{"list":"other","total":54,"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":"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":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"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":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"id":"1603.05027","title":"Identity Mappings in Deep Residual Networks","created":"2016-03-16","cited_by_count":1965},{"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":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"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":"2104.00298","title":"EfficientNetV2: Smaller Models and Faster Training","created":"2021-04-01","cited_by_count":1135},{"id":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"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":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"2106.02034","title":"DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification","created":"2021-06-03","cited_by_count":864},{"id":"2107.00652","title":"CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows","created":"2021-07-01","cited_by_count":527},{"id":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519},{"id":"2204.01697","title":"MaxViT: Multi-Axis Vision Transformer","created":"2022-04-04","cited_by_count":476},{"id":"2105.08050","title":"Pay Attention to MLPs","created":"2021-05-17","cited_by_count":368},{"id":"2105.03824","title":"FNet: Mixing Tokens with Fourier Transforms","created":"2021-05-09","cited_by_count":347},{"id":"2106.09681","title":"XCiT: Cross-Covariance Image Transformers","created":"2021-06-17","cited_by_count":338},{"id":"2003.07853","title":"Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation","created":"2020-03-17","cited_by_count":326},{"id":"2203.10638","title":"V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformer","created":"2022-03-20","cited_by_count":320},{"id":"2109.07644","title":"OPV2V: An Open Benchmark Dataset and Fusion Pipeline for Perception with Vehicle-to-Vehicle Communication","created":"2021-09-16","cited_by_count":304},{"id":"2201.02973","title":"MAXIM: Multi-Axis MLP for Image Processing","created":"2022-01-09","cited_by_count":302},{"id":"2008.07519","title":"V2VNet: Vehicle-to-Vehicle Communication for Joint Perception and Prediction","created":"2020-08-17","cited_by_count":292},{"id":"2107.00641","title":"Focal Self-attention for Local-Global Interactions in Vision Transformers","created":"2021-07-01","cited_by_count":288},{"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":"2106.03348","title":"ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias","created":"2021-06-07","cited_by_count":216},{"id":"1811.08188","title":"Orthographic Feature Transform for Monocular 3D Object Detection","created":"2018-11-20","cited_by_count":202},{"id":"2111.00643","title":"Learning Distilled Collaboration Graph for Multi-Agent Perception","created":"2021-11-01","cited_by_count":194},{"id":"1906.03560","title":"Cross-view Semantic Segmentation for Sensing Surroundings","created":"2019-06-09","cited_by_count":174},{"id":"1909.06459","title":"F-Cooper: Feature based Cooperative Perception for Autonomous Vehicle Edge Computing System Using 3D Point Clouds","created":"2019-09-13","cited_by_count":171},{"id":"1905.05265","title":"Cooper: Cooperative Perception for Connected Autonomous Vehicles based on 3D Point Clouds","created":"2019-05-13","cited_by_count":165},{"id":"2106.03650","title":"Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer","created":"2021-06-07","cited_by_count":115},{"id":"2110.00966","title":"Translating Images into Maps","created":"2021-10-03","cited_by_count":115},{"id":"2206.09959","title":"Global Context Vision Transformers","created":"2022-06-20","cited_by_count":98},{"id":"2005.04078","title":"A Sim2Real Deep Learning Approach for the Transformation of Images from Multiple Vehicle-Mounted Cameras to a Semantically Segmented Image in Bird's Eye View","created":"2020-05-08","cited_by_count":72},{"id":"2203.13168","title":"Model-Agnostic Multi-Agent Perception Framework","created":"2022-03-24","cited_by_count":51},{"id":"2002.08394","title":"MonoLayout: Amodal scene layout from a single image","created":"2020-02-19","cited_by_count":49},{"id":"2109.11615","title":"Keypoints-Based Deep Feature Fusion for Cooperative Vehicle Detection of Autonomous Driving","created":"2021-09-23","cited_by_count":45},{"id":"2006.11436","title":"BEV-Seg: Bird's Eye View Semantic Segmentation Using Geometry and Semantic Point Cloud","created":"2020-06-19","cited_by_count":38},{"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":"2206.06801","title":"Peripheral Vision Transformer","created":"2022-06-14","cited_by_count":27},{"id":"2103.15293","title":"Monocular 3D Vehicle Detection Using Uncalibrated Traffic Cameras through Homography","created":"2021-03-29","cited_by_count":21},{"id":"1812.00913","title":"The Right (Angled) Perspective: Improving the Understanding of Road Scenes Using Boosted Inverse Perspective Mapping","created":"2018-12-03","cited_by_count":11},{"id":"2011.04408","title":"SeasonDepth: Cross-Season Monocular Depth Prediction Dataset and Benchmark under Multiple Environments","created":"2020-11-09","cited_by_count":9}],"next_cursor":null}