{"total":305,"rows":[{"id":"2506.09042","title":"Cosmos-Drive-Dreams: Scalable Synthetic Driving Data Generation with World Foundation Models","created":"2025-06-10","cited_by_count":84,"area":"driving"},{"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":"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":"2509.20787","title":"Real-Time Object Detection Meets DINOv3","created":"2025-09-25","cited_by_count":27,"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":"2508.19294","title":"Object Detection with Multimodal Large Vision-Language Models: An In-depth Review","created":"2025-08-25","cited_by_count":14,"area":"mllm"},{"id":"2504.13099","title":"RF-DETR Object Detection vs YOLOv12 : A Study of Transformer-based and CNN-based Architectures for Single-Class and Multi-Class Greenfruit Detection in Complex Orchard Environments Under Label Ambiguity","created":"2025-04-17","cited_by_count":12,"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":"2511.22989","title":"MultiBanana: A Challenging Benchmark for Multi-Reference Text-to-Image Generation","created":"2025-11-28","cited_by_count":9,"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":"2505.05741","title":"Dome-DETR: DETR with Density-Oriented Feature-Query Manipulation for Efficient Tiny Object Detection","created":"2025-05-09","cited_by_count":6,"area":null},{"id":"2508.10704","title":"Beyond conventional vision: RGB-event fusion for robust object detection in dynamic traffic scenarios","created":"2025-08-14","cited_by_count":6,"area":null},{"id":"2509.19875","title":"Adaptive Guidance Semantically Enhanced via Multimodal LLM for Edge-Cloud Object Detection","created":"2025-09-24","cited_by_count":6,"area":"mllm"},{"id":"2509.20745","title":"Neptune-X: Active X-to-Maritime Generation for Universal Maritime Object Detection","created":"2025-09-25","cited_by_count":6,"area":null},{"id":"2510.13080","title":"Counting Hallucinations in Diffusion Models","created":"2025-10-15","cited_by_count":6,"area":"diffusion"},{"id":"2601.08587","title":"MoCha:End-to-End Video Character Replacement without Structural Guidance","created":"2026-01-13","cited_by_count":6,"area":null},{"id":"2504.02280","title":"LLM-Guided Evolution: An Autonomous Model Optimization for Object Detection","created":"2025-04-03","cited_by_count":5,"area":null},{"id":"2503.17237","title":"Strong Baseline: Multi-UAV Tracking via YOLOv12 with BoT-SORT-ReID","created":"2025-03-21","cited_by_count":4,"area":null},{"id":"2505.15325","title":"SoftHGNN: Soft Hypergraph Neural Networks for General Visual Recognition","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2505.16402","title":"AdvReal: Physical Adversarial Patch Generation Framework for Security Evaluation of Object Detection Systems","created":"2025-05-22","cited_by_count":4,"area":null},{"id":"2506.01130","title":"ProstaTD: Bridging Surgical Triplet from Classification to Fully Supervised Detection","created":"2025-06-01","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":"2509.12047","title":"A Computer Vision Pipeline for Individual-Level Behavior Analysis: Benchmarking on the Edinburgh Pig Dataset","created":"2025-09-15","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"},{"id":"2601.04734","title":"AIVD: Adaptive Edge-Cloud Collaboration for Accurate and Efficient Industrial Visual Detection","created":"2026-01-08","cited_by_count":4,"area":"mllm"},{"id":"2503.00057","title":"Improved YOLOv12 with LLM-Generated Synthetic Data for Enhanced Apple Detection and Benchmarking Against YOLOv11 and YOLOv10","created":"2025-02-26","cited_by_count":3,"area":null},{"id":"2503.13883","title":"YOLO-LLTS: Real-Time Low-Light Traffic Sign Detection