{"total":119,"rows":[{"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,"area":null},{"id":"2402.13616","title":"YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information","created":"2024-02-21","cited_by_count":425,"area":null},{"id":"2502.12524","title":"YOLOv12: Attention-Centric Real-Time Object Detectors","created":"2025-02-18","cited_by_count":305,"area":null},{"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,"area":null},{"id":"2212.07784","title":"RTMDet: An Empirical Study of Designing Real-Time Object Detectors","created":"2022-12-14","cited_by_count":195,"area":null},{"id":"2106.01178","title":"ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection","created":"2021-06-02","cited_by_count":157,"area":null},{"id":"2103.16237","title":"Delving into Localization Errors for Monocular 3D Object Detection","created":"2021-03-30","cited_by_count":140,"area":null},{"id":"2206.09474","title":"3D Object Detection for Autonomous Driving: A Comprehensive Survey","created":"2022-06-19","cited_by_count":132,"area":null},{"id":"2203.11139","title":"Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Clouds","created":"2022-03-21","cited_by_count":131,"area":null},{"id":"2404.09465","title":"PhyScene: Physically Interactable 3D Scene Synthesis for Embodied AI","created":"2024-04-15","cited_by_count":125,"area":null},{"id":"2104.09804","title":"SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloud","created":"2021-04-20","cited_by_count":119,"area":null},{"id":"2106.13365","title":"RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detection","created":"2021-06-25","cited_by_count":115,"area":null},{"id":"2108.10723","title":"Improving 3D Object Detection with Channel-wise Transformer","created":"2021-08-23","cited_by_count":108,"area":null},{"id":"2106.10823","title":"3D Object Detection for Autonomous Driving: A Survey","created":"2021-06-21","cited_by_count":106,"area":null},{"id":"2112.00322","title":"FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection","created":"2021-12-01","cited_by_count":97,"area":null},{"id":"2108.06709","title":"SPG: Unsupervised Domain Adaptation for 3D Object Detection via Semantic Point Generation","created":"2021-08-15","cited_by_count":94,"area":null},{"id":"2106.12449","title":"FusionPainting: Multimodal Fusion with Adaptive Attention for 3D Object Detection","created":"2021-06-23","cited_by_count":92,"area":null},{"id":"2210.07372","title":"SWFormer: Sparse Window Transformer for 3D Object Detection in Point Clouds","created":"2022-10-13","cited_by_count":92,"area":null},{"id":"2108.11127","title":"AutoShape: Real-Time Shape-Aware Monocular 3D Object Detection","created":"2021-08-25","cited_by_count":87,"area":null},{"id":"2303.02314","title":"Virtual Sparse Convolution for Multimodal 3D Object Detection","created":"2023-03-04","cited_by_count":81,"area":null},{"id":"2201.12558","title":"The KFIoU Loss for Rotated Object Detection","created":"2022-01-29","cited_by_count":73,"area":null},{"id":"2108.08258","title":"LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-based 3D Detector","created":"2021-08-18","cited_by_count":70,"area":null},{"id":"2112.02205","title":"Behind the Curtain: Learning Occluded Shapes for 3D Object Detection","created":"2021-12-04","cited_by_count":58,"area":null},{"id":"2205.12785","title":"AO2-DETR: Arbitrary-Oriented Object Detection Transformer","created":"2022-05-25","cited_by_count":55,"area":null},{"id":"2111.14382","title":"VPFNet: Improving 3D Object Detection with Virtual Point based LiDAR and Stereo Data Fusion","created":"2021-11-29","cited_by_count":48,"area":null},{"id":"2104.00902","title":"HVPR: Hybrid Voxel-Point Representation for Single-stage 3D Object Detection","created":"2021-04-02","cited_by_count":47,"area":null},{"id":"2211.11646","title":"NeRF-RPN: A general framework for object detection in NeRFs","created":"2022-11-21","cited_by_count":46,"area":null},{"id":"2304.14660","title":"Segment Anything Model for Medical