{"list":"other","total":154,"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":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1606.00915","title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","created":"2016-06-02","cited_by_count":3241},{"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":"1704.00028","title":"Improved Training of Wasserstein GANs","created":"2017-03-31","cited_by_count":2235},{"id":"1703.06211","title":"Deformable Convolutional Networks","created":"2017-03-17","cited_by_count":1488},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"id":"1712.00726","title":"Cascade R-CNN: Delving into High Quality Object Detection","created":"2017-12-03","cited_by_count":1276},{"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":"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":"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":"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":"1811.11168","title":"Deformable ConvNets v2: More Deformable, Better Results","created":"2018-11-27","cited_by_count":670},{"id":"2110.06922","title":"DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries","created":"2021-10-13","cited_by_count":658},{"id":"1808.00897","title":"BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation","created":"2018-08-02","cited_by_count":645},{"id":"2303.12077","title":"VAD: Vectorized Scene Representation for Efficient Autonomous Driving","created":"2023-03-21","cited_by_count":622},{"id":"2201.12329","title":"DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR","created":"2022-01-28","cited_by_count":573},{"id":"2203.05625","title":"PETR: Position Embedding Transformation for Multi-View 3D Object Detection","created":"2022-03-10","cited_by_count":552},{"id":"2312.14150","title":"DriveLM: Driving with Graph Visual Question Answering","created":"2023-12-21","cited_by_count":536},{"id":"2011.12450","title":"Sparse R-CNN: End-to-End Object Detection with Learnable Proposals","created":"2020-11-25","cited_by_count":495},{"id":"2104.10956","title":"FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection","created":"2021-04-22","cited_by_count":447},{"id":"1904.02689","title":"YOLACT: Real-time Instance Segmentation","created":"2019-04-04","cited_by_count":443},{"id":"2108.06152","title":"Conditional DETR for Fast Training Convergence","created":"2021-08-13","cited_by_count":424},{"id":"2206.01256","title":"PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images","created":"2022-06-02","cited_by_count":352},{"id":"2205.13790","title":"BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework","created":"2022-05-27","cited_by_count":336},{"id":"2208.14437","title":"MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction","created":"2022-08-30","cited_by_count":314},{"id":"1606.02147","title":"ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation","created":"2016-06-07","cited_by_count":291},{"id":"2402.13243","title":"VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planning","created":"2024-02-20","cited_by_count":289},{"id":"2107.06307","title":"HDMapNet: An Online HD Map Construction and Evaluation Framework","created":"2021-07-13","cited_by_count":281},{"id":"1611.02167","title":"Designing Neural Network Architectures using Reinforcement Learning","created":"2016-11-07","cited_by_count":279},{"id":"1904.04971","title":"CondConv: Conditionally Parameterized Convolutions for Efficient Inference","created":"2019-04-10","cited_by_count":273},{"id":"2204.05575","title":"DAIR-V2X: A Large-Scale Dataset for Vehicle-Infrastructure Cooperative 3D Object Detection","created":"2022-04-12","cited_by_count":273},{"id":"2209.08575","title":"SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation","created":"2022-09-18","cited_by_count":252},{"id":"2206.08920","title":"VectorMapNet: End-to-end Vectorized HD Map