{"list":"other","total":71,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"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":"1606.06650","title":"3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation","created":"2016-06-21","cited_by_count":1476},{"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":"1808.01244","title":"CornerNet: Detecting Objects as Paired Keypoints","created":"2018-08-03","cited_by_count":763},{"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":"2011.14141","title":"AdaBins: Depth Estimation using Adaptive Bins","created":"2020-11-28","cited_by_count":601},{"id":"2109.13410","title":"KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D","created":"2021-09-28","cited_by_count":575},{"id":"1912.02424","title":"Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection","created":"2019-12-05","cited_by_count":540},{"id":"2304.08069","title":"DETRs Beat YOLOs on Real-time Object Detection","created":"2023-04-17","cited_by_count":533},{"id":"1611.08974","title":"Semantic Scene Completion from a Single Depth Image","created":"2016-11-28","cited_by_count":472},{"id":"2104.10956","title":"FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection","created":"2021-04-22","cited_by_count":447},{"id":"1803.03243","title":"Domain Adaptive Faster R-CNN for Object Detection in the Wild","created":"2018-03-08","cited_by_count":443},{"id":"2302.07817","title":"Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction","created":"2023-02-15","cited_by_count":409},{"id":"2112.00726","title":"MonoScene: Monocular 3D Semantic Scene Completion","created":"2021-12-01","cited_by_count":363},{"id":"2303.09551","title":"SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving","created":"2023-03-16","cited_by_count":316},{"id":"2302.12251","title":"VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion","created":"2023-02-23","cited_by_count":313},{"id":"2304.05316","title":"OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction","created":"2023-04-11","cited_by_count":293},{"id":"2008.13367","title":"VarifocalNet: An IoU-aware Dense Object Detector","created":"2020-08-31","cited_by_count":231},{"id":"2012.03762","title":"Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion","created":"2020-12-07","cited_by_count":223},{"id":"2206.00630","title":"Unifying Voxel-based Representation with Transformer for 3D Object Detection","created":"2022-06-01","cited_by_count":202},{"id":"2008.10559","title":"LMSCNet: Lightweight Multiscale 3D Semantic Completion","created":"2020-08-24","cited_by_count":188},{"id":"2406.02918","title":"U-KAN Makes Strong Backbone for Medical Image Segmentation and Generation","created":"2024-06-05","cited_by_count":179},{"id":"1901.08043","title":"Bottom-up Object Detection by Grouping Extreme and Center Points","created":"2019-01-23","cited_by_count":156},{"id":"2504.00983","title":"WorldScore: A Unified Evaluation Benchmark for World Generation","created":"2025-04-01","cited_by_count":156},{"id":"2306.15670","title":"Symphonize 3D Semantic Scene Completion with Contextual Instance Queries","created":"2023-06-27","cited_by_count":90},{"id":"2003.07540","title":"Revisiting the Sibling Head in Object Detector","created":"2020-03-17","cited_by_count":82},{"id":"2108.09770","title":"MobileStereoNet: Towards Lightweight Deep Networks for Stereo Matching","created":"2021-08-22","cited_by_count":82},{"id":"2107.13802","title":"RigNet: Repetitive Image Guided Network for Depth Completion","created":"2021-07-29","cited_by_count":80},{"id":"2303.06884","title":"SCPNet: Semantic Scene Completion on Point Cloud","created":"2023-03-13","cited_by_count":80},{"id":"2306.09001","title":"SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous Driving","created":"2023-06-15","cited_by_count":75},{"id":"2011.09141","title":"Semantic Scene Completion using Local Deep Implicit Functions on LiDAR Data","created":"2020-11-18","cited_by_count":74},{"id":"2103.07466","title":"3D Semantic Scene Completion: a Survey","created":"2021-03-12","cited_by_count":74},{"id":"2203.06398","title":"SIGMA: Semantic-complete Graph Matching for Domain Adaptive Object Detection","created":"2022-03-12","cited_by_count":74},{"id":"2102.12252","title":"Localization Distillation for