Images?","created":"2023-04-28","cited_by_count":39,"area":null},{"id":"2209.10839","title":"Detecting Rotated Objects as Gaussian Distributions and Its 3-D Generalization","created":"2022-09-22","cited_by_count":36,"area":null},{"id":"2210.09267","title":"CramNet: Camera-Radar Fusion with Ray-Constrained Cross-Attention for Robust 3D Object Detection","created":"2022-10-17","cited_by_count":30,"area":null},{"id":"2105.07647","title":"FGR: Frustum-Aware Geometric Reasoning for Weakly Supervised 3D Vehicle Detection","created":"2021-05-17","cited_by_count":29,"area":null},{"id":"2310.05699","title":"Uni3DETR: Unified 3D Detection Transformer","created":"2023-10-09","cited_by_count":27,"area":null},{"id":"2207.10909","title":"DBQ-SSD: Dynamic Ball Query for Efficient 3D Object Detection","created":"2022-07-22","cited_by_count":25,"area":null},{"id":"2207.09332","title":"Rethinking IoU-based Optimization for Single-stage 3D Object Detection","created":"2022-07-19","cited_by_count":19,"area":null},{"id":"2106.06072","title":"Gaussian Bounding Boxes and Probabilistic Intersection-over-Union for Object Detection","created":"2021-06-10","cited_by_count":18,"area":null},{"id":"2310.04716","title":"Reinforced UI Instruction Grounding: Towards a Generic UI Task Automation API","created":"2023-10-07","cited_by_count":18,"area":null},{"id":"2104.10330","title":"BADet: Boundary-Aware 3D Object Detection from Point Clouds","created":"2021-04-21","cited_by_count":17,"area":null},{"id":"2207.12659","title":"Graph Neural Network and Spatiotemporal Transformer Attention for 3D Video Object Detection from Point Clouds","created":"2022-07-26","cited_by_count":17,"area":null},{"id":"2103.03480","title":"IAFA: Instance-aware Feature Aggregation for 3D Object Detection from a Single Image","created":"2021-03-05","cited_by_count":15,"area":null},{"id":"2305.10061","title":"Rethinking Boundary Discontinuity Problem for Oriented Object Detection","created":"2023-05-17","cited_by_count":15,"area":null},{"id":"2308.09098","title":"ImGeoNet: Image-induced Geometry-aware Voxel Representation for Multi-view 3D Object Detection","created":"2023-08-17","cited_by_count":14,"area":null},{"id":"2504.19478","title":"CasaGPT: Cuboid Arrangement and Scene Assembly for Interior Design","created":"2025-04-28","cited_by_count":14,"area":null},{"id":"2301.12515","title":"LiDAR-CS Dataset: LiDAR Point Cloud Dataset with Cross-Sensors for 3D Object Detection","created":"2023-01-29","cited_by_count":13,"area":null},{"id":"2104.05215","title":"SCPM-Net: An Anchor-free 3D Lung Nodule Detection Network using Sphere Representation and Center Points Matching","created":"2021-04-12","cited_by_count":12,"area":null},{"id":"2212.05265","title":"Multi-Sem Fusion: Multimodal Semantic Fusion for 3D Object Detection","created":"2022-12-10","cited_by_count":11,"area":null},{"id":"2204.00106","title":"A Survey of Robust 3D Object Detection Methods in Point Clouds","created":"2022-03-31","cited_by_count":10,"area":null},{"id":"2207.09805","title":"Multimodal Transformer for Automatic 3D Annotation and Object Detection","created":"2022-07-20","cited_by_count":10,"area":null},{"id":"2409.19648","title":"OrientedFormer: An End-to-End Transformer-Based Oriented Object Detector in Remote Sensing Images","created":"2024-09-29","cited_by_count":10,"area":null},{"id":"2203.15700","title":"MAP-Gen: An Automated 3D-Box Annotation Flow with Multimodal Attention Point Generator","created":"2022-03-29","cited_by_count":9,"area":null},{"id":"2305.07598","title":"Hausdorff Distance Matching with Adaptive Query Denoising for Rotated Detection Transformer","created":"2023-05-12","cited_by_count":9,"area":null},{"id":"2411.01584","title":"One for All: Multi-Domain Joint Training for Point Cloud Based 3D Object Detection","created":"2024-11-03","cited_by_count":8,"area":null},{"id":"2111.14055","title":"ESGN: Efficient Stereo Geometry Network for Fast 3D Object Detection","created":"2021-11-28","cited_by_count":7,"area":null},{"id":"2205.11925","title":"Robust 