"Probabilistic Future Prediction for Video Scene Understanding","created":"2020-03-13","cited_by_count":45},{"id":"2005.09202","title":"Multi-modal Sensor Fusion-Based Deep Neural Network for End-to-end Autonomous Driving with Scene Understanding","created":"2020-05-19","cited_by_count":42},{"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":"1707.05733","title":"Choosing Smartly: Adaptive Multimodal Fusion for Object Detection in Changing Environments","created":"2017-07-18","cited_by_count":34},{"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":"2204.00325","title":"CAT-Det: Contrastively Augmented Transformer for Multi-modal 3D Object Detection","created":"2022-04-01","cited_by_count":32},{"id":"2006.02000","title":"MultiXNet: Multiclass Multistage Multimodal Motion Prediction","created":"2020-06-03","cited_by_count":31},{"id":"1801.01726","title":"Semantic-aware Grad-GAN for Virtual-to-Real Urban Scene Adaption","created":"2018-01-05","cited_by_count":27},{"id":"2106.06452","title":"Keyframe-Focused Visual Imitation Learning","created":"2021-06-11","cited_by_count":25},{"id":"2008.04047","title":"Driving among Flatmobiles: Bird-Eye-View occupancy grids from a monocular camera for holistic trajectory planning","created":"2020-08-10","cited_by_count":24},{"id":"2011.01153","title":"Perceive, Attend, and Drive: Learning Spatial Attention for Safe Self-Driving","created":"2020-11-02","cited_by_count":24},{"id":"1901.02237","title":"3D Object Detection Using Scale Invariant and Feature Reweighting Networks","created":"2019-01-08","cited_by_count":23},{"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":"2104.10772","title":"MVFuseNet: Improving End-to-End Object Detection and Motion Forecasting through Multi-View Fusion of LiDAR Data","created":"2021-04-21","cited_by_count":18},{"id":"1811.03575","title":"Large-Scale Visual Active Learning with Deep Probabilistic Ensembles","created":"2018-11-08","cited_by_count":13},{"id":"1702.05596","title":"Brain Inspired Cognitive Model with Attention for Self-Driving Cars","created":"2017-02-18","cited_by_count":10},{"id":"2203.04421","title":"Leveraging Smooth Attention Prior for Multi-Agent Trajectory Prediction","created":"2022-03-08","cited_by_count":9},{"id":"2009.04554","title":"RoIFusion: 3D Object Detection from LiDAR and Vision","created":"2020-09-09","cited_by_count":6},{"id":"2010.12598","title":"A Software Architecture for Autonomous Vehicles: Team LRM-B Entry in the First CARLA Autonomous Driving Challenge","created":"2020-10-23","cited_by_count":5},{"id":"2203.16268","title":"Interactive Multi-scale Fusion of 2D and 3D Features for Multi-object Tracking","created":"2022-03-30","cited_by_count":4},{"id":"2101.03279","title":"Investigating the Effect of Sensor Modalities in Multi-Sensor Detection-Prediction Models","created":"2021-01-09","cited_by_count":3}],"next_cursor":"100"}