{"total":102,"rows":[{"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":"2303.13874","title":"Query-Dependent Video Representation for Moment Retrieval and Highlight Detection","created":"2023-03-24","cited_by_count":166,"area":null},{"id":"2207.10660","title":"Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild","created":"2022-07-21","cited_by_count":160,"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":"2208.02797","title":"Vision-Centric BEV Perception: A Survey","created":"2022-08-04","cited_by_count":126,"area":null},{"id":"2203.13310","title":"MonoDETR: Depth-guided Transformer for Monocular 3D Object Detection","created":"2022-03-24","cited_by_count":86,"area":null},{"id":"2303.03595","title":"LoGoNet: Towards Accurate 3D Object Detection with Local-to-Global Cross-Modal Fusion","created":"2023-03-07","cited_by_count":80,"area":null},{"id":"2303.08498","title":"BEVHeight: A Robust Framework for Vision-based Roadside 3D Object Detection","created":"2023-03-15","cited_by_count":75,"area":null},{"id":"2308.09711","title":"Robust Monocular Depth Estimation under Challenging Conditions","created":"2023-08-18","cited_by_count":58,"area":null},{"id":"2208.12079","title":"Bridging the View Disparity Between Radar and Camera Features for Multi-modal Fusion 3D Object Detection","created":"2022-08-25","cited_by_count":46,"area":null},{"id":"2308.04583","title":"LATR: 3D Lane Detection from Monocular Images with Transformer","created":"2023-08-08","cited_by_count":44,"area":null},{"id":"2404.00722","title":"DRCT: Saving Image Super-resolution away from Information Bottleneck","created":"2024-03-31","cited_by_count":40,"area":null},{"id":"2404.03181","title":"MonoCD: Monocular 3D Object Detection with Complementary Depths","created":"2024-04-04","cited_by_count":39,"area":null},{"id":"2305.15694","title":"Learning Occupancy for Monocular 3D Object Detection","created":"2023-05-25","cited_by_count":36,"area":null},{"id":"2309.16179","title":"BEVHeight++: Toward Robust Visual Centric 3D Object Detection","created":"2023-09-28","cited_by_count":30,"area":null},{"id":"2206.07705","title":"LET-3D-AP: Longitudinal Error Tolerant 3D Average Precision for Camera-Only 3D Detection","created":"2022-06-15","cited_by_count":27,"area":null},{"id":"2211.01142","title":"OPA-3D: Occlusion-Aware Pixel-Wise Aggregation for Monocular 3D Object Detection","created":"2022-11-02","cited_by_count":24,"area":null},{"id":"2207.04448","title":"Mix-Teaching: A Simple, Unified and Effective Semi-Supervised Learning Framework for Monocular 3D Object Detection","created":"2022-07-10","cited_by_count":23,"area":null},{"id":"2411.16833","title":"Open Vocabulary Monocular 3D Object Detection","created":"2024-11-25","cited_by_count":23,"area":null},{"id":"2303.09757","title":"Video Dehazing via a Multi-Range Temporal Alignment Network with Physical Prior","created":"2023-03-17","cited_by_count":22,"area":null},{"id":"2312.08022","title":"Mono3DVG: 3D Visual Grounding in Monocular Images","created":"2023-12-13","cited_by_count":22,"area":null},{"id":"2410.19590","title":"MonoDGP: Monocular 3D Object Detection with Decoupled-Query and Geometry-Error Priors","created":"2024-10-25","cited_by_count":22,"area":null},{"id":"2302.10549","title":"MonoPGC: Monocular 3D Object Detection with Pixel Geometry Contexts","created":"2023-02-21","cited_by_count":21,"area":null},{"id":"2312.14474","title":"MonoLSS: Learnable Sample Selection For Monocular 3D Detection","created":"2023-12-22","cited_by_count":19,"area":null},{"id":"2411.17385","title":"DepthCues: Evaluating Monocular Depth Perception in Large Vision Models","created":"2024-11-26","cited_by_count":19,"area":null},{"id":"2303.13018","title":"MonoATT: Online Monocular 3D Object Detection with Adaptive Token Transformer","created":"2023-03-23","cited_by_count":18,"area":null},{"id":"2405.07696","title":"MonoMAE: Enhancing Monocular 3D Detection through Depth-Aware Masked