{"total":83,"rows":[{"id":"2502.12524","title":"YOLOv12: Attention-Centric Real-Time Object Detectors","created":"2025-02-18","cited_by_count":305,"area":null},{"id":"2412.04234","title":"DEIM: DETR with Improved Matching for Fast Convergence","created":"2024-12-05","cited_by_count":68,"area":null},{"id":"2506.17733","title":"YOLOv13: Real-Time Object Detection with Hypergraph-Enhanced Adaptive Visual Perception","created":"2025-06-21","cited_by_count":58,"area":null},{"id":"2606.03748","title":"Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models","created":"2026-06-02","cited_by_count":57,"area":null},{"id":"2409.08475","title":"RT-DETRv3: Real-time End-to-End Object Detection with Hierarchical Dense Positive Supervision","created":"2024-09-13","cited_by_count":32,"area":null},{"id":"2509.20787","title":"Real-Time Object Detection Meets DINOv3","created":"2025-09-25","cited_by_count":27,"area":null},{"id":"2507.19993","title":"FROSS: Faster-than-Real-Time Online 3D Semantic Scene Graph Generation from RGB-D Images","created":"2025-07-26","cited_by_count":10,"area":null},{"id":"2504.19347","title":"Improving Small Drone Detection Through Multi-Scale Processing and Data Augmentation","created":"2025-04-27","cited_by_count":7,"area":null},{"id":"2509.11720","title":"Advanced Layout Analysis Models for Docling","created":"2025-09-15","cited_by_count":6,"area":null},{"id":"2602.14276","title":"ScreenParse: Moving Beyond Sparse Grounding with Complete Screen Parsing Supervision","created":"2026-02-15","cited_by_count":6,"area":null},{"id":"2509.23316","title":"C3-OWD: A Curriculum Cross-modal Contrastive Learning Framework for Open-World Detection","created":"2025-09-27","cited_by_count":5,"area":null},{"id":"2502.04656","title":"MHAF-YOLO: Multi-Branch Heterogeneous Auxiliary Fusion YOLO for accurate object detection","created":"2025-02-07","cited_by_count":4,"area":null},{"id":"2603.06917","title":"PaQ-DETR: Learning Pattern and Quality-Aware Dynamic Queries for Object Detection","created":"2026-03-06","cited_by_count":4,"area":null},{"id":"2504.21614","title":"Mcity Data Engine: Iterative Model Improvement Through Open-Vocabulary Data Selection","created":"2025-04-30","cited_by_count":3,"area":null},{"id":"2507.16254","title":"Edge-case Synthesis for Fisheye Object Detection: A Data-centric Perspective","created":"2025-07-22","cited_by_count":3,"area":null},{"id":"2509.12400","title":"From Orthomosaics to Raw UAV Imagery: Enhancing Palm Detection and Crown-Center Localization","created":"2025-09-15","cited_by_count":3,"area":null},{"id":"2602.19358","title":"Referring Layer Decomposition","created":"2026-02-22","cited_by_count":3,"area":null},{"id":"2603.18739","title":"EdgeCrafter: Compact ViTs for Edge Dense Prediction via Task-Specialized Distillation","created":"2026-03-19","cited_by_count":3,"area":null},{"id":"2504.15694","title":"You Sense Only Once Beneath: Ultra-Light Real-Time Underwater Object Detection","created":"2025-04-22","cited_by_count":2,"area":null},{"id":"2509.08818","title":"GeneVA: A Dataset of Human Annotations for Generative Text to Video Artifacts","created":"2025-09-10","cited_by_count":2,"area":null},{"id":"2509.20580","title":"A Comparative Benchmark of Real-time Detectors for Blueberry Detection towards Precision Orchard Management","created":"2025-09-24","cited_by_count":2,"area":null},{"id":"2602.22595","title":"Don't let the information slip away","created":"2026-02-26","cited_by_count":2,"area":null},{"id":"2603.15497","title":"Real-Time Oriented Object Detection Transformer in Remote Sensing Images","created":"2026-03-16","cited_by_count":2,"area":null},{"id":"2508.10600","title":"Towards Powerful and Practical Patch Attacks for 2D Object Detection in Autonomous Driving","created":"2025-08-14","cited_by_count":1,"area":null},{"id":"2510.15026","title":"MOBIUS: Big-to-Mobile Universal Instance Segmentation via Multi-modal Bottleneck Fusion and Calibrated Decoder Pruning","created":"2025-10-16","cited_by_count":1,"area":null},{"id":"2510.24885","title":"FruitProm: Probabilistic Maturity Estimation and Detection of Fruits and Vegetables","created":"2025-10-28","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":"2601.09698","title":"COMPOSE: Hypergraph Cover Optimization for Multi-view 3D Human Pose Estimation","created":"2026-01-14","cited_by_count":1,"area":null},{"id":"2602.20636","title":"SurgAtt-Tracker: Online Surgical