{"list":"other","total":69,"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":"1901.05103","title":"DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation","created":"2019-01-16","cited_by_count":2689},{"id":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"id":"2006.09661","title":"Implicit Neural Representations with Periodic Activation Functions","created":"2020-06-17","cited_by_count":2238},{"id":"1812.03828","title":"Occupancy Networks: Learning 3D Reconstruction in Function Space","created":"2018-12-10","cited_by_count":2041},{"id":"1812.02822","title":"Learning Implicit Fields for Generative Shape Modeling","created":"2018-12-06","cited_by_count":1060},{"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":"1604.07316","title":"End to End Learning for Self-Driving Cars","created":"2016-04-25","cited_by_count":1009},{"id":"1906.01618","title":"Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations","created":"2019-06-04","cited_by_count":864},{"id":"1905.05172","title":"PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization","created":"2019-05-13","cited_by_count":818},{"id":"2003.04618","title":"Convolutional Occupancy Networks","created":"2020-03-10","cited_by_count":761},{"id":"2011.13084","title":"Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes","created":"2020-11-26","cited_by_count":751},{"id":"1912.07372","title":"Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervision","created":"2019-12-16","cited_by_count":700},{"id":"2007.02442","title":"GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis","created":"2020-07-05","cited_by_count":689},{"id":"1710.02410","title":"End-to-end Driving via Conditional Imitation Learning","created":"2017-10-06","cited_by_count":485},{"id":"1811.06711","title":"An Algorithmic Perspective on Imitation Learning","created":"2018-11-16","cited_by_count":459},{"id":"2011.12950","title":"Space-time Neural Irradiance Fields for Free-Viewpoint Video","created":"2020-11-25","cited_by_count":414},{"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":"2003.08981","title":"Local Implicit Grid Representations for 3D Scenes","created":"2020-03-19","cited_by_count":373},{"id":"1904.08980","title":"Exploring the Limitations of Behavior Cloning for Autonomous Driving","created":"2019-04-18","cited_by_count":346},{"id":"2003.01456","title":"Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion","created":"2020-03-03","cited_by_count":343},{"id":"1905.10711","title":"DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction","created":"2019-05-26","cited_by_count":333},{"id":"2003.10983","title":"Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstruction","created":"2020-03-24","cited_by_count":321},{"id":"2012.09790","title":"Neural Radiance Flow for 4D View Synthesis and Video Processing","created":"2020-12-17","cited_by_count":270},{"id":"1904.06447","title":"Learning Shape Templates with Structured Implicit Functions","created":"2019-04-12","cited_by_count":242},{"id":"2101.06679","title":"End-to-end Interpretable Neural Motion Planner","created":"2021-01-17","cited_by_count":242},{"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":"1606.00704","title":"Adversarially Learned Inference","created":"2016-06-02","cited_by_count":216},{"id":"2006.09662","title":"MetaSDF: Meta-learning Signed Distance Functions","created":"2020-06-17","cited_by_count":214},{"id":"2101.06806","title":"MP3: A Unified Model to Map, Perceive, Predict and Plan","created":"2021-01-18","cited_by_count":212},{"id":"1905.07259","title":"Texture Fields: Learning Texture Representations in Function Space","created":"2019-05-17","cited_by_count":210},{"id":"1911.06971","title":"BSP-Net: Generating Compact Meshes via Binary Space Partitioning","created":"2019-11-16","cited_by_count":206},{"id":"1704.05519","title":"Computer Vision for Autonomous Vehicles: Problems, Datasets and State of the Art","created":"2017-04-18","cited_by_count":182},{"id":"1911.13225","title":"DIST: Rendering Deep Implicit Signed Distance Function with Differentiable Sphere Tracing","created":"2019-11-29","cited_by_count":180},{"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":"1909.05736","title":"CvxNet: Learnable Convex Decomposition","created":"2019-09-12","cited_by_count":174},{"id":"1707.00683","title":"Modulating early visual processing by language","created":"2017-07-02","cited_by_count":167},{"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":"2006.14911","title":"Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?","created":"2020-06-26","cited_by_count":139},{"id":"2003.06404","title":"A Survey of End-to-End Driving: Architectures and Training Methods","created":"2020-03-13","cited_by_count":123},{"id":"1901.07017","title":"Spatial Broadcast Decoder: A Simple Architecture for Learning Disentangled Representations in VAEs","created":"2019-01-21","cited_by_count":117},{"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":"1911.00767","title":"Learning to Infer Implicit Surfaces without 3D Supervision","created":"2019-11-02","cited_by_count":103},{"id":"1804.09364","title":"Driving Policy Transfer via Modularity and Abstraction","created":"2018-04-25","cited_by_count":92},{"id":"2010.14876","title":"Fighting Copycat Agents in Behavioral Cloning from Observation Histories","created":"2020-10-28","cited_by_count":71},{"id":"1806.06498","title":"Conditional Affordance Learning for Driving in Urban Environments","created":"2018-06-18","cited_by_count":70},{"id":"1809.04843","title":"On Offline Evaluation of Vision-based Driving Models","created":"2018-09-13","cited_by_count":64},{"id":"2006.09917","title":"FISHING Net: Future Inference of Semantic Heatmaps In Grids","created":"2020-06-17","cited_by_count":55},{"id":"2002.08394","title":"MonoLayout: Amodal scene layout from a single image","created":"2020-02-19","cited_by_count":49},{"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":"1905.06937","title":"Monocular Plan View Networks for Autonomous Driving","created":"2019-05-16","cited_by_count":37},{"id":"1505.00295","title":"Dense Optical Flow Prediction from a Static Image","created":"2015-05-02","cited_by_count":36},{"id":"1905.02231","title":"A Geometric Approach to Obtain a Bird's Eye View from an Image","created":"2019-05-06","cited_by_count":34},{"id":"2005.10091","title":"Label Efficient Visual Abstractions for Autonomous Driving","created":"2020-05-20","cited_by_count":33},{"id":"1806.03960","title":"AGIL: Learning Attention from Human for Visuomotor Tasks","created":"2018-06-01","cited_by_count":32},{"id":"1801.01726","title":"Semantic-aware Grad-GAN for Virtual-to-Real Urban Scene Adaption","created":"2018-01-05","cited_by_count":27},{"id":"1808.00327","title":"Generative Adversarial Frontal View to Bird View Synthesis","created":"2018-08-01","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":"2003.12406","title":"Learning Implicit Surface Light Fields","created":"2020-03-27","cited_by_count":23},{"id":"2005.03863","title":"Learning hierarchical behavior and motion planning for autonomous driving","created":"2020-05-08","cited_by_count":15},{"id":"2008.09417","title":"Action-Based Representation Learning for Autonomous Driving","created":"2020-08-21","cited_by_count":11},{"id":"2008.12969","title":"Driving Through Ghosts: Behavioral Cloning with False Positives","created":"2020-08-29","cited_by_count":8}],"next_cursor":null}