Autoencoders","created":"2024-05-13","cited_by_count":16,"area":null},{"id":"2305.17763","title":"NeurOCS: Neural NOCS Supervision for Monocular 3D Object Localization","created":"2023-05-28","cited_by_count":13,"area":null},{"id":"2403.17633","title":"UADA3D: Unsupervised Adversarial Domain Adaptation for 3D Object Detection with Sparse LiDAR and Large Domain Gaps","created":"2024-03-26","cited_by_count":12,"area":null},{"id":"2403.20318","title":"SeaBird: Segmentation in Bird's View with Dice Loss Improves Monocular 3D Detection of Large Objects","created":"2024-03-29","cited_by_count":12,"area":null},{"id":"2308.11607","title":"Delving into Motion-Aware Matching for Monocular 3D Object Tracking","created":"2023-08-22","cited_by_count":11,"area":null},{"id":"2403.17387","title":"Decoupled Pseudo-labeling for Semi-Supervised Monocular 3D Object Detection","created":"2024-03-26","cited_by_count":11,"area":null},{"id":"2209.13507","title":"CrossDTR: Cross-view and Depth-guided Transformers for 3D Object Detection","created":"2022-09-27","cited_by_count":10,"area":null},{"id":"2303.16818","title":"SimDistill: Simulated Multi-modal Distillation for BEV 3D Object Detection","created":"2023-03-29","cited_by_count":10,"area":null},{"id":"2307.08415","title":"Monocular 3D Object Detection with LiDAR Guided Semi Supervised Active Learning","created":"2023-07-17","cited_by_count":10,"area":null},{"id":"2505.04594","title":"Unleashing the Power of Chain-of-Prediction for Monocular 3D Object Detection","created":"2025-05-07","cited_by_count":10,"area":null},{"id":"2305.07270","title":"SSD-MonoDETR: Supervised Scale-aware Deformable Transformer for Monocular 3D Object Detection","created":"2023-05-12","cited_by_count":9,"area":null},{"id":"2306.01980","title":"Milestones in Autonomous Driving and Intelligent Vehicles Part II: Perception and Planning","created":"2023-06-03","cited_by_count":9,"area":null},{"id":"2312.07530","title":"Weakly Supervised 3D Object Detection via Multi-Level Visual Guidance","created":"2023-12-12","cited_by_count":9,"area":null},{"id":"2407.20818","title":"WARM-3D: A Weakly-Supervised Sim2Real Domain Adaptation Framework for Roadside Monocular 3D Object Detection","created":"2024-07-30","cited_by_count":9,"area":null},{"id":"2304.01289","title":"Monocular 3D Object Detection with Bounding Box Denoising in 3D by Perceiver","created":"2023-04-03","cited_by_count":8,"area":null},{"id":"2312.08371","title":"PTT: Point-Trajectory Transformer for Efficient Temporal 3D Object Detection","created":"2023-12-13","cited_by_count":8,"area":null},{"id":"2401.01075","title":"Depth-discriminative Metric Learning for Monocular 3D Object Detection","created":"2024-01-02","cited_by_count":8,"area":null},{"id":"2502.19630","title":"Ev-3DOD: Pushing the Temporal Boundaries of 3D Object Detection with Event Cameras","created":"2025-02-26","cited_by_count":8,"area":null},{"id":"2511.20648","title":"LocateAnything3D: Vision-Language 3D Detection with Chain-of-Sight","created":"2025-11-25","cited_by_count":8,"area":null},{"id":"2405.12200","title":"Multi-View Attentive Contextualization for Multi-View 3D Object Detection","created":"2024-05-20","cited_by_count":7,"area":null},{"id":"2407.13748","title":"General Geometry-aware Weakly Supervised 3D Object Detection","created":"2024-07-18","cited_by_count":7,"area":null},{"id":"2408.07422","title":"LLMI3D: MLLM-based 3D Perception from a Single 2D Image","created":"2024-08-14","cited_by_count":7,"area":null},{"id":"2205.11664","title":"Towards Model Generalization for Monocular 3D Object Detection","created":"2022-05-23","cited_by_count":6,"area":null},{"id":"2403.03468","title":"Multi-task Learning for Real-time Autonomous Driving Leveraging Task-adaptive Attention Generator","created":"2024-03-06","cited_by_count":6,"area":null},{"id":"2508.11185","title":"CHARM3R: Towards Unseen Camera Height Robust Monocular 3D Detector","created":"2025-08-15","cited_by_count":6,"area":null},{"id":"2601.01676","title":"LabelAny3D: