{"total":515,"rows":[{"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":"2409.18839","title":"MinerU: An Open-Source Solution for Precise Document Content Extraction","created":"2024-09-27","cited_by_count":267,"area":null},{"id":"2509.22186","title":"MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing","created":"2025-09-26","cited_by_count":116,"area":"mllm"},{"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":"2506.05218","title":"MonkeyOCR: Document Parsing with a Structure-Recognition-Relation Triplet Paradigm","created":"2025-06-05","cited_by_count":87,"area":null},{"id":"2410.12628","title":"DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception","created":"2024-10-16","cited_by_count":82,"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":"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":"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":"2406.03459","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":"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":"2503.19839","title":"FireEdit: Fine-grained Instruction-based Image Editing via Region-aware Vision Language Model","created":"2025-03-25","cited_by_count":32,"area":"mllm"},{"id":"2503.10080","title":"Bayesian Prompt Flow Learning for Zero-Shot Anomaly Detection","created":"2025-03-13","cited_by_count":31,"area":"mllm"},{"id":"2509.20787","title":"Real-Time Object Detection Meets DINOv3","created":"2025-09-25","cited_by_count":27,"area":null},{"id":"2412.05819","title":"[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs","created":"2024-12-08","cited_by_count":26,"area":"mllm"},{"id":"2503.17213","title":"PP-DocLayout: A Unified Document Layout Detection Model to Accelerate Large-Scale Data Construction","created":"2025-03-21","cited_by_count":26,"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":"2506.02404","title":"GraphRAG-Bench: Challenging Domain-Specific Reasoning for Evaluating Graph Retrieval-Augmented Generation","created":"2025-06-03","cited_by_count":24,"area":"lr"},{"id":"2512.15258","title":"VLA-AN: An Efficient and Onboard Vision-Language-Action Framework for Aerial Navigation in Complex Environments","created":"2025-12-17","cited_by_count":23,"area":"vla"},{"id":"2601.01528","title":"DrivingGen: A Comprehensive Benchmark for Generative Video World Models in Autonomous Driving","created":"2026-01-04","cited_by_count":21,"area":"wm"},{"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":"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":"2503.23135","title":"LSNet: See Large, Focus Small","created":"2025-03-29","cited_by_count":15,"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":"2412.18292","title":"Enhancing Multi-Robot Semantic Navigation Through Multimodal Chain-of-Thought Score Collaboration","created":"2024-12-24","cited_by_count":14,"area":"lr"},{"id":"2503.23398","title":"A Large Scale Analysis of Gender Biases in Text-to-Image Generative Models","created":"2025-03-30","cited_by_count":14,"area":null},{"id":"2506.23575","title":"Event-based Tiny Object Detection: A Benchmark Dataset and Baseline","created":"2025-06-30","cited_by_count":14,"area":null},{"id":"2411.17261","title":"HEIE: MLLM-Based Hierarchical Explainable AIGC Image Implausibility Evaluator","created":"2024-11-26","cited_by_count":13,"area":null},{"id":"2412.01798","title":"SEAL: Semantic Attention Learning for Long Video Representation","created":"2024-12-02","cited_by_count":13,"area":null},{"id":"2412.03409","title":"PrefixKV: Adaptive Prefix KV Cache is What Vision Instruction-Following Models Need for Efficient Generation","created":"2024-12-04","cited_by_count":13,"area":"lr"},{"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":"2508.18722","title":"VistaWise: Building Cost-Effective Agent with Cross-Modal Knowledge Graph for Minecraft","created":"2025-08-26","cited_by_count":13,"area":"agents"},{"id":"2511.10390","title":"MonkeyOCR v1.5 Technical Report: Unlocking Robust Document Parsing for Complex Patterns","created":"2025-11-13","cited_by_count":13,"area":"rag"},{"id":"2407.02988","title":"YOLOv5, YOLOv8 and YOLOv10: The Go-To Detectors for Real-time Vision","created":"2024-07-03","cited_by_count":12,"area":null},{"id":"2412.11154","title":"From Easy to Hard: Progressive Active Learning Framework for Infrared Small Target Detection with Single Point Supervision","created":"2024-12-15","cited_by_count":12,"area":null},{"id":"2501.13354","title":"ATRNet-STAR: A Large Dataset and Benchmark Towards Remote Sensing Object Recognition in the Wild","created":"2025-01-23","cited_by_count":12,"area":null},{"id":"2407.19696","title":"Cross-Layer Feature Pyramid Transformer for Small Object Detection in Aerial Images","created":"2024-07-29","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":"2411.16934","title":"Online Episodic Memory Visual Query Localization with Egocentric Streaming Object Memory","created":"2024-11-25","cited_by_count":11,"area":null},{"id":"2410.09831","title":"LoLI-Street: Benchmarking Low-Light Image Enhancement and Beyond","created":"2024-10-13","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":"2604.04911","title":"SpatialEdit: Benchmarking Fine-Grained Image Spatial Editing","created":"2026-04-06","cited_by_count":10,"area":null},{"id":"2509.00649","title":"MV-SSM: Multi-View State Space