{"total":275,"rows":[{"id":"2401.17270","title":"YOLO-World: Real-Time Open-Vocabulary Object Detection","created":"2024-01-30","cited_by_count":503,"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":"2410.17725","title":"YOLOv11: An Overview of the Key Architectural Enhancements","created":"2024-10-23","cited_by_count":425,"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":"2304.00501","title":"A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS","created":"2023-04-02","cited_by_count":151,"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":"2402.15584","title":"State Space Models for Event Cameras","created":"2024-02-23","cited_by_count":75,"area":null},{"id":"2301.05586","title":"YOLOv6 v3.0: A Full-Scale Reloading","created":"2023-01-13","cited_by_count":58,"area":null},{"id":"2304.10410","title":"Radar-Camera Fusion for Object Detection and Semantic Segmentation in Autonomous Driving: A Comprehensive Review","created":"2023-04-20","cited_by_count":58,"area":null},{"id":"2304.13455","title":"From Chaos Comes Order: Ordering Event Representations for Object Recognition and Detection","created":"2023-04-26","cited_by_count":52,"area":null},{"id":"2304.01484","title":"Mapping Degeneration Meets Label Evolution: Learning Infrared Small Target Detection with Single Point Supervision","created":"2023-04-04","cited_by_count":51,"area":null},{"id":"2309.11331","title":"Gold-YOLO: Efficient Object Detector via Gather-and-Distribute Mechanism","created":"2023-09-20","cited_by_count":51,"area":null},{"id":"2401.16355","title":"PathMMU: A Massive Multimodal Expert-Level Benchmark for Understanding and Reasoning in Pathology","created":"2024-01-29","cited_by_count":43,"area":"mllm"},{"id":"2303.14488","title":"Adaptive Sparse Convolutional Networks with Global Context Enhancement for Faster Object Detection on Drone Images","created":"2023-03-25","cited_by_count":41,"area":null},{"id":"2302.02367","title":"FastPillars: A Deployment-friendly Pillar-based 3D Detector","created":"2023-02-05","cited_by_count":39,"area":null},{"id":"2211.15444","title":"DAMO-YOLO : A Report on Real-Time Object Detection Design","created":"2022-11-23","cited_by_count":38,"area":null},{"id":"2406.03459","title":"LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection","created":"2024-06-05","cited_by_count":36,"area":null},{"id":"2503.07465","title":"YOLOE: Real-Time Seeing Anything","created":"2025-03-10","cited_by_count":36,"area":null},{"id":"2308.05480","title":"YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-time Object Detection","created":"2023-08-10","cited_by_count":33,"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":"2412.06647","title":"Object Detection using Event Camera: A MoE Heat Conduction based Detector and A New Benchmark Dataset","created":"2024-12-09","cited_by_count":25,"area":"moe"},{"id":"2311.13930","title":"Periodically Exchange Teacher-Student for Source-Free Object Detection","created":"2023-11-23","cited_by_count":24,"area":"distill"},{"id":"2212.01593","title":"Make RepVGG Greater Again: A Quantization-aware Approach","created":"2022-12-03","cited_by_count":22,"area":null},{"id":"2308.06173","title":"Physical Adversarial Attacks For Camera-based Smart Systems: Current Trends, Categorization, Applications, Research Challenges, and Future Outlook","created":"2023-08-11","cited_by_count":20,"area":null},{"id":"2401.02634","title":"AG-ReID.v2: Bridging Aerial and Ground Views for Person Re-identification","created":"2024-01-05","cited_by_count":20,"area":null},{"id":"2406.05835","title":"Mamba YOLO: A Simple Baseline for Object Detection with State Space Model","created":"2024-06-09","cited_by_count":19,"area":"ssm"},{"id":"2312.04548","title":"Multiview Aerial Visual Recognition (MAVREC): Can Multi-view Improve Aerial Visual Perception?","created":"2023-12-07","cited_by_count":18,"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":"2211.11426","title":"Revealing Hidden Context Bias in Segmentation and Object Detection through Concept-specific Explanations","created":"2022-11-21","cited_by_count":17,"area":null},{"id":"2302.07577","title":"Efficient Teacher: Semi-Supervised Object Detection for YOLOv5","created":"2023-02-15","cited_by_count":17,"area":null},{"id":"2304.05552","title":"DynamicDet: A Unified Dynamic Architecture for Object