{"total":425,"rows":[{"id":"2405.14458","title":"YOLOv10: Real-Time End-to-End Object Detection","created":"2024-05-23","cited_by_count":515,"area":null},{"id":"2410.17725","title":"YOLOv11: An Overview of the Key Architectural Enhancements","created":"2024-10-23","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":"2407.17140","title":"RT-DETRv2: Improved Baseline with Bag-of-Freebies for Real-Time Detection Transformer","created":"2024-07-24","cited_by_count":91,"area":null},{"id":"2509.25164","title":"YOLO26: Key Architectural Enhancements and Performance Benchmarking for Real-Time Object Detection","created":"2025-09-29","cited_by_count":79,"area":null},{"id":"2511.09554","title":"RF-DETR: Neural Architecture Search for Real-Time Detection Transformers","created":"2025-11-12","cited_by_count":75,"area":null},{"id":"2410.13842","title":"D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinement","created":"2024-10-17","cited_by_count":74,"area":"distill"},{"id":"2412.04234","title":"DEIM: DETR with Improved Matching for Fast Convergence","created":"2024-12-05","cited_by_count":68,"area":null},{"id":"2501.06187","title":"Multi-subject Open-set Personalization in Video Generation","created":"2025-01-10","cited_by_count":66,"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":"2406.10210","title":"Make It Count: Text-to-Image Generation with an Accurate Number of Objects","created":"2024-06-14","cited_by_count":47,"area":"diffusion"},{"id":"2404.00722","title":"DRCT: Saving Image Super-resolution away from Information Bottleneck","created":"2024-03-31","cited_by_count":40,"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":"2408.04804","title":"Hyper-YOLO: When Visual Object Detection Meets Hypergraph Computation","created":"2024-08-09","cited_by_count":29,"area":null},{"id":"2509.20787","title":"Real-Time Object Detection Meets DINOv3","created":"2025-09-25","cited_by_count":27,"area":null},{"id":"2411.00201","title":"YOLO Evolution: A Comprehensive Benchmark and Architectural Review of YOLOv12, YOLO11, and Their Previous Versions","created":"2024-10-31","cited_by_count":18,"area":null},{"id":"2510.09653","title":"Ultralytics YOLO Evolution: An Overview of YOLO27, YOLO26, YOLO11, YOLOv8, and YOLOv5 Object Detectors for Computer Vision and Pattern Recognition","created":"2025-10-06","cited_by_count":18,"area":null},{"id":"2407.02352","title":"Pelican: Correcting Hallucination in Vision-LLMs via Claim Decomposition and Program of Thought Verification","created":"2024-07-02","cited_by_count":17,"area":"lr"},{"id":"2404.09432","title":"The 8th AI City Challenge","created":"2024-04-15","cited_by_count":16,"area":null},{"id":"2501.01855","title":"UAV-DETR: Efficient End-to-End Object Detection for Unmanned Aerial Vehicle Imagery","created":"2025-01-03","cited_by_count":15,"area":null},{"id":"2501.13400","title":"YOLOv8 to YOLO11: A Comprehensive Architecture In-depth Comparative Review","created":"2025-01-23","cited_by_count":15,"area":null},{"id":"2405.12930","title":"Pytorch-Wildlife: A Collaborative Deep Learning Framework for Conservation","created":"2024-05-21","cited_by_count":14,"area":null},{"id":"2406.10139","title":"YOLOv1 to YOLOv10: A comprehensive review of YOLO variants and their application in the agricultural domain","created":"2024-06-14","cited_by_count":14,"area":null},{"id":"2504.20670","title":"FBRT-YOLO: Faster and Better for Real-Time Aerial Image Detection","created":"2025-04-29","cited_by_count":13,"area":null},{"id":"2507.05963","title":"Tora2: Motion and Appearance Customized Diffusion Transformer for Multi-Entity Video Generation","created":"2025-07-08","cited_by_count":12,"area":"diffusion"},{"id":"2411.02136","title":"Advanced computer vision for extracting georeferenced vehicle trajectories from drone imagery","created":"2024-11-04","cited_by_count":11,"area":null},{"id":"2503.08858","title":"SICNav-Diffusion: Safe and Interactive Crowd Navigation with Diffusion Trajectory Predictions","created":"2025-03-11","cited_by_count":11,"area":"diffusion"},{"id":"2504.11967","title":"Securing