Modeling for 3D Human Pose Estimation","created":"2025-08-31","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":"2505.17449","title":"Real-time Traffic Accident Anticipation with Feature Reuse","created":"2025-05-23","cited_by_count":8,"area":null},{"id":"2407.21308","title":"Enhanced Self-Checkout System for Retail Based on Improved YOLOv10","created":"2024-07-31","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":"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":"2412.20875","title":"Attention Is All You Need For Mixture-of-Depths Routing","created":"2024-12-30","cited_by_count":7,"area":null},{"id":"2501.06184","title":"PEACE: Empowering Geologic Map Holistic Understanding with MLLMs","created":"2025-01-10","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":"2409.05650","title":"Replay Consolidation with Label Propagation for Continual Object Detection","created":"2024-09-09","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":"2502.14063","title":"PedDet: Adaptive Spectral Optimization for Multimodal Pedestrian Detection","created":"2025-02-19","cited_by_count":6,"area":null},{"id":"2503.08726","title":"SIMAC: A Semantic-Driven Integrated Multimodal Sensing And Communication Framework","created":"2025-03-11","cited_by_count":6,"area":null},{"id":"2505.00630","title":"Vision Mamba in Remote Sensing: A Comprehensive Survey of Techniques, Applications and Outlook","created":"2025-05-01","cited_by_count":6,"area":"ssm"},{"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":"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":"2512.09607","title":"UrbanNav: Learning Language-Guided Urban Navigation from Web-Scale Human Trajectories","created":"2025-12-10","cited_by_count":6,"area":null},{"id":"2605.15199","title":"EntityBench: Towards Entity-Consistent Long-Range Multi-Shot Video Generation","created":"2026-05-14","cited_by_count":6,"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":"2409.07003","title":"ODYSSEE: Oyster Detection Yielded by Sensor Systems on Edge Electronics","created":"2024-09-11","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":"2411.03403","title":"Enhancing Maritime Situational Awareness through End-to-End Onboard Raw Data Analysis","created":"2024-11-05","cited_by_count":5,"area":null},{"id":"2411.16170","title":"CARE Transformer: Mobile-Friendly Linear Visual Transformer via Decoupled Dual Interaction","created":"2024-11-25","cited_by_count":5,"area":null},{"id":"2412.12505","title":"DocFusion: A Unified Framework for Document Parsing Tasks","created":"2024-12-17","cited_by_count":5,"area":null},{"id":"2501.06262","title":"Towards smart and adaptive agents for active sensing on edge devices","created":"2025-01-09","cited_by_count":5,"area":null},{"id":"2503.07252","title":"Semantic Communications with Computer Vision Sensing for Edge Video Transmission","created":"2025-03-10","cited_by_count":5,"area":null},{"id":"2504.02534","title":"Delineate Anything: Resolution-Agnostic Field Boundary Delineation on Satellite Imagery","created":"2025-04-03","cited_by_count":5,"area":null},{"id":"2510.02226","title":"TempoControl: Temporal Attention Guidance for Text-to-Video Models","created":"2025-10-02","cited_by_count":5,"area":null},{"id":"2602.01864","title":"Trust but Verify: Adaptive Conditioning for Reference-Based Diffusion Super-Resolution via Implicit Reference Correlation Modeling","created":"2026-02-02","cited_by_count":5,"area":"diffusion"},{"id":"2602.09002","title":"From Obstacles to Etiquette: Robot Social Navigation with VLM-Informed Path Selection","created":"2026-02-09","cited_by_count":5,"area":null},{"id":"2603.28130","title":"MDPBench: A Benchmark for Multilingual Document Parsing in Real-World Scenarios","created":"2026-03-30","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":"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":"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":"2412.00348","title":"Vision Technologies with Applications in Traffic Surveillance Systems: A Holistic Survey","created":"2024-11-30","cited_by_count":4,"area":null},{"id":"2412.01440","title":"BadPatch: Diffusion-Based Generation of Physical Adversarial Patches","created":"2024-12-02","cited_by_count":4,"area":"diffusion"},{"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":"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":"2504.02287","title":"MultiSensor-Home: A Wide-area Multi-modal Multi-view Dataset for Action Recognition and Transformer-based Sensor Fusion","created":"2025-04-03","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":"2506.01130","title":"ProstaTD: Bridging Surgical Triplet from Classification to Fully Supervised Detection","created":"2025-06-01","cited_by_count":4,"area":null},{"id":"2506.08887","title":"DiscoVLA: Discrepancy Reduction in Vision, Language, and Alignment for Parameter-Efficient Video-Text Retrieval","created":"2025-06-10","cited_by_count":4,"area":null},{"id":"2506.13457","title":"Deep Learning-Based Multi-Object Tracking: A Comprehensive Survey from Foundations to State-of-the-Art","created":"2025-06-16","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":"2507.22522","title":"Recognizing Actions from Robotic View for Natural Human-Robot Interaction","created":"2025-07-30","cited_by_count":4,"area":null}],"next_cursor":"100"}