{"list":"other","total":212,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"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":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1612.00593","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","created":"2016-12-02","cited_by_count":5248},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"1706.02413","title":"PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space","created":"2017-06-07","cited_by_count":4401},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1512.02325","title":"SSD: Single Shot MultiBox Detector","created":"2015-12-08","cited_by_count":3130},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"id":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"id":"1703.04977","title":"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?","created":"2017-03-15","cited_by_count":2352},{"id":"1801.07829","title":"Dynamic Graph CNN for Learning on Point Clouds","created":"2018-01-24","cited_by_count":2223},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"1812.05784","title":"PointPillars: Fast Encoders for Object Detection from Point Clouds","created":"2018-12-14","cited_by_count":1715},{"id":"2004.10934","title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","created":"2020-04-23","cited_by_count":1630},{"id":"1904.01355","title":"FCOS: Fully Convolutional One-Stage Object Detection","created":"2019-04-02","cited_by_count":1577},{"id":"1703.06211","title":"Deformable Convolutional Networks","created":"2017-03-17","cited_by_count":1488},{"id":"1612.08242","title":"YOLO9000: Better, Faster, Stronger","created":"2016-12-25","cited_by_count":1431},{"id":"2405.21060","title":"Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality","created":"2024-05-31","cited_by_count":1336},{"id":"1711.06396","title":"VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection","created":"2017-11-17","cited_by_count":1323},{"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":"2107.08430","title":"YOLOX: Exceeding YOLO Series in 2021","created":"2021-07-18","cited_by_count":1071},{"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":"2207.02696","title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","created":"2022-07-06","cited_by_count":982},{"id":"1812.04244","title":"PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud","created":"2018-12-11","cited_by_count":941},{"id":"1912.13192","title":"PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection","created":"2019-12-31","cited_by_count":891},{"id":"1602.00763","title":"Simple Online and Realtime Tracking","created":"2016-02-02","cited_by_count":868},{"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":"2110.06864","title":"ByteTrack: Multi-Object Tracking by Associating Every Detection Box","created":"2021-10-13","cited_by_count":823},{"id":"1808.01244","title":"CornerNet: Detecting Objects as Paired Keypoints","created":"2018-08-03","cited_by_count":763},{"id":"1611.07759","title":"Multi-View 3D Object Detection Network for Autonomous Driving","created":"2016-11-23","cited_by_count":724},{"id":"1406.4729","title":"Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition","created":"2014-06-18","cited_by_count":720},{"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":"2012.12556","title":"A Survey on Visual Transformer","created":"2020-12-23","cited_by_count":654},{"id":"2206.10092","title":"BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detection","created":"2022-06-21","cited_by_count":572},{"id":"1606.09549","title":"Fully-Convolutional Siamese Networks for Object Tracking","created":"2016-06-30","cited_by_count":568},{"id":"1912.12033","title":"Deep Learning for 3D Point Clouds: A Survey","created":"2019-12-27","cited_by_count":558},{"id":"2203.05625","title":"PETR: Position Embedding Transformation for Multi-View 3D Object Detection","created":"2022-03-10","cited_by_count":552},{"id":"1908.04616","title":"Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data","created":"2019-08-13","cited_by_count":532},{"id":"1905.05055","title":"Object Detection in 20 Years: A Survey","created":"2019-05-13","cited_by_count":531},{"id":"2004.01177","title":"Tracking Objects as Points","created":"2020-04-02","cited_by_count":483},{"id":"2211.05778","title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","created":"2022-11-10","cited_by_count":482},{"id":"2203.11496","title":"TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers","created":"2022-03-22","cited_by_count":466},{"id":"2112.02413","title":"PointCLIP: Point Cloud Understanding by CLIP","created":"2021-12-04","cited_by_count":463},{"id":"2203.06604","title":"Masked Autoencoders for Point Cloud Self-supervised Learning","created":"2022-03-13","cited_by_count":459},{"id":"1707.06484","title":"Deep Layer Aggregation","created":"2017-07-20","cited_by_count":436},{"id":"2108.06152","title":"Conditional DETR for Fast Training Convergence","created":"2021-08-13","cited_by_count":424},{"id":"1605.06409","title":"R-FCN: Object Detection via Region-based Fully Convolutional Networks","created":"2016-05-20","cited_by_count":414},{"id":"2012.15460","title":"TransTrack: Multiple Object Tracking with Transformer","created":"2020-12-31","cited_by_count":371},{"id":"1905.12681","title":"What Makes Training Multi-Modal Classification Networks Hard?","created":"2019-05-29","cited_by_count":344},{"id":"2205.13790","title":"BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework","created":"2022-05-27","cited_by_count":336},{"id":"2003.01251","title":"Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud","created":"2020-03-02","cited_by_count":335},{"id":"2103.01100","title":"Categorical Depth Distribution Network for Monocular 3D Object Detection","created":"2021-03-01","cited_by_count":327},{"id":"1712.02294","title":"Joint 3D Proposal Generation and Object Detection from View Aggregation","created":"2017-12-06","cited_by_count":326},{"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":"1902.07830","title":"Deep Multi-modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges","created":"2019-02-21","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":"2209.02976","title":"YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications","created":"2022-09-07","cited_by_count":275},{"id":"2310.18961","title":"AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection","created":"2023-10-29","cited_by_count":271},{"id":"2205.14401","title":"Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training","created":"2022-05-28","cited_by_count":264},{"id":"2001.06303","title":"Detection and Tracking Meet Drones Challenge","created":"2020-01-16","cited_by_count":263},{"id":"2102.00463","title":"PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection","created":"2021-01-31","cited_by_count":232},{"id":"2203.08195","title":"DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detection","created":"2022-03-15","cited_by_count":224},{"id":"2012.12397","title":"Multi-Task Multi-Sensor Fusion for 3D Object Detection","created":"2020-12-22","cited_by_count":203},{"id":"2012.11409","title":"3D Object Detection with Pointformer","created":"2020-12-21","cited_by_count":194},{"id":"2211.11682","title":"PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning","created":"2022-11-21","cited_by_count":187},{"id":"2301.04926","title":"CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIP","created":"2023-01-12","cited_by_count":181},{"id":"2209.09407","title":"DetCLIP: Dictionary-Enriched Visual-Concept Paralleled Pre-training for Open-world Detection","created":"2022-09-20","cited_by_count":176},{"id":"1409.7618","title":"Multiple Object Tracking: A Literature Review","created":"2014-09-26","cited_by_count":166},{"id":"1904.01649","title":"MVX-Net: Multimodal VoxelNet for 3D Object Detection","created":"2019-04-02","cited_by_count":163},{"id":"1904.09730","title":"An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detection","created":"2019-04-22","cited_by_count":163},{"id":"2307.14126","title":"Multi-modal Learning with Missing Modality via Shared-Specific Feature Modelling","created":"2023-07-26","cited_by_count":163},{"id":"2011.04841","title":"CenterFusion: Center-based Radar and Camera Fusion for 3D Object Detection","created":"2020-11-10","cited_by_count":161},{"id":"2212.06785","title":"Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoders","created":"2022-12-13","cited_by_count":144},{"id":"2204.08721","title":"Multimodal Token Fusion for Vision Transformers","created":"2022-04-19","cited_by_count":136},{"id":"1909.01300","title":"The Oxford Radar RobotCar Dataset: A Radar Extension to the Oxford RobotCar Dataset","created":"2019-09-03","cited_by_count":134},{"id":"2206.09474","title":"3D Object Detection for Autonomous Driving: A Comprehensive Survey","created":"2022-06-19","cited_by_count":132},{"id":"1701.06659","title":"DSSD : Deconvolutional Single Shot Detector","created":"2017-01-23","cited_by_count":131},{"id":"2103.07461","title":"Probabilistic two-stage detection","created":"2021-03-12","cited_by_count":130},{"id":"2206.07959","title":"Simple-BEV: What Really Matters for Multi-Sensor BEV Perception?","created":"2022-06-16","cited_by_count":128},{"id":"2011.10671","title":"A Review and Comparative Study on Probabilistic Object Detection in Autonomous Driving","created":"2020-11-20","cited_by_count":115},{"id":"2004.05224","title":"Deep Learning for Image and Point Cloud Fusion in Autonomous Driving: A Review","created":"2020-04-10","cited_by_count":108},{"id":"2106.10823","title":"3D Object Detection for Autonomous Driving: A Survey","created":"2021-06-21","cited_by_count":106},{"id":"2111.09621","title":"SimpleTrack: Understanding and Rethinking 3D Multi-object Tracking","created":"2021-11-18","cited_by_count":103},{"id":"2203.10314","title":"Voxel Set Transformer: A Set-to-Set Approach to 3D Object Detection from Point Clouds","created":"2022-03-19","cited_by_count":102}],"next_cursor":"100"}