{"list":"other","total":106,"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":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1603.08155","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","created":"2016-03-27","cited_by_count":2694},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"1812.05784","title":"PointPillars: Fast Encoders for Object Detection from Point Clouds","created":"2018-12-14","cited_by_count":1715},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"1711.06396","title":"VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection","created":"2017-11-17","cited_by_count":1323},{"id":"1811.04551","title":"Learning Latent Dynamics for Planning from Pixels","created":"2018-11-12","cited_by_count":1264},{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253},{"id":"2006.11275","title":"Center-based 3D Object Detection and Tracking","created":"2020-06-19","cited_by_count":1144},{"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":"2010.02193","title":"Mastering Atari with Discrete World Models","created":"2020-10-05","cited_by_count":1007},{"id":"1912.13192","title":"PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection","created":"2019-12-31","cited_by_count":891},{"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":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808},{"id":"1809.01999","title":"Recurrent World Models Facilitate Policy Evolution","created":"2018-09-04","cited_by_count":785},{"id":"1711.10275","title":"3D Semantic Segmentation with Submanifold Sparse Convolutional Networks","created":"2017-11-28","cited_by_count":748},{"id":"2106.02039","title":"Offline Reinforcement Learning as One Big Sequence Modeling Problem","created":"2021-06-03","cited_by_count":644},{"id":"2109.13410","title":"KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D","created":"2021-09-28","cited_by_count":575},{"id":"1903.00374","title":"Model-Based Reinforcement Learning for Atari","created":"2019-03-01","cited_by_count":502},{"id":"2205.15997","title":"TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving","created":"2022-05-31","cited_by_count":485},{"id":"1611.08974","title":"Semantic Scene Completion from a Single Depth Image","created":"2016-11-28","cited_by_count":472},{"id":"2203.11496","title":"TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers","created":"2022-03-22","cited_by_count":466},{"id":"2007.16100","title":"Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution","created":"2020-07-31","cited_by_count":423},{"id":"2012.15712","title":"Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detection","created":"2020-12-31","cited_by_count":410},{"id":"2302.07817","title":"Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction","created":"2023-02-15","cited_by_count":409},{"id":"2206.14176","title":"DayDreamer: World Models for Physical Robot Learning","created":"2022-06-28","cited_by_count":400},{"id":"2203.04955","title":"Temporal Difference Learning for Model Predictive Control","created":"2022-03-09","cited_by_count":397},{"id":"2112.00726","title":"MonoScene: Monocular 3D Semantic Scene Completion","created":"2021-12-01","cited_by_count":363},{"id":"1908.09492","title":"Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection","created":"2019-08-26","cited_by_count":350},{"id":"2205.13790","title":"BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework","created":"2022-05-27","cited_by_count":336},{"id":"2209.00588","title":"Transformers are Sample-Efficient World Models","created":"2022-09-01","cited_by_count":328},{"id":"2303.09551","title":"SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving","created":"2023-03-16","cited_by_count":316},{"id":"2302.12251","title":"VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion","created":"2023-02-23","cited_by_count":313},{"id":"2304.05316","title":"OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction","created":"2023-04-11","cited_by_count":293},{"id":"2109.02497","title":"Voxel Transformer for 3D Object Detection","created":"2021-09-06","cited_by_count":247},{"id":"2101.06679","title":"End-to-end Interpretable Neural Motion Planner","created":"2021-01-17","cited_by_count":242},{"id":"2102.00463","title":"PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection","created":"2021-01-31","cited_by_count":232},{"id":"2012.03762","title":"Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion","created":"2020-12-07","cited_by_count":223},{"id":"2303.03991","title":"OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perception","created":"2023-03-07","cited_by_count":221},{"id":"2207.14024","title":"Safety-Enhanced Autonomous Driving Using Interpretable Sensor Fusion Transformer","created":"2022-07-28","cited_by_count":212},{"id":"2306.02851","title":"Scene as Occupancy","created":"2023-06-05","cited_by_count":209},{"id":"2206.00630","title":"Unifying Voxel-based Representation with Transformer for 3D Object Detection","created":"2022-06-01","cited_by_count":202},{"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":"2112.06375","title":"Embracing Single Stride 3D Object Detector with Sparse Transformer","created":"2021-12-13","cited_by_count":193},{"id":"2112.12610","title":"PandaSet: Advanced Sensor Suite Dataset for Autonomous Driving","created":"2021-12-23","cited_by_count":190},{"id":"2103.12978","title":"RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentation","created":"2021-03-24","cited_by_count":173},{"id":"2206.14244","title":"Masked World Models for Visual Control","created":"2022-06-28","cited_by_count":170},{"id":"2305.06242","title":"Think Twice before Driving: Towards Scalable Decoders for End-to-End Autonomous Driving","created":"2023-05-10","cited_by_count":169},{"id":"2307.01492","title":"FB-OCC: 3D Occupancy Prediction based on Forward-Backward View