{"list":"other","total":62,"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":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"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":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"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":"1908.03557","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","created":"2019-08-09","cited_by_count":1296},{"id":"2001.06782","title":"Gradient Surgery for Multi-Task Learning","created":"2020-01-19","cited_by_count":1256},{"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":"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":"1711.02257","title":"GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks","created":"2017-11-07","cited_by_count":834},{"id":"1810.04650","title":"Multi-Task Learning as Multi-Objective Optimization","created":"2018-10-10","cited_by_count":821},{"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":"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":"1803.10704","title":"End-to-End Multi-Task Learning with Attention","created":"2018-03-28","cited_by_count":534},{"id":"2004.01888","title":"FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking","created":"2020-04-04","cited_by_count":490},{"id":"1604.03539","title":"Cross-stitch Networks for Multi-task Learning","created":"2016-04-12","cited_by_count":467},{"id":"2104.10956","title":"FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection","created":"2021-04-22","cited_by_count":447},{"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":"2303.11926","title":"Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection","created":"2023-03-21","cited_by_count":315},{"id":"1612.00496","title":"3D Bounding Box Estimation Using Deep Learning and Geometry","created":"2016-12-01","cited_by_count":278},{"id":"1904.11490","title":"RepPoints: Point Set Representation for Object Detection","created":"2019-04-25","cited_by_count":264},{"id":"1711.10006","title":"SSD-6D: Making RGB-based 3D detection and 6D pose estimation great again","created":"2017-11-27","cited_by_count":243},{"id":"1805.04409","title":"PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsing","created":"2018-05-11","cited_by_count":224},{"id":"2202.01017","title":"Multi-Task Learning as a Bargaining Game","created":"2022-02-02","cited_by_count":215},{"id":"2012.12397","title":"Multi-Task Multi-Sensor Fusion for 3D Object Detection","created":"2020-12-22","cited_by_count":203},{"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":"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":"2203.11089","title":"PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark","created":"2022-03-21","cited_by_count":140},{"id":"2006.01895","title":"Learning to Branch for Multi-Task Learning","created":"2020-06-02","cited_by_count":115},{"id":"1811.10203","title":"3D-LaneNet: End-to-End 3D Multiple Lane Detection","created":"2018-11-26","cited_by_count":107},{"id":"1904.01690","title":"Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstruction","created":"2019-04-02","cited_by_count":106},{"id":"1612.07695","title":"MultiNet: Real-time Joint Semantic Reasoning for Autonomous Driving","created":"2016-12-22","cited_by_count":90},{"id":"2203.02431","title":"Rethinking Efficient Lane Detection via Curve Modeling","created":"2022-03-04","cited_by_count":88},{"id":"2003.10656","title":"Gen-LaneNet: A Generalized and Scalable Approach for 3D Lane Detection","created":"2020-03-24","cited_by_count":75},{"id":"2403.15241","title":"IS-Fusion: Instance-Scene Collaborative Fusion for Multimodal 3D Object Detection","created":"2024-03-22","cited_by_count":57},{"id":"2301.02371","title":"Anchor3DLane: Learning to Regress 3D Anchors for Monocular 3D Lane Detection","created":"2023-01-06","cited_by_count":48},{"id":"2207.12655","title":"Semi-supervised 3D Object Detection with Proficient Teachers","created":"2022-07-26","cited_by_count":45},{"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":"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":"2212.02845","title":"SSDA3D: Semi-supervised Domain Adaptation for 3D Object Detection from Point Cloud","created":"2022-12-06","cited_by_count":37},{"id":"2312.15742","title":"DI-V2X: Learning Domain-Invariant Representation for Vehicle-Infrastructure Collaborative 3D Object Detection","created":"2023-12-25","cited_by_count":34},{"id":"2003.11291","title":"A Unified Object Motion and Affinity Model for Online Multi-Object Tracking","created":"2020-03-25","cited_by_count":33},{"id":"2112.15351","title":"Learning to Predict 3D Lane Shape and Camera Pose from a Single Image via Geometry Constraints","created":"2021-12-31","cited_by_count":30},{"id":"2008.03467","title":"RPT: Learning Point Set Representation for Siamese Visual Tracking","created":"2020-08-08","cited_by_count":26},{"id":"2305.15765","title":"Language-Guided 3D Object Detection in Point Cloud for Autonomous Driving","created":"2023-05-25","cited_by_count":20},{"id":"2103.03480","title":"IAFA: Instance-aware Feature Aggregation for 3D Object Detection from a Single Image","created":"2021-03-05","cited_by_count":15},{"id":"1708.02550","title":"Fast Scene Understanding for Autonomous Driving","created":"2017-08-08","cited_by_count":14},{"id":"2307.16617","title":"FULLER: Unified Multi-modality Multi-task 3D Perception via Multi-level Gradient Calibration","created":"2023-07-31","cited_by_count":13},{"id":"2306.09590","title":"The 1st-place Solution for CVPR 2023 OpenLane Topology in Autonomous Driving Challenge","created":"2023-06-16","cited_by_count":10},{"id":"2212.03504","title":"LWSIS: LiDAR-guided Weakly Supervised Instance Segmentation for Autonomous Driving","created":"2022-12-07","cited_by_count":9},{"id":"2309.10533","title":"Decoupling the Curve Modeling and Pavement Regression for Lane Detection","created":"2023-09-19","cited_by_count":4}],"next_cursor":null}