{"list":"other","total":183,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"1706.02413","title":"PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space","created":"2017-06-07","cited_by_count":4401},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"2006.09661","title":"Implicit Neural Representations with Periodic Activation Functions","created":"2020-06-17","cited_by_count":2238},{"id":"1812.05784","title":"PointPillars: Fast Encoders for Object Detection from Point Clouds","created":"2018-12-14","cited_by_count":1715},{"id":"2104.02057","title":"An Empirical Study of Training Self-Supervised Vision Transformers","created":"2021-04-05","cited_by_count":1616},{"id":"1705.07115","title":"Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics","created":"2017-05-19","cited_by_count":1358},{"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":"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":"1904.08755","title":"4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks","created":"2019-04-18","cited_by_count":1208},{"id":"2111.09886","title":"SimMIM: A Simple Framework for Masked Image Modeling","created":"2021-11-18","cited_by_count":1153},{"id":"2006.11275","title":"Center-based 3D Object Detection and Tracking","created":"2020-06-19","cited_by_count":1144},{"id":"2202.04200","title":"MaskGIT: Masked Generative Image Transformer","created":"2022-02-08","cited_by_count":1099},{"id":"2212.10156","title":"Planning-oriented Autonomous Driving","created":"2022-12-20","cited_by_count":1087},{"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":"1911.09070","title":"EfficientDet: Scalable and Efficient Object Detection","created":"2019-11-20","cited_by_count":1020},{"id":"1502.00956","title":"ORB-SLAM: a Versatile and Accurate Monocular SLAM System","created":"2015-02-03","cited_by_count":988},{"id":"2003.13678","title":"Designing Network Design Spaces","created":"2020-03-30","cited_by_count":960},{"id":"1812.04244","title":"PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud","created":"2018-12-11","cited_by_count":941},{"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":"2011.13084","title":"Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes","created":"2020-11-26","cited_by_count":751},{"id":"1711.10275","title":"3D Semantic Segmentation with Submanifold Sparse Convolutional Networks","created":"2017-11-28","cited_by_count":748},{"id":"1911.02620","title":"Argoverse: 3D Tracking and Forecasting with Rich Maps","created":"2019-11-06","cited_by_count":732},{"id":"1611.07759","title":"Multi-View 3D Object Detection Network for Autonomous Driving","created":"2016-11-23","cited_by_count":724},{"id":"2202.05263","title":"Block-NeRF: Scalable Large Scene Neural View Synthesis","created":"2022-02-10","cited_by_count":724},{"id":"2112.11790","title":"BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View","created":"2021-12-22","cited_by_count":713},{"id":"2301.00493","title":"Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting","created":"2023-01-02","cited_by_count":707},{"id":"1710.07035","title":"Generative Adversarial Networks: An Overview","created":"2017-10-19","cited_by_count":590},{"id":"2112.12130","title":"NICE-SLAM: Neural Implicit Scalable Encoding for SLAM","created":"2021-12-22","cited_by_count":589},{"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":"2206.10092","title":"BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detection","created":"2022-06-21","cited_by_count":572},{"id":"2203.05625","title":"PETR: Position Embedding Transformation for Multi-View 3D Object Detection","created":"2022-03-10","cited_by_count":552},{"id":"2007.10985","title":"PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding","created":"2020-07-21","cited_by_count":504},{"id":"2211.05778","title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","created":"2022-11-10","cited_by_count":482},{"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":"2203.06604","title":"Masked Autoencoders for Point Cloud Self-supervised Learning","created":"2022-03-13","cited_by_count":459},{"id":"2302.07817","title":"Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction","created":"2023-02-15","cited_by_count":409},{"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":"2112.00726","title":"MonoScene: Monocular 3D Semantic Scene Completion","created":"2021-12-01","cited_by_count":363},{"id":"1902.06326","title":"PIXOR: Real-time 3D Object Detection from Point Clouds","created":"2019-02-17","cited_by_count":358},{"id":"2206.01256","title":"PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images","created":"2022-06-02","cited_by_count":352},{"id":"2203.17054","title":"BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detection","created":"2022-03-31","cited_by_count":341},{"id":"2205.13790","title":"BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework","created":"2022-05-27","cited_by_count":336},{"id":"2103.01100","title":"Categorical Depth Distribution Network for Monocular 3D Object Detection","created":"2021-03-01","cited_by_count":327},{"id":"1712.02294","title":"Joint 3D Proposal Generation and Object Detection from View