{"list":"other","total":71,"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"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":"1506.02025","title":"Spatial Transformer Networks","created":"2015-06-05","cited_by_count":1429},{"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":"2112.11790","title":"BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View","created":"2021-12-22","cited_by_count":713},{"id":"1609.01775","title":"Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking","created":"2016-09-06","cited_by_count":692},{"id":"1901.02446","title":"Panoptic Feature Pyramid Networks","created":"2019-01-08","cited_by_count":645},{"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":"2302.07817","title":"Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction","created":"2023-02-15","cited_by_count":409},{"id":"2205.13790","title":"BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework","created":"2022-05-27","cited_by_count":336},{"id":"2303.09551","title":"SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving","created":"2023-03-16","cited_by_count":316},{"id":"2208.14437","title":"MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction","created":"2022-08-30","cited_by_count":314},{"id":"2211.10439","title":"BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision","created":"2022-11-18","cited_by_count":302},{"id":"2304.05316","title":"OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction","created":"2023-04-11","cited_by_count":293},{"id":"1904.07392","title":"NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection","created":"2019-04-16","cited_by_count":291},{"id":"1802.10062","title":"CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes","created":"2018-02-27","cited_by_count":267},{"id":"2205.02833","title":"Cross-view Transformers for real-time Map-view Semantic Segmentation","created":"2022-05-05","cited_by_count":264},{"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":"2303.03991","title":"OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perception","created":"2023-03-07","cited_by_count":221},{"id":"2306.02851","title":"Scene as Occupancy","created":"2023-06-05","cited_by_count":209},{"id":"1908.03684","title":"Bayesian Loss for Crowd Count Estimation with Point Supervision","created":"2019-08-10","cited_by_count":162},{"id":"2107.12746","title":"Rethinking Counting and Localization in Crowds:A Purely Point-Based Framework","created":"2021-07-27","cited_by_count":152},{"id":"1811.10452","title":"Context-Aware Crowd Counting","created":"2018-11-26","cited_by_count":150},{"id":"2308.09244","title":"SparseBEV: High-Performance Sparse 3D Object Detection from Multi-Camera Videos","created":"2023-08-18","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":"2009.13077","title":"Distribution Matching for Crowd Counting","created":"2020-09-28","cited_by_count":143},{"id":"2308.02236","title":"FB-BEV: BEV Representation from Forward-Backward View Transformations","created":"2023-08-04","cited_by_count":98},{"id":"1708.00199","title":"Switching Convolutional Neural Network for Crowd Counting","created":"2017-08-01","cited_by_count":93},{"id":"1909.01203","title":"Cross View Fusion for 3D Human Pose Estimation","created":"2019-09-03","cited_by_count":90},{"id":"2202.13065","title":"An End-to-End Transformer Model for Crowd Localization","created":"2022-02-26","cited_by_count":74},{"id":"2104.09116","title":"TransCrowd: weakly-supervised crowd counting with transformers","created":"2021-04-19","cited_by_count":61},{"id":"2312.16108","title":"LaneSegNet: Map Learning with Lane Segment Perception for Autonomous Driving","created":"2023-12-26","cited_by_count":57},{"id":"2206.05253","title":"Rethinking Spatial Invariance of Convolutional Networks for Object Counting","created":"2022-06-10","cited_by_count":54},{"id":"1608.06197","title":"CrowdNet: A Deep Convolutional Network for Dense Crowd Counting","created":"2016-08-22","cited_by_count":52},{"id":"2209.13801","title":"Translation, Scale