Transformation","created":"2023-07-04","cited_by_count":165},{"id":"2206.02680","title":"Separable Self-attention for Mobile Vision Transformers","created":"2022-06-06","cited_by_count":163},{"id":"2106.01178","title":"ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection","created":"2021-06-02","cited_by_count":157},{"id":"2210.07729","title":"Model-Based Imitation Learning for Urban Driving","created":"2022-10-14","cited_by_count":150},{"id":"2308.10901","title":"Structured World Models from Human Videos","created":"2023-08-21","cited_by_count":147},{"id":"2309.09502","title":"RenderOcc: Vision-Centric 3D Occupancy Prediction with 2D Rendering Supervision","created":"2023-09-18","cited_by_count":128},{"id":"2104.15060","title":"DriveGAN: Towards a Controllable High-Quality Neural Simulation","created":"2021-04-30","cited_by_count":125},{"id":"2208.11112","title":"DeepInteraction: 3D Object Detection via Modality Interaction","created":"2022-08-23","cited_by_count":125},{"id":"2301.06051","title":"DSVT: Dynamic Sparse Voxel Transformer with Rotated Sets","created":"2023-01-15","cited_by_count":122},{"id":"2306.10013","title":"PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentation","created":"2023-06-16","cited_by_count":115},{"id":"1608.07916","title":"Vehicle Detection from 3D Lidar Using Fully Convolutional Network","created":"2016-08-29","cited_by_count":107},{"id":"2001.08726","title":"Interpretable End-to-end Urban Autonomous Driving with Latent Deep Reinforcement Learning","created":"2020-01-23","cited_by_count":103},{"id":"2306.15670","title":"Symphonize 3D Semantic Scene Completion with Contextual Instance Queries","created":"2023-06-27","cited_by_count":90},{"id":"2005.12126","title":"Learning to Simulate Dynamic Environments with GameGAN","created":"2020-05-25","cited_by_count":86},{"id":"2302.13540","title":"OccDepth: A Depth-Aware Method for 3D Semantic Scene Completion","created":"2023-02-27","cited_by_count":86},{"id":"2304.14340","title":"SparseFusion: Fusing Multi-Modal Sparse Representations for Multi-Sensor 3D Object Detection","created":"2023-04-27","cited_by_count":83},{"id":"2003.00186","title":"HVNet: Hybrid Voxel Network for LiDAR Based 3D Object Detection","created":"2020-02-29","cited_by_count":82},{"id":"2303.03595","title":"LoGoNet: Towards Accurate 3D Object Detection with Local-to-Global Cross-Modal Fusion","created":"2023-03-07","cited_by_count":80},{"id":"2202.02703","title":"Multi-modal Sensor Fusion for Auto Driving Perception: A Survey","created":"2022-02-06","cited_by_count":76},{"id":"2011.09141","title":"Semantic Scene Completion using Local Deep Implicit Functions on LiDAR Data","created":"2020-11-18","cited_by_count":74},{"id":"2203.05662","title":"Point Density-Aware Voxels for LiDAR 3D Object Detection","created":"2022-03-10","cited_by_count":70},{"id":"2301.07668","title":"Behind the Scenes: Density Fields for Single View Reconstruction","created":"2023-01-18","cited_by_count":63},{"id":"2206.09900","title":"Occupancy-MAE: Self-supervised Pre-training Large-scale LiDAR Point Clouds with Masked Occupancy Autoencoders","created":"2022-06-20","cited_by_count":58},{"id":"2111.10502","title":"CamLiFlow: Bidirectional Camera-LiDAR Fusion for Joint Optical Flow and Scene Flow Estimation","created":"2021-11-20","cited_by_count":56},{"id":"2205.13817","title":"Iso-Dream: Isolating and Leveraging Noncontrollable Visual Dynamics in World Models","created":"2022-05-27","cited_by_count":53},{"id":"1901.02705","title":"Model-Predictive Policy Learning with Uncertainty Regularization for Driving in Dense Traffic","created":"2019-01-08","cited_by_count":50},{"id":"2212.02501","title":"SceneRF: Self-Supervised Monocular 3D Scene Reconstruction with Radiance Fields","created":"2022-12-05","cited_by_count":49},{"id":"2211.12740","title":"Masked Autoencoding for Scalable and Generalizable Decision Making","created":"2022-11-23","cited_by_count":45},{"id":"2305.02968","title":"Masked Trajectory Models for Prediction, Representation, and Control","created":"2023-05-04","cited_by_count":42},{"id":"2207.00531","title":"Masked Autoencoder for Self-Supervised Pre-training on Lidar Point Clouds","created":"2022-07-01","cited_by_count":39},{"id":"2310.07522","title":"S4C: Self-Supervised Semantic Scene Completion with Neural Fields","created":"2023-10-11","cited_by_count":28},{"id":"2303.13510","title":"MV-JAR: Masked Voxel Jigsaw and Reconstruction for LiDAR-Based Self-Supervised Pre-Training","created":"2023-03-23","cited_by_count":26},{"id":"2306.09117","title":"UniOcc: Unifying Vision-Centric 3D Occupancy Prediction with Geometric and Semantic Rendering","created":"2023-06-15","cited_by_count":26},{"id":"2309.15082","title":"RPEFlow: Multimodal Fusion of RGB-PointCloud-Event for Joint Optical Flow and Scene Flow Estimation","created":"2023-09-26","cited_by_count":26},{"id":"2303.01212","title":"Grid-Centric Traffic Scenario Perception for Autonomous Driving: A Comprehensive Review","created":"2023-03-02","cited_by_count":25},{"id":"2310.11239","title":"LiDAR-based 4D Occupancy Completion and Forecasting","created":"2023-10-17","cited_by_count":23},{"id":"2212.07289","title":"ConQueR: Query Contrast Voxel-DETR for 3D Object Detection","created":"2022-12-14","cited_by_count":21},{"id":"2305.06621","title":"PVT-SSD: Single-Stage 3D Object Detector with Point-Voxel Transformer","created":"2023-05-11","cited_by_count":21},{"id":"2308.01686","title":"LiDAR-Camera Panoptic Segmentation via Geometry-Consistent and Semantic-Aware Alignment","created":"2023-08-03","cited_by_count":18},{"id":"2307.02427","title":"FOCUS: Object-Centric World Models for Robotics Manipulation","created":"2023-07-05","cited_by_count":17},{"id":"2004.02724","title":"Reconfigurable Voxels: A New Representation for LiDAR-Based Point Clouds","created":"2020-04-06","cited_by_count":16}],"next_cursor":"100"}