Attention Tracking via Temporal Proposal Reranking and Motion-Aware Refinement","created":"2026-02-24","cited_by_count":1,"area":null},{"id":"2602.21010","title":"Le-DETR: Revisiting Real-Time Detection Transformer with Efficient Encoder Design","created":"2026-02-24","cited_by_count":1,"area":null},{"id":"2603.09411","title":"RiO-DETR: DETR for Real-time Oriented Object Detection","created":"2026-03-10","cited_by_count":1,"area":null},{"id":"2604.23442","title":"Resource-Constrained UAV-Based Weed Detection for Site-Specific Management on Edge Devices","created":"2026-04-25","cited_by_count":1,"area":null},{"id":"2606.09367","title":"RT-SDGOD: Real-Time Single-Domain Generalized Object Detection","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2607.05177","title":"CP-WSP: A Declarative CP-SAT Framework for Configurable Multi-Constraint Workforce Scheduling","created":"2026-07-06","cited_by_count":1,"area":null},{"id":"2608.21429","title":"Measuring Gender Representation in Animated Films","created":"2026-08-17","cited_by_count":1,"area":null},{"id":"2411.19289","title":"STAG-VIO: Stabilized Prompt-to-Geometry Interface for Robust Dynamic Visual--Inertial Odometry","created":"2024-11-28","cited_by_count":0,"area":null},{"id":"2504.09196","title":"RT-DATR: Real-time Unsupervised Domain Adaptive Detection Transformer with Adversarial Feature Alignment","created":"2025-04-12","cited_by_count":0,"area":null},{"id":"2504.16557","title":"Beyond Anonymization: Object Scrubbing for Privacy-Preserving 2D and 3D Vision Tasks","created":"2025-04-23","cited_by_count":0,"area":null},{"id":"2507.03564","title":"2.5D Object Detection for Intelligent Roadside Infrastructure","created":"2025-07-04","cited_by_count":0,"area":null},{"id":"2508.03749","title":"Closed-Circuit Television Data as an Emergent Data Source for Urban Rail Platform Crowding Estimation","created":"2025-08-03","cited_by_count":0,"area":null},{"id":"2508.14343","title":"Inter-Class Relational Loss for Small Object Detection: A Case Study on License Plates","created":"2025-08-20","cited_by_count":0,"area":null},{"id":"2509.01241","title":"RT-DETRv2 Explained in 8 Illustrations","created":"2025-09-01","cited_by_count":0,"area":null},{"id":"2509.22365","title":"HierLight-YOLO: A Hierarchical and Lightweight Object Detection Network for UAV Photography","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2510.03501","title":"Real-Time Threaded Houbara Detection and Segmentation for Wildlife Conservation using Mobile Platforms","created":"2025-10-03","cited_by_count":0,"area":null},{"id":"2512.09461","title":"Cytoplasmic Strings Analysis in Human Embryo Time-Lapse Videos using Deep Learning Framework","created":"2025-12-10","cited_by_count":0,"area":null},{"id":"2601.05747","title":"FlyPose: Towards Robust Human Pose Estimation From Aerial Views","created":"2026-01-09","cited_by_count":0,"area":null},{"id":"2601.08319","title":"YOLOBirDrone: Dataset for Bird vs Drone Detection and Classification and a YOLO based enhanced learning architecture","created":"2026-01-13","cited_by_count":0,"area":null},{"id":"2601.14776","title":"M2I2HA: Multi-modal Object Detection Based on Intra- and Inter-Modal Hypergraph Attention","created":"2026-01-21","cited_by_count":0,"area":null},{"id":"2602.06786","title":"Machine Learning for Detection and Severity Estimation of Sweetpotato Weevil Damage in Field and Lab Conditions","created":"2026-02-06","cited_by_count":0,"area":null},{"id":"2602.10259","title":"PMMA: The Polytechnique Montreal Mobility Aids Dataset","created":"2026-02-10","cited_by_count":0,"area":null},{"id":"2602.14140","title":"Detection of On-Ground Chestnuts Using Artificial Intelligence Toward Automated Picking","created":"2026-02-15","cited_by_count":0,"area":null},{"id":"2602.17189","title":"Texo: Formula Recognition within 20M Parameters","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2603.01324","title":"Open-Vocabulary vs Supervised Learning Methods for Post-Disaster Visual Scene Understanding","created":"2026-03-01","cited_by_count":0,"area":null},{"id":"2603.13679","title":"Toward Scalable Co-located Practical Learning: Assisting with Computer Vision and Multimodal Analytics","created":"2026-03-14","cited_by_count":0,"area":null},{"id":"2603.20143","title":"Synergistic Perception and Generative Recomposition: A Multi-Agent Orchestration for Expert-Level Building