{"list":"other","total":61,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"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":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"1812.05784","title":"PointPillars: Fast Encoders for Object Detection from Point Clouds","created":"2018-12-14","cited_by_count":1715},{"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":"1809.02983","title":"Dual Attention Network for Scene Segmentation","created":"2018-09-09","cited_by_count":1003},{"id":"1911.02620","title":"Argoverse: 3D Tracking and Forecasting with Rich Maps","created":"2019-11-06","cited_by_count":732},{"id":"1808.00897","title":"BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation","created":"2018-08-02","cited_by_count":645},{"id":"2103.00112","title":"Transformer in Transformer","created":"2021-02-27","cited_by_count":633},{"id":"2203.05625","title":"PETR: Position Embedding Transformation for Multi-View 3D Object Detection","created":"2022-03-10","cited_by_count":552},{"id":"2206.01256","title":"PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images","created":"2022-06-02","cited_by_count":352},{"id":"2006.04139","title":"Learning Texture Transformer Network for Image Super-Resolution","created":"2020-06-07","cited_by_count":347},{"id":"2107.06307","title":"HDMapNet: An Online HD Map Construction and Evaluation Framework","created":"2021-07-13","cited_by_count":281},{"id":"1612.00496","title":"3D Bounding Box Estimation Using Deep Learning and Geometry","created":"2016-12-01","cited_by_count":278},{"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":"1905.12365","title":"Disentangling Monocular 3D Object Detection","created":"2019-05-29","cited_by_count":217},{"id":"1702.03920","title":"Cognitive Mapping and Planning for Visual Navigation","created":"2017-02-13","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":"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":"1912.04799","title":"Learning Depth-Guided Convolutions for Monocular 3D Object Detection","created":"2019-12-10","cited_by_count":169},{"id":"1908.00821","title":"Learning Lightweight Lane Detection CNNs by Self Attention Distillation","created":"2019-08-02","cited_by_count":162},{"id":"1904.07846","title":"Temporal Cycle-Consistency Learning","created":"2019-04-16","cited_by_count":154},{"id":"2206.15398","title":"PolarFormer: Multi-camera 3D Object Detection with Polar Transformer","created":"2022-06-30","cited_by_count":147},{"id":"2203.04050","title":"BEVSegFormer: Bird's Eye View Semantic Segmentation From Arbitrary Camera Rigs","created":"2022-03-08","cited_by_count":123},{"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},{"id":"2110.00966","title":"Translating Images into Maps","created":"2021-10-03","cited_by_count":115},{"id":"1811.02146","title":"TrafficPredict: Trajectory Prediction for Heterogeneous Traffic-Agents","created":"2018-11-06","cited_by_count":111},{"id":"1903.10955","title":"GS3D: An Efficient 3D Object Detection Framework for Autonomous Driving","created":"2019-03-26","cited_by_count":106},{"id":"1904.06807","title":"Multi-Channel Attention Selection GAN with Cascaded Semantic Guidance for Cross-View Image Translation","created":"2019-04-15","cited_by_count":97},{"id":"2007.09451","title":"Feature Pyramid Transformer","created":"2020-07-18","cited_by_count":96},{"id":"1612.02709","title":"Predicting Ground-Level Scene Layout from Aerial Imagery","created":"2016-12-08","cited_by_count":90},{"id":"1612.07695","title":"MultiNet: Real-time Joint Semantic Reasoning for Autonomous Driving","created":"2016-12-22","cited_by_count":90},{"id":"1804.02176","title":"Monocular Semantic Occupancy Grid Mapping with Convolutional Variational Encoder-Decoder Networks","created":"2018-04-06","cited_by_count":84},{"id":"2003.12737","title":"Actor-Transformers for Group Activity Recognition","created":"2020-03-28","cited_by_count":84},{"id":"1803.03396","title":"Cross-View Image Synthesis using Conditional GANs","created":"2018-03-09","cited_by_count":69},{"id":"2008.11351","title":"SNE-RoadSeg: Incorporating Surface Normal Information into Semantic Segmentation for Accurate Freespace Detection","created":"2020-08-26","cited_by_count":66},{"id":"2002.08394","title":"MonoLayout: Amodal scene layout from a single image","created":"2020-02-19","cited_by_count":49},{"id":"2206.04042","title":"Learning Ego 3D Representation as Ray Tracing","created":"2022-06-08","cited_by_count":43},{"id":"1903.02193","title":"Robust Lane Detection from Continuous Driving Scenes Using Deep Neural Networks","created":"2019-03-06","cited_by_count":41},{"id":"1803.10870","title":"Learning to Look around Objects for Top-View Representations of Outdoor Scenes","created":"2018-03-28","cited_by_count":37},{"id":"1905.06937","title":"Monocular Plan View Networks for Autonomous Driving","created":"2019-05-16","cited_by_count":37},{"id":"1905.02231","title":"A Geometric Approach to Obtain a Bird's Eye View from an Image","created":"2019-05-06","cited_by_count":34},{"id":"1905.04354","title":"FastDraw: Addressing the Long Tail of Lane Detection by Adapting a Sequential Prediction Network","created":"2019-05-10","cited_by_count":34},{"id":"2012.12160","title":"Convolutional Recurrent Network for Road Boundary Extraction","created":"2020-12-21","cited_by_count":33},{"id":"2012.03040","title":"Understanding Bird's-Eye View of Road Semantics using an Onboard Camera","created":"2020-12-05","cited_by_count":29},{"id":"1808.00327","title":"Generative Adversarial Frontal View to Bird View Synthesis","created":"2018-08-01","cited_by_count":25},{"id":"2204.07733","title":"GitNet: Geometric Prior-based Transformation for Birds-Eye-View Segmentation","created":"2022-04-16","cited_by_count":24},{"id":"1905.01447","title":"Leveraging Crowdsourced GPS Data for Road Extraction from Aerial Imagery","created":"2019-05-04","cited_by_count":23},{"id":"1812.06152","title":"A Parametric Top-View Representation of Complex Road Scenes","created":"2018-12-14","cited_by_count":20},{"id":"1904.08494","title":"Learning 2D to 3D Lifting for Object Detection in 3D for Autonomous Vehicles","created":"2019-03-27","cited_by_count":18},{"id":"2007.00822","title":"Understanding Road Layout from Videos as a Whole","created":"2020-07-02","cited_by_count":10}],"next_cursor":null}