and Rotation: Cross-Modal Alignment Meets RGB-Infrared Vehicle Detection","created":"2022-09-28","cited_by_count":50},{"id":"1712.06679","title":"DecideNet: Counting Varying Density Crowds Through Attention Guided Detection and Density Estimation","created":"2017-12-18","cited_by_count":49},{"id":"1807.01989","title":"Revisiting Perspective Information for Efficient Crowd Counting","created":"2018-07-05","cited_by_count":49},{"id":"1908.08692","title":"Crowd Counting with Deep Structured Scale Integration Network","created":"2019-08-23","cited_by_count":46},{"id":"1811.11968","title":"ADCrowdNet: An Attention-injective Deformable Convolutional Network for Crowd Understanding","created":"2018-11-29","cited_by_count":45},{"id":"1707.09605","title":"CNN-based Cascaded Multi-task Learning of High-level Prior and Density Estimation for Crowd Counting","created":"2017-07-30","cited_by_count":41},{"id":"2308.13814","title":"Point-Query Quadtree for Crowd Counting, Localization, and More","created":"2023-08-26","cited_by_count":40},{"id":"2003.00217","title":"NAS-Count: Counting-by-Density with Neural Architecture Search","created":"2020-02-29","cited_by_count":36},{"id":"1905.10085","title":"PCC Net: Perspective Crowd Counting via Spatial Convolutional Network","created":"2019-05-24","cited_by_count":33},{"id":"2003.00164","title":"Towards Using Count-level Weak Supervision for Crowd Counting","created":"2020-02-29","cited_by_count":33},{"id":"2003.11883","title":"DCNAS: Densely Connected Neural Architecture Search for Semantic Image Segmentation","created":"2020-03-26","cited_by_count":33},{"id":"2007.08260","title":"Weighing Counts: Sequential Crowd Counting by Reinforcement Learning","created":"2020-07-16","cited_by_count":30},{"id":"2109.14483","title":"CCTrans: Simplifying and Improving Crowd Counting with Transformer","created":"2021-09-29","cited_by_count":30},{"id":"2205.01551","title":"Cross-View Cross-Scene Multi-View Crowd Counting","created":"2022-05-03","cited_by_count":28},{"id":"1702.02359","title":"Multi-scale Convolutional Neural Networks for Crowd Counting","created":"2017-02-08","cited_by_count":26},{"id":"2103.16291","title":"Leveraging Self-Supervision for Cross-Domain Crowd Counting","created":"2021-03-30","cited_by_count":24},{"id":"1711.04433","title":"Crowd counting via scale-adaptive convolutional neural network","created":"2017-11-13","cited_by_count":23},{"id":"2301.04467","title":"FrustumFormer: Adaptive Instance-aware Resampling for Multi-view 3D Detection","created":"2023-01-10","cited_by_count":21},{"id":"2208.02894","title":"Redesigning Multi-Scale Neural Network for Crowd Counting","created":"2022-08-04","cited_by_count":17},{"id":"2306.01209","title":"Counting Crowds in Bad Weather","created":"2023-06-02","cited_by_count":14},{"id":"2012.00946","title":"Wide-Area Crowd Counting: Multi-View Fusion Networks for Counting in Large Scenes","created":"2020-12-02","cited_by_count":13},{"id":"2202.13660","title":"FusionCount: Efficient Crowd Counting via Multiscale Feature Fusion","created":"2022-02-28","cited_by_count":13},{"id":"2112.15509","title":"Scene-Adaptive Attention Network for Crowd Counting","created":"2021-12-31","cited_by_count":12},{"id":"2308.05311","title":"DAOT: Domain-Agnostically Aligned Optimal Transport for Domain-Adaptive Crowd Counting","created":"2023-08-10","cited_by_count":12},{"id":"2108.00584","title":"Congested Crowd Instance Localization with Dilated Convolutional Swin Transformer","created":"2021-08-02","cited_by_count":11},{"id":"2205.03307","title":"Forget Less, Count Better: A Domain-Incremental Self-Distillation Learning Benchmark for Lifelong Crowd Counting","created":"2022-05-06","cited_by_count":9},{"id":"2003.08162","title":"3D Crowd Counting via Geometric Attention-guided Multi-View Fusion","created":"2020-03-18","cited_by_count":8},{"id":"2002.06515","title":"A Real-Time Deep Network for Crowd Counting","created":"2020-02-16","cited_by_count":7}],"next_cursor":null}