via Prior-Guided Enhancement and Multibranch Feature Interaction","created":"2025-03-18","cited_by_count":3,"area":null},{"id":"2504.16419","title":"PixelWeb: The First Web GUI Dataset with Pixel-Wise Labels","created":"2025-04-23","cited_by_count":3,"area":null},{"id":"2504.18586","title":"A Decade of You Only Look Once (YOLO) for Object Detection: A Review","created":"2025-04-24","cited_by_count":3,"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":"2506.14696","title":"YOLOv11-RGBT: Towards a Comprehensive Single-Stage Multispectral Object Detection Framework","created":"2025-06-17","cited_by_count":3,"area":null},{"id":"2506.21151","title":"Robust Deep Learning for Myocardial Scar Segmentation in Cardiac MRI with Noisy Labels","created":"2025-06-26","cited_by_count":3,"area":null},{"id":"2507.08729","title":"RoundaboutHD: High-Resolution Real-World Urban Environment Benchmark for Multi-Camera Vehicle Tracking","created":"2025-07-11","cited_by_count":3,"area":null},{"id":"2508.15038","title":"Decentralized Vision-Based Autonomous Aerial Wildlife Monitoring","created":"2025-08-20","cited_by_count":3,"area":null},{"id":"2509.17044","title":"AgriDoctor: A Multimodal Intelligent Assistant for Agriculture","created":"2025-09-21","cited_by_count":3,"area":null},{"id":"2512.15098","title":"Uni-Parser Technical Report","created":"2025-12-17","cited_by_count":3,"area":null},{"id":"2601.18597","title":"EFSI-DETR: Efficient Frequency-Semantic Integration for Real-Time Small Object Detection in UAV Imagery","created":"2026-01-26","cited_by_count":3,"area":null},{"id":"2602.00168","title":"YOLOE-26: Integrating YOLO26 with YOLOE for Real-Time Open-Vocabulary Instance Segmentation","created":"2026-01-29","cited_by_count":3,"area":null},{"id":"2602.00249","title":"SANEval: Open-Vocabulary Compositional Benchmarks with Failure-mode Diagnosis","created":"2026-01-30","cited_by_count":3,"area":null},{"id":"2602.04547","title":"OmniRad: A Radiological Foundation Model for Multi-Task Medical Image Analysis","created":"2026-02-04","cited_by_count":3,"area":null},{"id":"2602.11730","title":"STVG-R1: Incentivizing Instance-Level Reasoning and Grounding in Videos via Reinforcement Learning","created":"2026-02-12","cited_by_count":3,"area":"lr"},{"id":"2602.13305","title":"WildfireVLM: AI-powered Analysis for Early Wildfire Detection and Risk Assessment Using Satellite Imagery","created":"2026-02-09","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":"2604.23970","title":"LLM-Guided Agentic Floor Plan Parsing for Accessible Indoor Navigation of Blind and Low-Vision People","created":"2026-04-27","cited_by_count":3,"area":"agents"},{"id":"2605.16740","title":"TRACE: Evidence Grounding-Guided Multi-Video Event Understanding and Claim Generation","created":"2026-05-16","cited_by_count":3,"area":null},{"id":"2606.07953","title":"Unification of Closed-Open Industrial Detection Scenarios: New Large-Scale Benchmarks,Challenges and Baselines","created":"2026-06-06","cited_by_count":3,"area":"mllm"},{"id":"2504.15165","title":"An Efficient Aerial Image Detection with Variable Receptive Fields","created":"2025-04-21","cited_by_count":2,"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":"2504.19722","title":"The ATLAS of Traffic Lights: A Reliable Perception Framework for Autonomous Driving","created":"2025-04-28","cited_by_count":2,"area":null},{"id":"2507.12832","title":"MVA 2025 Small Multi-Object Tracking for Spotting Birds Challenge: Dataset, Methods, and Results","created":"2025-07-17","cited_by_count":2,"area":null},{"id":"2508.12813","title":"SIS-Challenge: Event-based Spatio-temporal Instance Segmentation Challenge at the CVPR 2025 Event-based