Detection","created":"2023-04-12","cited_by_count":15,"area":null},{"id":"2309.04902","title":"Transformers in Small Object Detection: A Benchmark and Survey of State-of-the-Art","created":"2023-09-10","cited_by_count":15,"area":null},{"id":"2311.01057","title":"Ultra-Efficient On-Device Object Detection on AI-Integrated Smart Glasses with TinyissimoYOLO","created":"2023-11-02","cited_by_count":15,"area":null},{"id":"2407.16424","title":"ESOD: Efficient Small Object Detection on High-Resolution Images","created":"2024-07-23","cited_by_count":15,"area":null},{"id":"2505.04616","title":"Person Recognition at Altitude and Range: Fusion of Face, Body Shape and Gait","created":"2025-05-07","cited_by_count":14,"area":null},{"id":"2304.05370","title":"Overload: Latency Attacks on Object Detection for Edge Devices","created":"2023-04-11","cited_by_count":13,"area":null},{"id":"2403.12686","title":"WaterVG: Waterway Visual Grounding based on Text-Guided Vision and mmWave Radar","created":"2024-03-19","cited_by_count":13,"area":null},{"id":"2304.05071","title":"Fracture Detection in Pediatric Wrist Trauma X-ray Images Using YOLOv8 Algorithm","created":"2023-04-11","cited_by_count":12,"area":null},{"id":"2307.05999","title":"Flexible and Fully Quantized Ultra-Lightweight TinyissimoYOLO for Ultra-Low-Power Edge Systems","created":"2023-07-12","cited_by_count":11,"area":null},{"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":"2211.01778","title":"Progressive Transformation Learning for Leveraging Virtual Images in Training","created":"2022-11-03","cited_by_count":10,"area":null},{"id":"2309.16393","title":"HIC-YOLOv5: Improved YOLOv5 For Small Object Detection","created":"2023-09-28","cited_by_count":10,"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":"2412.02734","title":"MVCTrack: Boosting 3D Point Cloud Tracking via Multimodal-Guided Virtual Cues","created":"2024-12-03","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":"2310.10563","title":"RefConv: Re-parameterized Refocusing Convolution for Powerful ConvNets","created":"2023-10-16","cited_by_count":9,"area":null},{"id":"2408.14496","title":"A New Era in Computational Pathology: A Survey on Foundation and Vision-Language Models","created":"2024-08-23","cited_by_count":9,"area":"mllm"},{"id":"2410.19872","title":"Radar and Camera Fusion for Object Detection and Tracking: A Comprehensive Survey","created":"2024-10-24","cited_by_count":9,"area":null},{"id":"2410.22898","title":"YOLOv11 for Vehicle Detection: Advancements, Performance, and Applications in Intelligent Transportation Systems","created":"2024-10-30","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":"2210.04399","title":"Deep Learning for Logo Detection: A Survey","created":"2022-10-10","cited_by_count":8,"area":null},{"id":"2303.11567","title":"One-to-Few Label Assignment for End-to-End Dense Detection","created":"2023-03-21","cited_by_count":8,"area":null},{"id":"2310.05392","title":"Lightweight Full-Convolutional Siamese Tracker","created":"2023-10-09","cited_by_count":8,"area":null},{"id":"2401.04942","title":"Latency-aware Road Anomaly Segmentation in Videos: A Photorealistic Dataset and New Metrics","created":"2024-01-10","cited_by_count":8,"area":null},{"id":"2403.01123","title":"ELA: Efficient Local Attention for Deep Convolutional Neural Networks","created":"2024-03-02","cited_by_count":8,"area":null},{"id":"2209.06428","title":"Semantic Visual Simultaneous Localization and Mapping: A Survey","created":"2022-09-14","cited_by_count":7,"area":null},{"id":"2402.00703","title":"Vehicle Perception from Satellite","created":"2024-02-01","cited_by_count":7,"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":"2302.07483","title":"EdgeYOLO: An Edge-Real-Time Object Detector","created":"2023-02-15","cited_by_count":6,"area":null},{"id":"2302.11089","title":"Recent Advancements in Deep Learning Applications and Methods for Autonomous Navigation: A Comprehensive Review","created":"2023-02-22","cited_by_count":6,"area":null},{"id":"2304.05098","title":"Benchmarking the Physical-world Adversarial Robustness of Vehicle Detection","created":"2023-04-11","cited_by_count":6,"area":null},{"id":"2311.05494","title":"Object-centric Cross-modal Feature Distillation for Event-based Object Detection","created":"2023-11-09","cited_by_count":6,"area":"distill"},{"id":"2312.10588","title":"Post-Training