the Skies: A Comprehensive Survey on Anti-UAV Methods, Benchmarking, and Future Directions","created":"2025-04-16","cited_by_count":11,"area":null},{"id":"2505.01456","title":"Unlearning Sensitive Information in Multimodal LLMs: Benchmark and Attack-Defense Evaluation","created":"2025-05-01","cited_by_count":11,"area":"mllm"},{"id":"2602.16356","title":"Articulated 3D Scene Graphs for Open-World Mobile Manipulation","created":"2026-02-18","cited_by_count":11,"area":null},{"id":"2604.07823","title":"LPM 1.0: Video-based Character Performance Model","created":"2026-04-09","cited_by_count":11,"area":null},{"id":"2403.11249","title":"YOLOv9 for Fracture Detection in Pediatric Wrist Trauma X-ray Images","created":"2024-03-17","cited_by_count":10,"area":null},{"id":"2407.05128","title":"SCSA: Exploring the Synergistic Effects Between Spatial and Channel Attention","created":"2024-07-06","cited_by_count":10,"area":null},{"id":"2503.16710","title":"4D Gaussian Splatting SLAM","created":"2025-03-20","cited_by_count":10,"area":null},{"id":"2505.10931","title":"M4-SAR: A Multi-Resolution, Multi-Polarization, Multi-Scene, Multi-Source Dataset and Benchmark for optical-SAR Object Detection","created":"2025-05-16","cited_by_count":10,"area":null},{"id":"2405.16464","title":"Multi-Modal UAV Detection, Classification and Tracking Algorithm -- Technical Report for CVPR 2024 UG2 Challenge","created":"2024-05-26","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":"2412.10040","title":"RemDet: Rethinking Efficient Model Design for UAV Object Detection","created":"2024-12-13","cited_by_count":9,"area":null},{"id":"2510.03797","title":"Road Damage and Manhole Detection using Deep Learning for Smart Cities: A Polygonal Annotation Approach","created":"2025-10-04","cited_by_count":9,"area":null},{"id":"2408.06970","title":"Prompt-Based Segmentation at Multiple Resolutions and Lighting Conditions using Segment Anything Model 2","created":"2024-08-13","cited_by_count":8,"area":null},{"id":"2411.05633","title":"SynDroneVision: A Synthetic Dataset for Image-Based Drone Detection","created":"2024-11-08","cited_by_count":8,"area":null},{"id":"2411.13753","title":"FAST-Splat: Fast, Ambiguity-Free Semantics Transfer in Gaussian Splatting","created":"2024-11-20","cited_by_count":8,"area":null},{"id":"2408.09332","title":"YOLOv1 to YOLOv10: The fastest and most accurate real-time object detection systems","created":"2024-08-18","cited_by_count":7,"area":null},{"id":"2409.00045","title":"PolypDB: A Curated Multi-Center Dataset for Development of AI Algorithms in Colonoscopy","created":"2024-08-19","cited_by_count":7,"area":null},{"id":"2411.11011","title":"CCi-YOLOv8n: Enhanced Fire Detection with CARAFE and Context-Guided Modules","created":"2024-11-17","cited_by_count":7,"area":null},{"id":"2412.13490","title":"Comparative Analysis of YOLOv9, YOLOv10 and RT-DETR for Real-Time Weed Detection","created":"2024-12-18","cited_by_count":7,"area":null},{"id":"2503.24389","title":"SU-YOLO: Spiking Neural Network for Efficient Underwater Object Detection","created":"2025-03-31","cited_by_count":7,"area":null},{"id":"2508.17416","title":"Data Leakage in Visual Datasets","created":"2025-08-24","cited_by_count":7,"area":null},{"id":"2601.12882","title":"YOLO26: An Analysis of NMS-Free End to End Framework for Real-Time Object Detection","created":"2026-01-19","cited_by_count":7,"area":null},{"id":"2408.06632","title":"EditScribe: Non-Visual Image Editing with Natural Language Verification Loops","created":"2024-08-13","cited_by_count":6,"area":null},{"id":"2410.17144","title":"YOLO-TS: Real-Time Traffic Sign Detection with Enhanced Accuracy Using Optimized Receptive Fields and Anchor-Free Fusion","created":"2024-10-22","cited_by_count":6,"area":null},{"id":"2502.13023","title":"Detection and Geographic Localization of Natural Objects in the Wild: A Case Study on Palms","created":"2025-02-18","cited_by_count":6,"area":null},{"id":"2512.05412","title":"YOLO and SGBM Integration for Autonomous Tree Branch Detection and Depth