Vision Workshop","created":"2025-08-18","cited_by_count":2,"area":null},{"id":"2509.18388","title":"MVP: Motion Vector Propagation for Zero-Shot Video Object Detection","created":"2025-09-22","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":"2509.22909","title":"TY-RIST: Tactical YOLO Tricks for Real-time Infrared Small Target Detection","created":"2025-09-26","cited_by_count":2,"area":null},{"id":"2510.05759","title":"OneVision: An End-to-End Generative Framework for Multi-view E-commerce Vision Search","created":"2025-10-07","cited_by_count":2,"area":null},{"id":"2510.07580","title":"MaizeStandCounting (MaSC): Automated and Accurate Maize Stand Counting from UAV Imagery Using Image Processing and Deep Learning","created":"2025-10-08","cited_by_count":2,"area":null},{"id":"2510.14946","title":"EdgeNavMamba: Mamba Optimized Object Detection for Energy Efficient Edge Devices","created":"2025-10-16","cited_by_count":2,"area":"ssm"},{"id":"2510.21532","title":"FrameShield: Adversarially Robust Video Anomaly Detection","created":"2025-10-24","cited_by_count":2,"area":null},{"id":"2511.00653","title":"Benchmarking individual tree segmentation using multispectral airborne laser scanning data: the FGI-EMIT dataset","created":"2025-11-01","cited_by_count":2,"area":null},{"id":"2511.18344","title":"A Tri-Modal Dataset and a Baseline System for Tracking Unmanned Aerial Vehicles","created":"2025-11-23","cited_by_count":2,"area":null},{"id":"2512.18046","title":"YolovN-CBi: A Lightweight and Efficient Architecture for Real-Time Detection of Small UAVs","created":"2025-12-19","cited_by_count":2,"area":null},{"id":"2602.14582","title":"YOLO26: A Comprehensive Architecture Overview and Key Improvements","created":"2026-02-16","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":"2506.07637","title":"HieraEdgeNet: A Multi-Scale Edge-Enhanced Framework for Automated Pollen Recognition","created":"2025-06-09","cited_by_count":1,"area":null},{"id":"2506.12697","title":"MGDFIS: Multi-scale Global-detail Feature Integration Strategy for Small Object Detection","created":"2025-06-15","cited_by_count":1,"area":null},{"id":"2506.19498","title":"T-Rex: Task-Adaptive Spatial Representation Extraction for Robotic Manipulation with Vision-Language Models","created":"2025-06-24","cited_by_count":1,"area":"mllm"},{"id":"2506.22517","title":"Container damage detection using advanced computer vision model Yolov12 vs Yolov11 vs RF-DETR A comparative analysis","created":"2025-06-26","cited_by_count":1,"area":null},{"id":"2506.23505","title":"Improve Underwater Object Detection through YOLOv12 Architecture and Physics-informed Augmentation","created":"2025-06-30","cited_by_count":1,"area":null},{"id":"2507.00825","title":"High-Frequency Semantics and Geometric Priors for End-to-End Detection Transformers in Challenging UAV Imagery","created":"2025-07-01","cited_by_count":1,"area":null},{"id":"2507.12344","title":"Improving Lightweight Weed Detection via Knowledge Distillation","created":"2025-07-16","cited_by_count":1,"area":"distill"},{"id":"2507.17859","title":"FishDet-M: A Unified Large-Scale Benchmark for Robust Fish Detection and CLIP-Guided Model Selection in Diverse Aquatic Visual Domains","created":"2025-07-23","cited_by_count":1,"area":null},{"id":"2508.06537","title":"Benchmarking Deep Learning-Based Object Detection Models on Feature Deficient Astrophotography Imagery Dataset","created":"2025-08-04","cited_by_count":1,"area":null},{"id":"2508.08352","title":"Designing Object Detection Models for TinyML: Foundations, Comparative Analysis, Challenges, and Emerging Solutions","created":"2025-08-11","cited_by_count":1,"area":null},{"id":"2508.17666","title":"M^3-GloDets: Multi-Region and Multi-Scale Analysis of Fine-Grained Diseased Glomerular Detection","created":"2025-08-25","cited_by_count":1,"area":null},{"id":"2509.12442","title":"Cott-ADNet: Lightweight Real-Time Cotton Boll and Flower Detection Under Field Conditions","created":"2025-09-15","cited_by_count":1,"area":null},{"id":"2509.15181","title":"Maize Seedling Detection Dataset (MSDD): A Curated High-Resolution RGB Dataset for Seedling Maize Detection and Benchmarking with YOLOv9, YOLO11, YOLOv12 and Faster-RCNN","created":"2025-09-18","cited_by_count":1,"area":null},{"id":"2509.17792","title":"Degradation-Aware All-in-One Image Restoration via Latent Prior Encoding","created":"2025-09-22","cited_by_count":1,"area":null},{"id":"2509.20318","title":"A Comprehensive Evaluation of YOLO-based Deer Detection Performance on Edge Devices","created":"2025-09-24","cited_by_count":1,"area":null},{"id":"2509.25564","title":"FishNet++: Analyzing the capabilities of Multimodal Large Language Models in marine biology","created":"2025-09-29","cited_by_count":1,"area":"mllm"},{"id":"2509.26166","title":"Beyond Overall Accuracy: Pose- and Occlusion-driven Fairness Analysis in Pedestrian Detection for Autonomous Driving","created":"2025-09-30","cited_by_count":1,"area":null},{"id":"2510.01651","title":"LadderMoE: Ladder-Side Mixture of Experts Adapters for Bronze Inscription Recognition","created":"2025-10-02","cited_by_count":1,"area":null},{"id":"2510.27263","title":"ODP-Bench: Benchmarking Out-of-Distribution Performance Prediction","created":"2025-10-31","cited_by_count":1,"area":null},{"id":"2511.15204","title":"Physics-Based Benchmarking Metrics for Multimodal Synthetic Images","created":"2025-11-19","cited_by_count":1,"area":null},{"id":"2512.01665","title":"Bridging the Scale Gap: Balanced Tiny and General Object Detection in Remote Sensing Imagery","created":"2025-12-01","cited_by_count":1,"area":"moe"},{"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":"2512.09489","title":"MODA: The First Challenging Benchmark for Multispectral Object Detection in Aerial Images","created":"2025-12-10","cited_by_count":1,"area":null},{"id":"2512.20011","title":"PaveSync: A Unified and Comprehensive Dataset for Pavement Distress Analysis and Classification","created":"2025-12-23","cited_by_count":1,"area":null},{"id":"2601.02016","title":"Enhancing Object Detection with Privileged Information: A Model-Agnostic Teacher-Student Approach","created":"2026-01-05","cited_by_count":1,"area":"distill"},{"id":"2601.04991","title":"Higher-Order Adversarial Patches for Real-Time Object Detectors","created":"2026-01-08","cited_by_count":1,"area":null},{"id":"2602.04170","title":"Partial Ring Scan: Revisiting Scan Order in Vision State Space Models","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2602.19380","title":"Detector-in-the-Loop Tracking: Active Memory Rectification for Stable Glottic Opening Localization","created":"2026-02-22","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":"2603.06386","title":"REACT++: Efficient Cross-Attention for Real-Time Scene Graph Generation","created":"2026-03-06","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":"2603.10604","title":"HyPER-GAN: Hybrid Patch-Based Image-to-Image Translation for Real-Time Photorealism Enhancement in Game Engines","created":"2026-03-11","cited_by_count":1,"area":null},{"id":"2603.17684","title":"Does YOLO Really Need to See Every Training Image in Every Epoch?","created":"2026-03-18","cited_by_count":1,"area":null},{"id":"2603.22841","title":"UAV-DETR: DETR for Anti-Drone Target Detection","created":"2026-03-24","cited_by_count":1,"area":null}],"next_cursor":"100"}