Quantization for Re-parameterization via Coarse & Fine Weight Splitting","created":"2023-12-17","cited_by_count":6,"area":null},{"id":"2402.16370","title":"DEYO: DETR with YOLO for End-to-End Object Detection","created":"2024-02-26","cited_by_count":6,"area":null},{"id":"2407.12597","title":"Enhancing Wrist Fracture Detection with YOLO","created":"2024-07-17","cited_by_count":6,"area":null},{"id":"2409.06259","title":"ALSS-YOLO: An Adaptive Lightweight Channel Split and Shuffling Network for TIR Wildlife Detection in UAV Imagery","created":"2024-09-10","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":"2605.26486","title":"LongCat-Video-Avatar 1.5 Technical Report","created":"2026-05-26","cited_by_count":6,"area":null},{"id":"2302.00386","title":"EfficientRep:An Efficient Repvgg-style ConvNets with Hardware-aware Neural Network Design","created":"2023-02-01","cited_by_count":5,"area":null},{"id":"2305.06553","title":"WeLayout: WeChat Layout Analysis System for the ICDAR 2023 Competition on Robust Layout Segmentation in Corporate Documents","created":"2023-05-11","cited_by_count":5,"area":null},{"id":"2307.16412","title":"RCS-YOLO: A Fast and High-Accuracy Object Detector for Brain Tumor Detection","created":"2023-07-31","cited_by_count":5,"area":null},{"id":"2308.03476","title":"Exploring the Physical World Adversarial Robustness of Vehicle Detection","created":"2023-08-07","cited_by_count":5,"area":null},{"id":"2308.11918","title":"AMSP-UOD: When Vortex Convolution and Stochastic Perturbation Meet Underwater Object Detection","created":"2023-08-23","cited_by_count":5,"area":null},{"id":"2309.04708","title":"UnitModule: A Lightweight Joint Image Enhancement Module for Underwater Object Detection","created":"2023-09-09","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":"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":"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":"2410.19869","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":"2504.10165","title":"WildLive: Near Real-time Visual Wildlife Tracking onboard UAVs","created":"2025-04-14","cited_by_count":5,"area":null},{"id":"2505.12820","title":"Rethinking Features-Fused-Pyramid-Neck for Object Detection","created":"2025-05-19","cited_by_count":5,"area":null},{"id":"2505.16740","title":"Robust Vision-Based Runway Detection through Conformal Prediction and Conformal mAP","created":"2025-05-22","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":"2211.06588","title":"DEYO: DETR with YOLO for Step-by-Step Object Detection","created":"2022-11-12","cited_by_count":4,"area":null},{"id":"2304.08842","title":"UDTIRI: An Online Open-Source Intelligent Road Inspection Benchmark Suite","created":"2023-04-18","cited_by_count":4,"area":null},{"id":"2309.01587","title":"SATAY: A Streaming Architecture Toolflow for Accelerating YOLO Models on FPGA Devices","created":"2023-09-04","cited_by_count":4,"area":null},{"id":"2403.00176","title":"SoD$^2$: Statically Optimizing Dynamic Deep Neural Network","created":"2024-02-29","cited_by_count":4,"area":null},{"id":"2404.07514","title":"Generalization Gap in Data Augmentation: Insights from Illumination","created":"2024-04-11","cited_by_count":4,"area":null},{"id":"2404.18413","title":"3AM: An Ambiguity-Aware Multi-Modal Machine Translation Dataset","created":"2024-04-29","cited_by_count":4,"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":"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":"2407.20872","title":"A Comparative Analysis of YOLOv5, YOLOv8, and YOLOv10 in Kitchen Safety","created":"2024-07-30","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":"2411.12301","title":"Physics-Guided Detector for SAR Airplanes","created":"2024-11-19","cited_by_count":4,"area":null},{"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":"2504.02558","title":"Rip Current Segmentation: A Novel Benchmark and YOLOv8 Baseline Results","created":"2025-04-03","cited_by_count":4,"area":null},{"id":"2504.17421","title":"Towards Harnessing the Collaborative Power of Large and Small Models for Domain Tasks","created":"2025-04-24","cited_by_count":4,"area":null},{"id":"2512.23273","title":"YOLO-Master: MOE-Accelerated with Specialized Transformers for Enhanced Real-time Detection","created":"2025-12-29","cited_by_count":4,"area":"moe"}],"next_cursor":"100"}