{"total":77,"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":"2308.09616","title":"Far3D: Expanding the Horizon for Surround-view 3D Object Detection","created":"2023-08-18","cited_by_count":70,"area":null},{"id":"2305.16318","title":"Referred by Multi-Modality: A Unified Temporal Transformer for Video Object Segmentation","created":"2023-05-25","cited_by_count":54,"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":"2404.03181","title":"MonoCD: Monocular 3D Object Detection with Complementary Depths","created":"2024-04-04","cited_by_count":39,"area":null},{"id":"2504.07958","title":"Detect Anything 3D in the Wild","created":"2025-04-10","cited_by_count":33,"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":"2405.11867","title":"Depth Prompting for Sensor-Agnostic Depth Estimation","created":"2024-05-20","cited_by_count":26,"area":null},{"id":"2411.16833","title":"Open Vocabulary Monocular 3D Object Detection","created":"2024-11-25","cited_by_count":23,"area":null},{"id":"2310.00400","title":"MonoGAE: Roadside Monocular 3D Object Detection with Ground-Aware Embeddings","created":"2023-09-30","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":"2311.00371","title":"Learning Cooperative Trajectory Representations for Motion Forecasting","created":"2023-11-01","cited_by_count":21,"area":null},{"id":"2212.01231","title":"BEV-SAN: Accurate BEV 3D Object Detection via Slice Attention Networks","created":"2022-12-02","cited_by_count":20,"area":null},{"id":"2604.08626","title":"WildDet3D: Scaling Promptable 3D Detection in the Wild","created":"2026-04-09","cited_by_count":14,"area":null},{"id":"2403.06093","title":"Enhancing 3D Object Detection with 2D Detection-Guided Query Anchors","created":"2024-03-10","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":"2507.23567","title":"3D-MOOD: Lifting 2D to 3D for Monocular Open-Set Object Detection","created":"2025-07-31","cited_by_count":11,"area":null},{"id":"2504.07836","title":"AerialVG: A Challenging Benchmark for Aerial Visual Grounding by Exploring Positional Relations","created":"2025-04-10","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":"2405.09883","title":"RoScenes: A Large-scale Multi-view 3D Dataset for Roadside Perception","created":"2024-05-16","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":"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":"2406.08152","title":"CT3D++: Improving 3D Object Detection with Keypoint-induced Channel-wise Transformer","created":"2024-06-12","cited_by_count":7,"area":null},{"id":"2407.09857","title":"IFTR: An Instance-Level Fusion Transformer for Visual Collaborative Perception","created":"2024-07-13","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":"2507.19188","title":"VisHall3D: Monocular Semantic Scene Completion from Reconstructing the Visible Regions to Hallucinating the Invisible Regions","created":"2025-07-25","cited_by_count":7,"area":null},{"id":"2404.00149","title":"VSRD: Instance-Aware Volumetric Silhouette Rendering for Weakly Supervised 3D Object Detection","created":"2024-03-29","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":"2310.15624","title":"GUPNet++: Geometry Uncertainty Propagation Network for Monocular 3D Object Detection","created":"2023-10-24","cited_by_count":5,"area":null},{"id":"2311.03620","title":"FusionViT: Hierarchical 3D Object Detection via LiDAR-Camera Vision Transformer Fusion","created":"2023-11-07","cited_by_count":5,"area":null},{"id":"2403.09212","title":"PoIFusion: Multi-Modal 3D Object Detection via Fusion at Points of Interest","created":"2024-03-14","cited_by_count":4,"area":null},{"id":"2412.20911","title":"TiGDistill-BEV: Multi-view BEV 3D Object Detection via Target Inner-Geometry Learning Distillation","created":"2024-12-30","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":"2603.27059","title":"Towards Intrinsic-Aware Monocular 3D Object Detection","created":"2026-03-28","cited_by_count":4,"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":"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":"2501.09481","title":"MonoSOWA: Scalable monocular 3D Object detector Without human Annotations","created":"2025-01-16","cited_by_count":2,"area":null},{"id":"2505.16029","title":"Learning better representations for crowded pedestrians in offboard LiDAR-camera 3D tracking-by-detection","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2507.09214","title":"Stereo-based 3D Anomaly Object Detection for Autonomous Driving: A New Dataset and Baseline","created":"2025-07-12","cited_by_count":2,"area":null},{"id":"2509.09946","title":"Online 3D Multi-Camera Perception through Robust 2D Tracking and Depth-based Late Aggregation","created":"2025-09-12","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":"2511.19301","title":"IDEAL-M3D: Instance Diversity-Enriched Active Learning for Monocular 3D Detection","created":"2025-11-24","cited_by_count":2,"area":null},{"id":"2512.16818","title":"DenseBEV: Transforming BEV Grid Cells into 3D Objects","created":"2025-12-18","cited_by_count":2,"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":"2408.01739","title":"LAM3D: Leveraging Attention for Monocular 3D Object Detection","created":"2024-08-03","cited_by_count":1,"area":null},{"id":"2409.02846","title":"MaDis-Stereo: Enhanced Stereo Matching via Distilled Masked Image Modeling","created":"2024-09-04","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":"2509.08738","title":"CrowdQuery: Density-Guided Query Module for Enhanced 2D and 3D Detection in Crowded Scenes","created":"2025-09-10","cited_by_count":1,"area":null},{"id":"2512.02392","title":"From Detection to Association: Learning Discriminative Object Embeddings for Multi-Object Tracking","created":"2025-12-02","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":"2409.15529","title":"VaLID: Verification as Late Integration of Detections for LiDAR-Camera Fusion","created":"2024-09-23","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":"2412.07768","title":"Test-time Correction: An Online 3D Detection System via Visual Prompting","created":"2024-12-10","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":"2501.18162","title":"IROAM: Improving Roadside Monocular 3D Object Detection Learning from Autonomous Vehicle Data Domain","created":"2025-01-30","cited_by_count":0,"area":null},{"id":"2504.18203","title":"LiDAR-Guided Monocular 3D Object Detection for Long-Range Railway Monitoring","created":"2025-04-25","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":"2509.05999","title":"S-LAM3D: Segmentation-Guided Monocular 3D Object Detection via Feature Space Fusion","created":"2025-09-07","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":"2511.19057","title":"LAA3D: A Benchmark of Detecting and Tracking Low-Altitude Aircraft in 3D Space","created":"2025-11-24","cited_by_count":0,"area":null},{"id":"2512.01178","title":"VSRD++: Autolabeling for 3D Object Detection via Instance-Aware Volumetric Silhouette Rendering","created":"2025-12-01","cited_by_count":0,"area":null},{"id":"2602.05730","title":"Depth as Prior Knowledge for Object Detection","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2604.05780","title":"Sparsity-Aware Voxel Attention and Foreground Modulation for 3D Semantic Scene Completion","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2604.17024","title":"CAM3DNet: Comprehensively mining the multi-scale features for 3D Object Detection with Multi-View Cameras","created":"2026-04-18","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},{"id":"2608.01495","title":"Probing the 3D Object-Level Understanding of Pre-Trained Detection Transformers","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2608.09147","title":"RefineAny3D: Depth Refinement as Semantic Alignment for Monocular 3D Detection","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2609.01172","title":"Monocular Depth Estimation from a Single Image: Progress and Opportunities","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2610.19071","title":"MonoMIP: Multi-Height Inverse Perspective Mapping for Monocular 3D Object Detection","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}