{"list":"other","total":57,"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":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"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":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"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":"2006.11275","title":"Center-based 3D Object Detection and Tracking","created":"2020-06-19","cited_by_count":1144},{"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":"2110.06864","title":"ByteTrack: Multi-Object Tracking by Associating Every Detection Box","created":"2021-10-13","cited_by_count":823},{"id":"1711.08488","title":"Frustum PointNets for 3D Object Detection from RGB-D Data","created":"2017-11-22","cited_by_count":640},{"id":"2005.04259","title":"VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation","created":"2020-05-08","cited_by_count":530},{"id":"2101.02702","title":"TrackFormer: Multi-Object Tracking with Transformers","created":"2021-01-07","cited_by_count":518},{"id":"1710.02410","title":"End-to-end Driving via Conditional Imitation Learning","created":"2017-10-06","cited_by_count":485},{"id":"2205.15997","title":"TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving","created":"2022-05-31","cited_by_count":485},{"id":"1911.10150","title":"PointPainting: Sequential Fusion for 3D Object Detection","created":"2019-11-22","cited_by_count":449},{"id":"2207.07115","title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","created":"2022-07-14","cited_by_count":439},{"id":"1912.12294","title":"Learning by Cheating","created":"2019-12-27","cited_by_count":383},{"id":"2104.09224","title":"Multi-Modal Fusion Transformer for End-to-End Autonomous Driving","created":"2021-04-19","cited_by_count":377},{"id":"2012.15460","title":"TransTrack: Multiple Object Tracking with Transformer","created":"2020-12-31","cited_by_count":371},{"id":"2207.07601","title":"ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning","created":"2022-07-15","cited_by_count":368},{"id":"1904.08980","title":"Exploring the Limitations of Behavior Cloning for Autonomous Driving","created":"2019-04-18","cited_by_count":346},{"id":"2203.14360","title":"Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking","created":"2022-03-27","cited_by_count":346},{"id":"2108.09640","title":"DenseTNT: End-to-end Trajectory Prediction from Dense Goal Sets","created":"2021-08-22","cited_by_count":295},{"id":"2206.08129","title":"Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline","created":"2022-06-16","cited_by_count":248},{"id":"2104.10490","title":"FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Cameras","created":"2021-04-21","cited_by_count":239},{"id":"2106.05392","title":"Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers","created":"2021-06-09","cited_by_count":224},{"id":"2207.14024","title":"Safety-Enhanced Autonomous Driving Using Interpretable Sensor Fusion Transformer","created":"2022-07-28","cited_by_count":212},{"id":"2106.05210","title":"Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation","created":"2021-06-09","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":"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":"2005.14711","title":"PnPNet: End-to-End Perception and Prediction with Tracking in the Loop","created":"2020-05-29","cited_by_count":144},{"id":"2203.11934","title":"Learning from All Vehicles","created":"2022-03-22","cited_by_count":135},{"id":"2007.12036","title":"Implicit Latent Variable Model for Scene-Consistent Motion Forecasting","created":"2020-07-23","cited_by_count":116},{"id":"2105.00636","title":"Learning to drive from a world on rails","created":"2021-05-03","cited_by_count":114},{"id":"2205.09753","title":"HDGT: Heterogeneous Driving Graph Transformer for Multi-Agent Trajectory Prediction via Scene Encoding","created":"2022-04-30","cited_by_count":110},{"id":"2003.06754","title":"MotionNet: Joint Perception and Motion Prediction for Autonomous Driving Based on Bird's Eye View Maps","created":"2020-03-15","cited_by_count":100},{"id":"2205.02222","title":"COOPERNAUT: End-to-End Driving with Cooperative Perception for Networked Vehicles","created":"2022-05-04","cited_by_count":95},{"id":"1911.06978","title":"Grounding Human-to-Vehicle Advice for Self-driving Vehicles","created":"2019-11-16","cited_by_count":71},{"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":"2008.05927","title":"End-to-end Contextual Perception and Prediction with Interaction Transformer","created":"2020-08-13","cited_by_count":54},{"id":"2001.06499","title":"Temporal Interlacing Network","created":"2020-01-17","cited_by_count":45},{"id":"2203.08563","title":"MonoJSG: Joint Semantic and Geometric Cost Volume for Monocular 3D Object Detection","created":"2022-03-16","cited_by_count":30},{"id":"2011.01153","title":"Perceive, Attend, and Drive: Learning Spatial Attention for Safe Self-Driving","created":"2020-11-02","cited_by_count":24},{"id":"2202.05140","title":"Transferable and Adaptable Driving Behavior Prediction","created":"2022-02-10","cited_by_count":20},{"id":"2010.14712","title":"Socially-Compatible Behavior Design of Autonomous Vehicles with Verification on Real Human Data","created":"2020-10-28","cited_by_count":18},{"id":"2104.05858","title":"Exploring Geometric Consistency for Monocular 3D Object Detection","created":"2021-04-12","cited_by_count":17},{"id":"2110.15156","title":"Blending Anti-Aliasing into Vision Transformer","created":"2021-10-28","cited_by_count":16},{"id":"2109.02173","title":"Multi-Agent Variational Occlusion Inference Using People as Sensors","created":"2021-09-05","cited_by_count":10},{"id":"2111.00788","title":"Hierarchical Adaptable and Transferable Networks (HATN) for Driving Behavior Prediction","created":"2021-11-01","cited_by_count":10},{"id":"1711.01022","title":"People as Sensors: Imputing Maps from Human Actions","created":"2017-11-03","cited_by_count":7}],"next_cursor":null}