Learning","created":"2022-06-17","cited_by_count":245},{"id":"2405.19620","title":"SparseDrive: End-to-End Autonomous Driving via Sparse Scene Representation","created":"2024-05-30","cited_by_count":241},{"id":"2402.11502","title":"GenAD: Generative End-to-End Autonomous Driving","created":"2024-02-18","cited_by_count":225},{"id":"2106.11037","title":"One Million Scenes for Autonomous Driving: ONCE Dataset","created":"2021-06-21","cited_by_count":218},{"id":"2309.16292","title":"DiLu: A Knowledge-Driven Approach to Autonomous Driving with Large Language Models","created":"2023-09-28","cited_by_count":207},{"id":"2002.10111","title":"SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimation","created":"2020-02-24","cited_by_count":204},{"id":"2308.05736","title":"MapTRv2: An End-to-End Framework for Online Vectorized HD Map Construction","created":"2023-08-10","cited_by_count":193},{"id":"1803.06184","title":"The ApolloScape Open Dataset for Autonomous Driving and its Application","created":"2018-03-16","cited_by_count":190},{"id":"1712.06080","title":"Spatial As Deep: Spatial CNN for Traffic Scene Understanding","created":"2017-12-17","cited_by_count":187},{"id":"1906.03560","title":"Cross-view Semantic Segmentation for Sensing Surroundings","created":"2019-06-09","cited_by_count":174},{"id":"1908.00821","title":"Learning Lightweight Lane Detection CNNs by Self Attention Distillation","created":"2019-08-02","cited_by_count":162},{"id":"2308.12570","title":"StreamMapNet: Streaming Mapping Network for Vectorized Online HD Map Construction","created":"2023-08-24","cited_by_count":145},{"id":"2103.16237","title":"Delving into Localization Errors for Monocular 3D Object Detection","created":"2021-03-30","cited_by_count":140},{"id":"2203.11089","title":"PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark","created":"2022-03-21","cited_by_count":140},{"id":"1802.05591","title":"Towards End-to-End Lane Detection: an Instance Segmentation Approach","created":"2018-02-15","cited_by_count":129},{"id":"2004.11757","title":"Ultra Fast Structure-aware Deep Lane Detection","created":"2020-04-24","cited_by_count":122},{"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":"2011.04233","title":"End-to-end Lane Shape Prediction with Transformers","created":"2020-11-09","cited_by_count":111},{"id":"1811.10203","title":"3D-LaneNet: End-to-End 3D Multiple Lane Detection","created":"2018-11-26","cited_by_count":107},{"id":"2110.01997","title":"Structured Bird's-Eye-View Traffic Scene Understanding from Onboard Images","created":"2021-10-05","cited_by_count":98},{"id":"2004.10924","title":"PolyLaneNet: Lane Estimation via Deep Polynomial Regression","created":"2020-04-23","cited_by_count":95},{"id":"2105.05003","title":"CondLaneNet: a Top-to-down Lane Detection Framework Based on Conditional Convolution","created":"2021-05-11","cited_by_count":95},{"id":"2203.02431","title":"Rethinking Efficient Lane Detection via Curve Modeling","created":"2022-03-04","cited_by_count":88},{"id":"2308.16477","title":"PivotNet: Vectorized Pivot Learning for End-to-end HD Map Construction","created":"2023-08-31","cited_by_count":85},{"id":"2304.10440","title":"OpenLane-V2: A Topology Reasoning Benchmark for Unified 3D HD Mapping","created":"2023-04-20","cited_by_count":83},{"id":"2108.11250","title":"YOLOP: You Only Look Once for Panoptic Driving Perception","created":"2021-08-25","cited_by_count":82},{"id":"2203.10350","title":"CLRNet: Cross Layer Refinement Network for Lane Detection","created":"2022-03-19","cited_by_count":82},{"id":"2306.09700","title":"End-to-End Vectorized HD-map Construction with Piecewise Bezier Curve","created":"2023-06-16","cited_by_count":82},{"id":"2203.13608","title":"Rope3D: TheRoadside Perception Dataset for Autonomous Driving and Monocular 3D Object Detection Task","created":"2022-03-25","cited_by_count":81},{"id":"2211.11943","title":"Conv2Former: A Simple