Label Any Object 3D in the Wild","created":"2026-01-04","cited_by_count":6,"area":null},{"id":"2211.01556","title":"Ground Plane Matters: Picking Up Ground Plane Prior in Monocular 3D Object Detection","created":"2022-11-03","cited_by_count":5,"area":null},{"id":"2211.17126","title":"BEVUDA: Multi-geometric Space Alignments for Domain Adaptive BEV 3D Object Detection","created":"2022-11-30","cited_by_count":5,"area":null},{"id":"2212.10049","title":"OBMO: One Bounding Box Multiple Objects for Monocular 3D Object Detection","created":"2022-12-20","cited_by_count":5,"area":null},{"id":"2310.15624","title":"GUPNet++: Geometry Uncertainty Propagation Network for Monocular 3D Object Detection","created":"2023-10-24","cited_by_count":5,"area":null},{"id":"2406.04999","title":"ProMotion: Prototypes As Motion Learners","created":"2024-06-07","cited_by_count":5,"area":null},{"id":"2406.12671","title":"GeoBench: Benchmarking and Analyzing Monocular Geometry Estimation Models","created":"2024-06-18","cited_by_count":5,"area":null},{"id":"2210.02493","title":"Depth Is All You Need for Monocular 3D Detection","created":"2022-10-05","cited_by_count":4,"area":null},{"id":"2407.19154","title":"RePLAy: Remove Projective LiDAR Depthmap Artifacts via Exploiting Epipolar Geometry","created":"2024-07-27","cited_by_count":4,"area":null},{"id":"2504.06801","title":"MonoPlace3D: Learning 3D-Aware Object Placement for 3D Monocular Detection","created":"2025-04-09","cited_by_count":4,"area":null},{"id":"2504.11014","title":"GATE3D: Generalized Attention-based Task-synergized Estimation in 3D*","created":"2025-04-15","cited_by_count":4,"area":null},{"id":"2603.27059","title":"Towards Intrinsic-Aware Monocular 3D Object Detection","created":"2026-03-28","cited_by_count":4,"area":null},{"id":"2207.07933","title":"Consistency of Implicit and Explicit Features Matters for Monocular 3D Object Detection","created":"2022-07-16","cited_by_count":3,"area":null},{"id":"2404.05280","title":"MOSE: Boosting Vision-based Roadside 3D Object Detection with Scene Cues","created":"2024-04-08","cited_by_count":3,"area":null},{"id":"2410.23728","title":"GigaCheck: Detecting LLM-generated Content via Object-Centric Span Localization","created":"2024-10-31","cited_by_count":3,"area":null},{"id":"2502.00315","title":"MonoDINO-DETR: Depth-Enhanced Monocular 3D Object Detection Using a Vision Foundation Model","created":"2025-02-01","cited_by_count":3,"area":null},{"id":"2506.09541","title":"3DGeoDet: General-purpose Geometry-aware Image-based 3D Object Detection","created":"2025-06-11","cited_by_count":3,"area":null},{"id":"2304.11906","title":"Transformer-based stereo-aware 3D object detection from binocular images","created":"2023-04-24","cited_by_count":2,"area":null},{"id":"2306.05418","title":"Weakly Supervised 3D Object Detection with Multi-Stage Generalization","created":"2023-06-08","cited_by_count":2,"area":null},{"id":"2404.06715","title":"Sparse Points to Dense Clouds: Enhancing 3D Detection with Limited LiDAR Data","created":"2024-04-10","cited_by_count":2,"area":null},{"id":"2404.09431","title":"Vision Foundation Model Driven Foreground-Aware Pseudo-LiDAR Generation for Monocular 3D Object Detection","created":"2024-04-15","cited_by_count":2,"area":null},{"id":"2408.12747","title":"CatFree3D: Category-agnostic 3D Object Detection with Diffusion","created":"2024-08-22","cited_by_count":2,"area":null},{"id":"2501.09481","title":"MonoSOWA: Scalable monocular 3D Object detector Without human Annotations","created":"2025-01-16","cited_by_count":2,"area":null},{"id":"2511.07862","title":"MonoCLUE : Object-Aware Clustering Enhances Monocular 3D Object Detection","created":"2025-11-11","cited_by_count":2,"area":null},{"id":"2511.18788","title":"StereoDETR: Stereo-based Transformer for 3D Object Detection","created":"2025-11-24","cited_by_count":2,"area":null},{"id":"2303.11243","title":"Augment and Criticize: Exploring