Estimation in Radiata Pine Pruning Applications","created":"2025-12-05","cited_by_count":6,"area":null},{"id":"2603.20192","title":"LumosX: Relate Any Identities with Their Attributes for Personalized Video Generation","created":"2026-03-20","cited_by_count":6,"area":"diffusion"},{"id":"2405.01699","title":"SOAR: Advancements in Small Body Object Detection for Aerial Imagery Using State Space Models and Programmable Gradients","created":"2024-05-02","cited_by_count":5,"area":null},{"id":"2405.15939","title":"Diversifying Human Pose in Synthetic Data for Aerial-view Human Detection","created":"2024-05-24","cited_by_count":5,"area":null},{"id":"2407.04381","title":"Multi-Branch Auxiliary Fusion YOLO with Re-parameterization Heterogeneous Convolutional for accurate object detection","created":"2024-07-05","cited_by_count":5,"area":null},{"id":"2407.12040","title":"Comprehensive Performance Evaluation of YOLOv12, YOLO11, YOLOv10, YOLOv9 and YOLOv8 on Detecting and Counting Fruitlet in Complex Orchard Environments","created":"2024-07-01","cited_by_count":5,"area":null},{"id":"2408.05649","title":"Advancing Pavement Distress Detection in Developing Countries: A Novel Deep Learning Approach with Locally-Collected Datasets","created":"2024-08-10","cited_by_count":5,"area":null},{"id":"2409.00317","title":"FBD-SV-2024: Flying Bird Object Detection Dataset in Surveillance Video","created":"2024-08-31","cited_by_count":5,"area":null},{"id":"2410.11124","title":"Real-Time Localization and Bimodal Point Pattern Analysis of Palms Using UAV Imagery","created":"2024-10-14","cited_by_count":5,"area":null},{"id":"2410.19869","title":"Comparing YOLOv11 and YOLOv8 for instance segmentation of occluded and non-occluded immature green fruits in complex orchard environment","created":"2024-10-24","cited_by_count":5,"area":null},{"id":"2501.17387","title":"Assessing the Capability of YOLO- and Transformer-based Object Detectors for Real-time Weed Detection","created":"2025-01-29","cited_by_count":5,"area":null},{"id":"2503.08843","title":"Keypoint Semantic Integration for Improved Feature Matching in Outdoor Agricultural Environments","created":"2025-03-11","cited_by_count":5,"area":null},{"id":"2507.14505","title":"DCHM: Depth-Consistent Human Modeling for Multiview Detection","created":"2025-07-19","cited_by_count":5,"area":null},{"id":"2508.02067","title":"YOLOv1 to YOLOv11: A Comprehensive Survey of Real-Time Object Detection Innovations and Challenges","created":"2025-08-04","cited_by_count":5,"area":null},{"id":"2406.11254","title":"YOLO9tr: A Lightweight Model for Pavement Damage Detection Utilizing a Generalized Efficient Layer Aggregation Network and Attention Mechanism","created":"2024-06-17","cited_by_count":4,"area":null},{"id":"2406.13988","title":"LGmap: Local-to-Global Mapping Network for Online Long-Range Vectorized HD Map Construction","created":"2024-06-20","cited_by_count":4,"area":null},{"id":"2407.04590","title":"SH17: A Dataset for Human Safety and Personal Protective Equipment Detection in Manufacturing Industry","created":"2024-07-05","cited_by_count":4,"area":null},{"id":"2408.11760","title":"R2Det: Exploring Relaxed Rotation Equivariance in 2D object detection","created":"2024-08-21","cited_by_count":4,"area":null},{"id":"2409.07813","title":"What is YOLOv9: An In-Depth Exploration of the Internal Features of the Next-Generation Object Detector","created":"2024-09-12","cited_by_count":4,"area":null},{"id":"2410.12143","title":"Mixture of Scale Experts for Alignment-free RGBT Video Object Detection and A Unified Benchmark","created":"2024-10-16","cited_by_count":4,"area":null},{"id":"2410.14371","title":"Interpretable end-to-end Neurosymbolic Reinforcement Learning agents","created":"2024-10-18","cited_by_count":4,"area":"deeprl"},{"id":"2412.05252","title":"From classical techniques to convolution-based models: A review of object detection algorithms","created":"2024-12-06","cited_by_count":4,"area":null},{"id":"2412.07518","title":"Hallucination Elimination and Semantic Enhancement Framework for