Transformer-Style ConvNet for Visual Recognition","created":"2022-11-22","cited_by_count":81},{"id":"2007.12147","title":"CurveLane-NAS: Unifying Lane-Sensitive Architecture Search and Adaptive Point Blending","created":"2020-07-23","cited_by_count":80},{"id":"2002.06604","title":"Key Points Estimation and Point Instance Segmentation Approach for Lane Detection","created":"2020-02-16","cited_by_count":77},{"id":"2008.13719","title":"RESA: Recurrent Feature-Shift Aggregator for Lane Detection","created":"2020-08-31","cited_by_count":77},{"id":"2003.10656","title":"Gen-LaneNet: A Generalized and Scalable Approach for 3D Lane Detection","created":"2020-03-24","cited_by_count":75},{"id":"2303.08498","title":"BEVHeight: A Robust Framework for Vision-based Roadside 3D Object Detection","created":"2023-03-15","cited_by_count":75},{"id":"2308.07732","title":"UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representation","created":"2023-08-15","cited_by_count":74},{"id":"2204.07335","title":"A Keypoint-based Global Association Network for Lane Detection","created":"2022-04-15","cited_by_count":68},{"id":"2403.15951","title":"MapTracker: Tracking with Strided Memory Fusion for Consistent Vector HD Mapping","created":"2024-03-23","cited_by_count":68},{"id":"2308.01006","title":"FusionAD: Multi-modality Fusion for Prediction and Planning Tasks of Autonomous Driving","created":"2023-08-02","cited_by_count":67},{"id":"2105.13680","title":"Focus on Local: Detecting Lane Marker from Bottom Up via Key Point","created":"2021-05-28","cited_by_count":65},{"id":"2004.05304","title":"Inter-Region Affinity Distillation for Road Marking Segmentation","created":"2020-04-11","cited_by_count":58},{"id":"2312.16108","title":"LaneSegNet: Map Learning with Lane Segment Perception for Autonomous Driving","created":"2023-12-26","cited_by_count":57},{"id":"1710.06288","title":"VPGNet: Vanishing Point Guided Network for Lane and Road Marking Detection and Recognition","created":"2017-10-17","cited_by_count":56},{"id":"2304.05277","title":"Graph-based Topology Reasoning for Driving Scenes","created":"2023-04-11","cited_by_count":54},{"id":"2303.08815","title":"Lane Graph as Path: Continuity-preserving Path-wise Modeling for Online Lane Graph Construction","created":"2023-03-15","cited_by_count":50},{"id":"2301.02371","title":"Anchor3DLane: Learning to Regress 3D Anchors for Monocular 3D Lane Detection","created":"2023-01-06","cited_by_count":48},{"id":"2403.08639","title":"HIMap: HybrId Representation Learning for End-to-end Vectorized HD Map Construction","created":"2024-03-13","cited_by_count":48},{"id":"2005.08630","title":"End-to-End Lane Marker Detection via Row-wise Classification","created":"2020-05-06","cited_by_count":47},{"id":"2205.00301","title":"ONCE-3DLanes: Building Monocular 3D Lane Detection","created":"2022-04-30","cited_by_count":44},{"id":"2308.04583","title":"LATR: 3D Lane Detection from Monocular Images with Transformer","created":"2023-08-08","cited_by_count":44},{"id":"1411.7113","title":"Real time Detection of Lane Markers in Urban Streets","created":"2014-11-26","cited_by_count":41},{"id":"1903.02193","title":"Robust Lane Detection from Continuous Driving Scenes Using Deep Neural Networks","created":"2019-03-06","cited_by_count":41},{"id":"2103.12040","title":"LaneAF: Robust Multi-Lane Detection with Affinity Fields","created":"2021-03-22","cited_by_count":41},{"id":"2310.06753","title":"TopoMLP: A Simple yet Strong Pipeline for Driving Topology Reasoning","created":"2023-10-10","cited_by_count":41},{"id":"2209.07989","title":"CurveFormer: 3D Lane Detection by Curve Propagation with Curve Queries and Attention","created":"2022-09-16","cited_by_count":40},{"id":"2206.07389","title":"Ultra Fast Deep Lane Detection with Hybrid Anchor Driven Ordinal Classification","created":"2022-06-15","cited_by_count":39}],"next_cursor":"100"}