Dense Object Detection","created":"2021-02-24","cited_by_count":55},{"id":"1906.04423","title":"NAS-FCOS: Fast Neural Architecture Search for Object Detection","created":"2019-06-11","cited_by_count":53},{"id":"2405.13675","title":"Context and Geometry Aware Voxel Transformer for Semantic Scene Completion","created":"2024-05-22","cited_by_count":50},{"id":"1804.03550","title":"Two Stream 3D Semantic Scene Completion","created":"2018-04-10","cited_by_count":48},{"id":"2403.08766","title":"MonoOcc: Digging into Monocular Semantic Occupancy Prediction","created":"2024-03-13","cited_by_count":44},{"id":"2404.11958","title":"Not All Voxels Are Equal: Hardness-Aware Semantic Scene Completion with Self-Distillation","created":"2024-04-18","cited_by_count":43},{"id":"2312.02158","title":"PaSCo: Urban 3D Panoptic Scene Completion with Uncertainty Awareness","created":"2023-12-04","cited_by_count":42},{"id":"2403.15008","title":"Tri-Perspective View Decomposition for Geometry-Aware Depth Completion","created":"2024-03-22","cited_by_count":42},{"id":"2312.05752","title":"Camera-based 3D Semantic Scene Completion with Sparse Guidance Network","created":"2023-12-10","cited_by_count":40},{"id":"2007.11056","title":"BorderDet: Border Feature for Dense Object Detection","created":"2020-07-21","cited_by_count":39},{"id":"2107.02963","title":"Disentangle Your Dense Object Detector","created":"2021-07-07","cited_by_count":37},{"id":"2109.11453","title":"Semantic Segmentation-assisted Scene Completion for LiDAR Point Clouds","created":"2021-09-23","cited_by_count":37},{"id":"2407.02077","title":"Hierarchical Temporal Context Learning for Camera-based Semantic Scene Completion","created":"2024-07-02","cited_by_count":32},{"id":"2408.09859","title":"OccMamba: Semantic Occupancy Prediction with State Space Models","created":"2024-08-19","cited_by_count":30},{"id":"2406.16073","title":"LGS: A Light-weight 4D Gaussian Splatting for Efficient Surgical Scene Reconstruction","created":"2024-06-23","cited_by_count":21},{"id":"2502.05040","title":"GaussRender: Learning 3D Occupancy with Gaussian Rendering","created":"2025-02-07","cited_by_count":18},{"id":"2411.16072","title":"Language Driven Occupancy Prediction","created":"2024-11-25","cited_by_count":17},{"id":"2409.19972","title":"DAOcc: 3D Object Detection Assisted Multi-Sensor Fusion for 3D Occupancy Prediction","created":"2024-09-30","cited_by_count":15},{"id":"2203.05469","title":"Prediction-Guided Distillation for Dense Object Detection","created":"2022-03-10","cited_by_count":14},{"id":"2309.00655","title":"RigNet++: Semantic Assisted Repetitive Image Guided Network for Depth Completion","created":"2023-09-01","cited_by_count":11},{"id":"2501.07260","title":"Skip Mamba Diffusion for Monocular 3D Semantic Scene Completion","created":"2025-01-13","cited_by_count":9},{"id":"2503.12369","title":"L2COcc: Lightweight Camera-Centric Semantic Scene Completion via Distillation of LiDAR Model","created":"2025-03-16","cited_by_count":8},{"id":"2503.06219","title":"VLScene: Vision-Language Guidance Distillation for Camera-Based 3D Semantic Scene Completion","created":"2025-03-08","cited_by_count":6},{"id":"2505.15235","title":"X-GRM: Large Gaussian Reconstruction Model for Sparse-view X-rays to Computed Tomography","created":"2025-05-21","cited_by_count":6},{"id":"2505.13279","title":"Event-Driven Dynamic Scene Depth Completion","created":"2025-05-19","cited_by_count":5},{"id":"2207.12042","title":"Revisiting AP Loss for Dense Object Detection: Adaptive Ranking Pair Selection","created":"2022-07-25","cited_by_count":4},{"id":"2411.16129","title":"Three Cars Approaching within 100m! Enhancing Distant Geometry by Tri-Axis Voxel Scanning for Camera-based Semantic Scene Completion","created":"2024-11-25","cited_by_count":4},{"id":"2504.04732","title":"Inverse++: Vision-Centric 3D Semantic Occupancy Prediction Assisted with 3D Object Detection","created":"2025-04-07","cited_by_count":4},{"id":"2501.03605","title":"ConcealGS: Concealing Invisible Copyright Information in 3D Gaussian Splatting","created":"2025-01-07","cited_by_count":3},{"id":"2503.16825","title":"SGFormer: Satellite-Ground Fusion for 3D Semantic Scene Completion","created":"2025-03-21","cited_by_count":3}],"next_cursor":null}