Aggregation","created":"2017-12-06","cited_by_count":326},{"id":"2208.14437","title":"MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction","created":"2022-08-30","cited_by_count":314},{"id":"2302.12251","title":"VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion","created":"2023-02-23","cited_by_count":313},{"id":"2103.02603","title":"Towards Open World Object Detection","created":"2021-03-03","cited_by_count":297},{"id":"2201.00520","title":"Vision Transformer with Deformable Attention","created":"2022-01-03","cited_by_count":295},{"id":"2107.06307","title":"HDMapNet: An Online HD Map Construction and Evaluation Framework","created":"2021-07-13","cited_by_count":281},{"id":"2205.02833","title":"Cross-view Transformers for real-time Map-view Semantic Segmentation","created":"2022-05-05","cited_by_count":264},{"id":"2111.14643","title":"Urban Radiance Fields","created":"2021-11-29","cited_by_count":263},{"id":"2206.08920","title":"VectorMapNet: End-to-end Vectorized HD Map Learning","created":"2022-06-17","cited_by_count":245},{"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":"2207.02202","title":"CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse Transformers","created":"2022-07-05","cited_by_count":227},{"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":"2106.11037","title":"One Million Scenes for Autonomous Driving: ONCE Dataset","created":"2021-06-21","cited_by_count":218},{"id":"2101.02691","title":"Self-Supervised Pretraining of 3D Features on any Point-Cloud","created":"2021-01-07","cited_by_count":217},{"id":"2101.06806","title":"MP3: A Unified Model to Map, Perceive, Predict and Plan","created":"2021-01-18","cited_by_count":212},{"id":"1811.08188","title":"Orthographic Feature Transform for Monocular 3D Object Detection","created":"2018-11-20","cited_by_count":202},{"id":"2206.00630","title":"Unifying Voxel-based Representation with Transformer for 3D Object Detection","created":"2022-06-01","cited_by_count":202},{"id":"2203.10642","title":"FUTR3D: A Unified Sensor Fusion Framework for 3D Detection","created":"2022-03-20","cited_by_count":194},{"id":"2205.09743","title":"BEVerse: Unified Perception and Prediction in Birds-Eye-View for Vision-Centric Autonomous Driving","created":"2022-05-19","cited_by_count":191},{"id":"2008.10559","title":"LMSCNet: Lightweight Multiscale 3D Semantic Completion","created":"2020-08-24","cited_by_count":188},{"id":"2210.13641","title":"NeRF-SLAM: Real-Time Dense Monocular SLAM with Neural Radiance Fields","created":"2022-10-24","cited_by_count":188},{"id":"2208.12262","title":"MaskCLIP: Masked Self-Distillation Advances Contrastive Language-Image Pretraining","created":"2022-08-25","cited_by_count":187},{"id":"2210.02443","title":"Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detection","created":"2022-10-05","cited_by_count":178},{"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":"2210.00379","title":"NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (Updated Post-Gaussian Splatting)","created":"2022-10-01","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":"1611.03631","title":"Voxblox: Incremental 3D Euclidean Signed Distance Fields for On-Board MAV Planning","created":"2016-11-11","cited_by_count":150},{"id":"2210.07729","title":"Model-Based Imitation Learning for Urban Driving","created":"2022-10-14","cited_by_count":150},{"id":"2206.15398","title":"PolarFormer: Multi-camera 3D Object Detection with Polar Transformer","created":"2022-06-30","cited_by_count":147},{"id":"2006.11339","title":"Video Panoptic Segmentation","created":"2020-06-19","cited_by_count":142},{"id":"2203.11089","title":"PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark","created":"2022-03-21","cited_by_count":140},{"id":"2206.09474","title":"3D Object Detection for Autonomous Driving: A Comprehensive Survey","created":"2022-06-19","cited_by_count":132},{"id":"2112.01513","title":"OW-DETR: Open-world Detection Transformer","created":"2021-12-02","cited_by_count":129},{"id":"2206.07959","title":"Simple-BEV: What Really Matters for Multi-Sensor BEV Perception?","created":"2022-06-16","cited_by_count":128},{"id":"2004.02122","title":"Anisotropic Convolutional Networks for 3D Semantic Scene Completion","created":"2020-04-05","cited_by_count":127},{"id":"2003.14052","title":"3D Sketch-aware Semantic Scene Completion via Semi-supervised Structure Prior","created":"2020-03-31","cited_by_count":126},{"id":"2208.02797","title":"Vision-Centric BEV Perception: A Survey","created":"2022-08-04","cited_by_count":126},{"id":"2208.11112","title":"DeepInteraction: 3D Object Detection via Modality Interaction","created":"2022-08-23","cited_by_count":125},{"id":"2203.04050","title":"BEVSegFormer: Bird's Eye View Semantic Segmentation From Arbitrary Camera Rigs","created":"2022-03-08","cited_by_count":123},{"id":"2209.05324","title":"Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipe","created":"2022-09-12","cited_by_count":122},{"id":"1906.08945","title":"Rules of the Road: Predicting Driving Behavior with a Convolutional Model of Semantic Interactions","created":"2019-06-21","cited_by_count":117}],"next_cursor":"100"}