3D Object Detection in Cold Weather Conditions","created":"2022-05-24","cited_by_count":7,"area":null},{"id":"2301.01615","title":"StereoDistill: Pick the Cream from LiDAR for Distilling Stereo-based 3D Object Detection","created":"2023-01-04","cited_by_count":7,"area":null},{"id":"2311.08077","title":"Zero-Shot Segmentation of Eye Features Using the Segment Anything Model (SAM)","created":"2023-11-14","cited_by_count":7,"area":null},{"id":"2508.20063","title":"OpenM3D: Open Vocabulary Multi-view Indoor 3D Object Detection without Human Annotations","created":"2025-08-27","cited_by_count":7,"area":null},{"id":"2103.05929","title":"MapFusion: A General Framework for 3D Object Detection with HDMaps","created":"2021-03-10","cited_by_count":6,"area":null},{"id":"2210.00978","title":"Uncertainty-Driven Active Vision for Implicit Scene Reconstruction","created":"2022-10-03","cited_by_count":6,"area":null},{"id":"2312.10390","title":"Not Every Side Is Equal: Localization Uncertainty Estimation for Semi-Supervised 3D Object Detection","created":"2023-12-16","cited_by_count":6,"area":null},{"id":"2502.01565","title":"GauCho: Gaussian Distributions with Cholesky Decomposition for Oriented Object Detection","created":"2025-02-03","cited_by_count":6,"area":null},{"id":"2502.09471","title":"Wholly-WOOD: Wholly Leveraging Diversified-quality Labels for Weakly-supervised Oriented Object Detection","created":"2025-02-13","cited_by_count":6,"area":null},{"id":"2109.12474","title":"EllipseNet: Anchor-Free Ellipse Detection for Automatic Cardiac Biometrics in Fetal Echocardiography","created":"2021-09-26","cited_by_count":5,"area":null},{"id":"2311.17629","title":"RQFormer: Rotated Query Transformer for End-to-End Oriented Object Detection","created":"2023-11-29","cited_by_count":5,"area":null},{"id":"2210.05018","title":"LidarNAS: Unifying and Searching Neural Architectures for 3D Point Clouds","created":"2022-10-10","cited_by_count":4,"area":null},{"id":"2303.04506","title":"Radio astronomical images object detection and segmentation: A benchmark on deep learning methods","created":"2023-03-08","cited_by_count":4,"area":null},{"id":"2101.08684","title":"A two-stage data association approach for 3D Multi-object Tracking","created":"2021-01-21","cited_by_count":3,"area":null},{"id":"2103.10042","title":"Suppress-and-Refine Framework for End-to-End 3D Object Detection","created":"2021-03-18","cited_by_count":3,"area":null},{"id":"2203.06585","title":"CVFNet: Real-time 3D Object Detection by Learning Cross View Features","created":"2022-03-13","cited_by_count":3,"area":null},{"id":"2407.01558","title":"Visual Grounding Methods for Efficient Interaction with Desktop Graphical User Interfaces","created":"2024-05-05","cited_by_count":3,"area":null},{"id":"2202.03176","title":"Field-of-View IoU for Object Detection in 360{\\deg} Images","created":"2022-02-07","cited_by_count":2,"area":null},{"id":"2207.12120","title":"Efficient Graph-Friendly COCO Metric Computation for Train-Time Model Evaluation","created":"2022-07-21","cited_by_count":2,"area":null},{"id":"2303.12743","title":"DR.CPO: Diversified and Realistic 3D Augmentation via Iterative Construction, Random Placement, and HPR Occlusion","created":"2023-03-20","cited_by_count":2,"area":null},{"id":"2304.09694","title":"CrossFusion: Interleaving Cross-modal Complementation for Noise-resistant 3D Object Detection","created":"2023-04-19","cited_by_count":2,"area":null},{"id":"2304.12624","title":"Shape-Net: Room Layout Estimation from Panoramic Images Robust to Occlusion using Knowledge Distillation with 3D Shapes as Additional Inputs","created":"2023-04-25","cited_by_count":2,"area":null},{"id":"2401.07240","title":"DCDet: Dynamic Cross-based 3D Object Detector","created":"2024-01-14","cited_by_count":2,"area":null},{"id":"2401.12447","title":"NIV-SSD: Neighbor IoU-Voting Single-Stage Object Detector From Point Cloud","created":"2024-01-23","cited_by_count":2,"area":null},{"id":"2406.07023","title":"LiSD: An Efficient Multi-Task Learning Framework for LiDAR Segmentation and Detection","created":"2024-06-11","cited_by_count":2,"area":null},{"id":"2410.15812","title":"FusionLungNet: Multi-scale Fusion Convolution with Refinement Network for Lung CT Image Segmentation","created":"2024-10-21","cited_by_count":2,"area":null},{"id":"2504.16443","title":"Marginalized Generalized IoU (MGIoU): A Unified Objective Function for Optimizing Any Convex Parametric Shapes","created":"2025-04-23","cited_by_count":2,"area":null},{"id":"2112.01702","title":"Localized Feature Aggregation Module for Semantic Segmentation","created":"2021-12-03","cited_by_count":1,"area":null},{"id":"2206.00960","title":"SparseDet: Towards End-to-End 3D Object Detection","created":"2022-06-02","cited_by_count":1,"area":null},{"id":"2212.12264","title":"Collective Intelligent Strategy for Improved Segmentation of COVID-19 from CT","created":"2022-12-23","cited_by_count":1,"area":null},{"id":"2301.02166","title":"Identification of lung nodules CT scan using YOLOv5 based on convolution neural network","created":"2022-12-31","cited_by_count":1,"area":null},{"id":"2306.03497","title":"Instructive Feature Enhancement for Dichotomous Medical Image Segmentation","created":"2023-06-06","cited_by_count":1,"area":null},{"id":"2309.07104","title":"Polygon Intersection-over-Union Loss for Viewpoint-Agnostic Monocular 3D Vehicle Detection","created":"2023-09-13","cited_by_count":1,"area":null},{"id":"2311.09819","title":"PWISeg: Point-based Weakly-supervised Instance Segmentation for Surgical Instruments","created":"2023-11-16","cited_by_count":1,"area":null},{"id":"2312.15377","title":"End-to-End 3D Object Detection using LiDAR Point Cloud","created":"2023-12-24","cited_by_count":1,"area":null},{"id":"2407.01017","title":"Coding for Intelligence from the Perspective of Category","created":"2024-07-01","cited_by_count":1,"area":null},{"id":"2410.06516","title":"QuadBEV: An Efficient Quadruple-Task Perception Framework via Bird's-Eye-View Representation","created":"2024-10-09","cited_by_count":1,"area":null},{"id":"2411.09101","title":"Heuristical Comparison of Vision Transformers Against Convolutional Neural Networks for Semantic Segmentation on Remote Sensing Imagery","created":"2024-11-14","cited_by_count":1,"area":null},{"id":"2503.06458","title":"Reconstructing Depth Images of Moving Objects from Wi-Fi CSI Data","created":"2025-03-09","cited_by_count":1,"area":null},{"id":"2504.07462","title":"Learning Universal Features for Generalizable Image Forgery Localization","created":"2025-04-10","cited_by_count":1,"area":null},{"id":"2506.22890","title":"CP-uniGuard: A Unified, Probability-Agnostic, and Adaptive Framework for Malicious Agent Detection and Defense in Multi-Agent Embodied Perception Systems","created":"2025-06-28","cited_by_count":1,"area":null},{"id":"2509.21894","title":"LG-CD: Enhancing Language-Guided Change Detection through SAM2 Adaptation","created":"2025-09-26","cited_by_count":1,"area":null},{"id":"2605.04409","title":"UAV as Urban Construction Change Monitor: A New Benchmark and Change Captioning Model","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2107.12707","title":"DV-Det: Efficient 3D Point Cloud Object Detection with Dynamic Voxelization","created":"2021-07-27","cited_by_count":0,"area":null},{"id":"2206.11048","title":"Automated GI tract segmentation using deep learning","created":"2022-06-22","cited_by_count":0,"area":null},{"id":"2206.15109","title":"MKIoU Loss: Towards Accurate Oriented Object Detection in Aerial Images","created":"2022-06-30","cited_by_count":0,"area":null},{"id":"2208.07103","title":"Global Consistent Point Cloud Registration Based on Lie-algebraic Cohomology","created":"2022-08-15","cited_by_count":0,"area":null},{"id":"2210.00756","title":"CERBERUS: Simple and Effective All-In-One Automotive Perception Model with Multi Task Learning","created":"2022-10-03","cited_by_count":0,"area":null}],"next_cursor":"100"}