Informative Samples for Semi-Supervised Monocular 3D Object Detection","created":"2023-03-20","cited_by_count":1,"area":null},{"id":"2308.00596","title":"MonoNext: A 3D Monocular Object Detection with ConvNext","created":"2023-08-01","cited_by_count":1,"area":null},{"id":"2405.15176","title":"MonoDETRNext: Next-Generation Accurate and Efficient Monocular 3D Object Detector","created":"2024-05-24","cited_by_count":1,"area":null},{"id":"2501.03700","title":"AuxDepthNet: Real-Time Monocular 3D Object Detection with Depth-Sensitive Features","created":"2025-01-07","cited_by_count":1,"area":null},{"id":"2507.02393","title":"PLOT: Pseudo-Labeling via Object Tracking for Monocular 3D Object Detection","created":"2025-07-03","cited_by_count":1,"area":null},{"id":"2508.20488","title":"Adaptive Dual Uncertainty Optimization: Boosting Monocular 3D Object Detection under Test-Time Shifts","created":"2025-08-28","cited_by_count":1,"area":null},{"id":"2509.14151","title":"BEVUDA++: Geometric-aware Unsupervised Domain Adaptation for Multi-View 3D Object Detection","created":"2025-09-17","cited_by_count":1,"area":null},{"id":"2512.05663","title":"LeAD-M3D: Leveraging Asymmetric Distillation for Real-Time Monocular 3D Detection","created":"2025-12-05","cited_by_count":1,"area":null},{"id":"2604.01646","title":"MonoSAOD: Monocular 3D Object Detection with Sparsely Annotated Label","created":"2026-04-02","cited_by_count":1,"area":null},{"id":"2606.24805","title":"DDStereo: Efficient Dual Decoder Transformers for Stereo 3D Road Anomaly Detection","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2209.09486","title":"Self-supervised 3D Object Detection from Monocular Pseudo-LiDAR","created":"2022-09-20","cited_by_count":0,"area":null},{"id":"2211.07108","title":"Recursive Cross-View: Use Only 2D Detectors to Achieve 3D Object Detection without 3D Annotations","created":"2022-11-14","cited_by_count":0,"area":null},{"id":"2309.00928","title":"S$^3$-MonoDETR: Supervised Shape&Scale-perceptive Deformable Transformer for Monocular 3D Object Detection","created":"2023-09-02","cited_by_count":0,"area":null},{"id":"2411.02747","title":"Efficient Feature Aggregation and Scale-Aware Regression for Monocular 3D Object Detection","created":"2024-11-05","cited_by_count":0,"area":null},{"id":"2412.19165","title":"Revisiting Monocular 3D Object Detection with Depth Thickness Field","created":"2024-12-26","cited_by_count":0,"area":null},{"id":"2503.02201","title":"MonoLite3D: Lightweight 3D Object Properties Estimation","created":"2025-03-04","cited_by_count":0,"area":null},{"id":"2503.09807","title":"How good are deep learning methods for automated road safety analysis using video data? An experimental study","created":"2025-03-12","cited_by_count":0,"area":null},{"id":"2506.14835","title":"MonoVQD: Monocular 3D Object Detection with Variational Query Denoising and Self-Distillation","created":"2025-06-14","cited_by_count":0,"area":null},{"id":"2511.13195","title":"Difficulty-Aware Label-Guided Denoising for Monocular 3D Object Detection","created":"2025-11-17","cited_by_count":0,"area":null},{"id":"2601.01036","title":"Mono3DV: Monocular 3D Object Detection with 3D-Aware Bipartite Matching and Variational Query DeNoising","created":"2026-01-03","cited_by_count":0,"area":null},{"id":"2601.03617","title":"Systematic Evaluation of Depth Backbones and Semantic Cues for Monocular Pseudo-LiDAR 3D Detection","created":"2026-01-07","cited_by_count":0,"area":null},{"id":"2603.19776","title":"ReManNet: A Riemannian Manifold Network for Monocular 3D Lane Detection","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2603.27995","title":"UniDA3D: A Unified Domain-Adaptive Framework for Multi-View 3D Object Detection","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2605.14781","title":"MonoPRIO: Adaptive Prior Conditioning for Unified Monocular 3D Object Detection","created":"2026-05-14","cited_by_count":0,"area":null}],"next_cursor":"100"}