Vision-Language Models in Traffic Scenarios","created":"2024-12-10","cited_by_count":4,"area":"mllm"},{"id":"2412.08913","title":"Sensing for Space Safety and Sustainability: A Deep Learning Approach with Vision Transformers","created":"2024-12-12","cited_by_count":4,"area":null},{"id":"2501.08931","title":"Visual WetlandBirds Dataset: Bird Species Identification and Behavior Recognition in Videos","created":"2025-01-15","cited_by_count":4,"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":"2503.11481","title":"T2I-FineEval: Fine-Grained Compositional Metric for Text-to-Image Evaluation","created":"2025-03-14","cited_by_count":4,"area":null},{"id":"2504.00234","title":"CBIL: Collective Behavior Imitation Learning for Fish from Real Videos","created":"2025-03-31","cited_by_count":4,"area":"offlinerl"},{"id":"2505.15325","title":"SoftHGNN: Soft Hypergraph Neural Networks for General Visual Recognition","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2506.18737","title":"USVTrack: USV-Based 4D Radar-Camera Tracking Dataset for Autonomous Driving in Inland Waterways","created":"2025-06-23","cited_by_count":4,"area":null},{"id":"2507.13373","title":"Butter: Frequency Consistency and Hierarchical Fusion for Autonomous Driving Object Detection","created":"2025-07-12","cited_by_count":4,"area":null},{"id":"2603.00462","title":"OPGAgent: An Agent for Auditable Dental Panoramic X-ray Interpretation","created":"2026-02-28","cited_by_count":4,"area":null},{"id":"2404.01571","title":"Leveraging YOLO-World and GPT-4V LMMs for Zero-Shot Person Detection and Action Recognition in Drone Imagery","created":"2024-04-02","cited_by_count":3,"area":"mllm"},{"id":"2404.10078","title":"Low-Light Image Enhancement Framework for Improved Object Detection in Fisheye Lens Datasets","created":"2024-04-15","cited_by_count":3,"area":null},{"id":"2405.16116","title":"REACT: Real-time Efficiency and Accuracy Compromise for Tradeoffs in Scene Graph Generation","created":"2024-05-25","cited_by_count":3,"area":null},{"id":"2407.18137","title":"XS-VID: A Large-Scale Benchmark for Small Object Detection and Tracking in Videos","created":"2024-07-25","cited_by_count":3,"area":null},{"id":"2408.01897","title":"CAF-YOLO: A Robust Framework for Multi-Scale Lesion Detection in Biomedical Imagery","created":"2024-08-04","cited_by_count":3,"area":null},{"id":"2408.02181","title":"AssemAI: Interpretable Image-Based Anomaly Detection for Manufacturing Pipelines","created":"2024-08-05","cited_by_count":3,"area":null},{"id":"2408.14087","title":"LSM-YOLO: A Compact and Effective ROI Detector for Medical Detection","created":"2024-08-26","cited_by_count":3,"area":null},{"id":"2409.01604","title":"DAPONet: A Dual Attention and Partially Overparameterized Network for Real-Time Road Damage Detection","created":"2024-09-03","cited_by_count":3,"area":null},{"id":"2409.02546","title":"Real-Time Dynamic Scale-Aware Fusion Detection Network: Take Road Damage Detection as an example","created":"2024-09-04","cited_by_count":3,"area":null},{"id":"2409.05274","title":"Rethinking Theoretical Illumination for Efficient Low-Light Image Enhancement","created":"2024-09-09","cited_by_count":3,"area":null},{"id":"2409.17526","title":"Drone Stereo Vision for Radiata Pine Branch Detection and Distance Measurement: Integrating SGBM and Segmentation Models","created":"2024-09-26","cited_by_count":3,"area":null},{"id":"2410.12068","title":"V3D-SLAM: Robust RGB-D SLAM in Dynamic Environments with 3D Semantic Geometry Voting","created":"2024-10-15","cited_by_count":3,"area":null},{"id":"2411.02582","title":"Real-Time Detection for Small UAVs: Combining YOLO and Multi-frame Motion Analysis","created":"2024-10-10","cited_by_count":3,"area":null},{"id":"2411.19534","title":"QUOTA: Quantifying Objects with Text-to-Image Models for Any Domain","created":"2024-11-29","cited_by_count":3,"area":null},{"id":"2501.05567","title":"Approximate Supervised Object Distance Estimation on Unmanned Surface Vehicles","created":"2025-01-09","cited_by_count":3,"area":null}],"next_cursor":"100"}