Inspection","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2603.24850","title":"Towards automatic smoke detector inspection: Recognition of the smoke detectors in industrial facilities and preparation for future drone integration","created":"2026-03-25","cited_by_count":0,"area":null},{"id":"2604.03697","title":"SGTA: Scene-Graph Based Multi-Modal Traffic Agent for Video Understanding","created":"2026-04-04","cited_by_count":0,"area":null},{"id":"2604.11042","title":"Improving Layout Representation Learning Across Inconsistently Annotated Datasets via Agentic Harmonization","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2604.14884","title":"FSDETR: Frequency-Spatial Feature Enhancement for Small Object Detection","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2604.24419","title":"BMD-45: A Large-Scale CCTV Vehicle Detection Dataset for Urban Traffic in Developing Cities","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2604.26084","title":"FruitProM-V2: Robust Probabilistic Maturity Estimation and Detection of Fruits and Vegetables","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2604.26633","title":"SynSur: An end-to-end generative pipeline for synthetic industrial surface defect generation and detection","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2605.03784","title":"ReLeaf: Benchmarking Leaf Segmentation across Domains and Species","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2605.24831","title":"YOLO26 vs. YOLOv8: A Comprehensive Architectural Benchmark of Next-Generation Real-Time Object Detection Models","created":"2026-05-24","cited_by_count":0,"area":null},{"id":"2605.25046","title":"TinyFormer: Preserving Tiny Objects in YOLO-DETR Hybrid Real-time Detectors","created":"2026-05-24","cited_by_count":0,"area":null},{"id":"2605.30578","title":"AdvScene: Rethinking Adversarial Patch Evaluation Through Scene Robustness","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.10953","title":"Architect-Ant: Editable Automatic Furnishing of Architectural Floor Plans","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2607.00124","title":"Segmenting, Fast and Slow: Real-Time Open-Vocabulary Video Instance Segmentation with Dual-Path Processing","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.00734","title":"ConRTF: Edge-Constrained Boundary Distribution Refinement for Realtime TransFormer Table Structure Recognition","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.07170","title":"PUF: Plug-and-Play Uncertainty-Aware Fusion for Online 3D Scene Graph Generation","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2607.16671","title":"Foundation-Assisted Active Learning for Object Detection Annotation","created":"2026-07-18","cited_by_count":0,"area":null},{"id":"2607.24981","title":"Enabling Fully Integer-Only Inference for Lightweight Detection Transformers","created":"2026-07-27","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":"2608.07876","title":"SurgLAT: Surgical Latent Attention Tracking for Depth-Aware Robotic Laparoscope Control","created":"2026-08-08","cited_by_count":0,"area":null},{"id":"2608.08115","title":"SUMI: Scalable Unified Model for 3D Point Cloud Inference","created":"2026-08-08","cited_by_count":0,"area":null},{"id":"2609.06581","title":"Reading Decoder Trajectories: Training-Free Counterfactual Query-Trajectory Reliability for Small-Object Detection","created":"2026-09-06","cited_by_count":0,"area":null},{"id":"2609.12202","title":"QuPAINT: Physics-Aware Multimodal Reasoning for Quantum Material Characterization","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.26092","title":"Match One, Learn with Graph: One-to-Graph Query Collaboration with Backward Sharing for Object Detection","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2609.26590","title":"GTR: Gated Token Recurrence for Efficient Dense Prediction","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.31734","title":"Measuring the evolution of camera distance across a century of film","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2610.03013","title":"RYOPO: Bringing End-to-End Category-Level Object Pose Estimation into Real Time","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.08286","title":"Event Detection in Table Tennis Videos using 2D Keypoints","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.15808","title":"Grounding Deep Learning Framework Testing in Data Flow","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}