{"total":79,"rows":[{"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":"2510.16017","title":"InfraGPT Smart Infrastructure: An End-to-End VLM-Based Framework for Detecting and Managing Urban Defects","created":"2025-10-15","cited_by_count":3,"area":"mllm"},{"id":"2510.16371","title":"Cataract-LMM Large-Scale Multi-Source Multi-Task Benchmark for Deep Learning in Surgical Video Analysis","created":"2025-10-18","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":"2603.13507","title":"MIRAGE: Model-agnostic Industrial Realistic Anomaly Generation and Evaluation for Visual Anomaly Detection","created":"2026-03-13","cited_by_count":3,"area":null},{"id":"2605.19619","title":"MiMuon: Mixed Muon Optimizer with Improved Generalization for Large Models","created":"2026-05-19","cited_by_count":3,"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":"2603.17684","title":"Does YOLO Really Need to See Every Training Image in Every Epoch?","created":"2026-03-18","cited_by_count":1,"area":null},{"id":"2604.14661","title":"AIPC: Agent-Based Automation for AI Model Deployment with Qualcomm AI Runtime","created":"2026-04-16","cited_by_count":1,"area":null},{"id":"2605.29894","title":"Train the Agent, Not the Expert: Learning to Harness Heterogeneous Experts for Multi-Turn Visual Reasoning","created":"2026-05-28","cited_by_count":1,"area":"lr"},{"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":"2607.07320","title":"SoccerNet 2026 Challenges Results","created":"2026-07-08","cited_by_count":1,"area":null},{"id":"2608.15705","title":"PixelControl: Fine-Grained Condition Fidelity in Text-to-Image Diffusion","created":"2026-08-16","cited_by_count":1,"area":"diffusion"},{"id":"2512.13130","title":"LeafTrackNet: A Deep Learning Framework for Robust Leaf Tracking in Top-Down Plant Phenotyping","created":"2025-12-15","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":"2602.13330","title":"Zwitscherkasten -- DIY Audiovisual bird monitoring","created":"2026-02-11","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":"2603.16351","title":"Automated identification of Ichneumonoidea wasps via YOLO-based deep learning: Integrating HiresCam for Explainable AI","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2603.26755","title":"Domain-Guided YOLO26 with Composite BCE-Dice-Lov\\'{a}sz Loss for Multi-Class Fetal Head Ultrasound Segmentation","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2604.01129","title":"ReinDriveGen: Reinforcement Post-Training for Out-of-Distribution Driving Scene Generation","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2604.01958","title":"MAVFusion: Efficient Infrared and Visible Video Fusion via Motion-Aware Sparse Interaction","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.02032","title":"IndoorCrowd: A Multi-Scene Dataset for Human Detection, Segmentation, and Tracking with an Automated Annotation Pipeline","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.03317","title":"Gaze to Insight: A Scalable AI Approach for Detecting Gaze Behaviours in Face-to-Face Collaborative Learning","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2604.07132","title":"CSA-Graphs: A Privacy-Preserving Structural Dataset for Child Sexual Abuse Research","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2604.10017","title":"What and Where to Adapt: Structure-Semantics Co-Tuning for Machine Vision Compression via Synergistic Adapters","created":"2026-04-11","cited_by_count":0,"area":null},{"id":"2604.10077","title":"DocRevive: A Unified Pipeline for Document Text Restoration","created":"2026-04-11","cited_by_count":0,"area":null},{"id":"2604.15221","title":"Vision-Based Safe Human-Robot Collaboration with Uncertainty Guarantees","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2604.21313","title":"PLAS-Net: Pixel-Level Area Segmentation for UAV-Based Beach Litter Monitoring","created":"2026-04-23","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":"2604.28197","title":"OmniRobotHome: A Multi-Camera Home Platform for Real-Time Human-Robot Interaction","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2605.00908","title":"Evaluation of Convolutional and Transformer-Based Detectors for Weed Detection in Tomato Plantations","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2605.02291","title":"A Hybrid Approach for Closing the Sim2real Appearance Gap in Game Engine Synthetic Datasets","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2605.07388","title":"A Marine Debris Detection Framework for Ocean Robots via Self-Attention Enhancement and Feature Interaction Optimization","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.08781","title":"Contour-Native Bridge Defect Detection and Compact Digital Archiving with Frequency-Supervised Fourier Contours","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.18413","title":"Cracks in the Foundation: A Civil Infrastructure Dataset to Challenge Vision Foundation Models","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2605.19595","title":"A novel YOLO26-MoE optimized by an LLM agent for insulator fault detection considering UAV images","created":"2026-05-19","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":"2605.26533","title":"A Hybrid Vision-Language Architecture for Automated Defect Reasoning and Report Generation in Industrial Inspection","created":"2026-05-26","cited_by_count":0,"area":"lr"},{"id":"2606.09882","title":"WHU-Infra3D: A Full-stack Multi-modal Dataset and Benchmark for 3D Roadside Infrastructure Inventory","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.10940","title":"Democratising Camera Trap AI: An Open-Source Model for Detecting UK Mammals","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2606.15049","title":"Gaussian Spatial Priors for Anatomy-Aware Object Detection in Surgical Videos","created":"2026-06-13","cited_by_count":0,"area":null},{"id":"2606.18523","title":"DART: A design-aware microfluidic chip paradigm for real-time live-cell image analysis","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2606.22515","title":"Biological Sex Determination in Cadavers Using Deep Learning Algorithms from Computed Tomography Images of Pelvis and Skull","created":"2026-06-21","cited_by_count":0,"area":null},{"id":"2606.23825","title":"From Spatial to Spectral: An Efficient, Frequency-Guided Feature Representation Learner for Small Object Detection","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2606.25284","title":"Evaluation Protocols and Validation for Cameras in Indoor Healthcare Monitoring","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2606.25732","title":"Efficient Real-World Dehazing via Physics-Inspired Global-Local Decoupling","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2606.27317","title":"OctoSense: Self-Supervised Learning for Multimodal Robot Perception","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2607.05153","title":"Geometric Causal Models","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.09835","title":"Does YOLO26 Truly Offer Advantages Over Its Predecessors for Edge Deployment? A Benchmark Study in Aquaculture","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2607.10749","title":"Water Reflection Detection Using Symmetric Attention","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2607.10990","title":"TreeSoc: Tree-Structured Dynamic Reasoning and Tool Synergy for Soccer Video Understanding","created":"2026-07-13","cited_by_count":0,"area":"lr"},{"id":"2607.15082","title":"Towards Hierarchical Structure Understanding of Newspaper Images","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2607.15527","title":"Physics-aware Masked Diffusion-based Flood Simulation for Urban Fisheye Disaster Detection","created":"2026-07-17","cited_by_count":0,"area":"diffusion"},{"id":"2607.18283","title":"FedCC: A Low-Resource Federated Adaptation of Foundation Models for Robust Corpus Callosum localization in Fetal Ultrasound Images","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.18747","title":"SkyEV: RGB-Event UAV detection and tracking dataset and baseline","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2607.28996","title":"SULAND v2: A Refined RGB Dataset and Deep Learning Object Detection Benchmark for UAV/UGV-Based SUrface LANDmine Detection Under Domain Shift","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.01906","title":"Assessing the Benefits of Combining Advanced Deep Learning Techniques for Post-Disaster Building Damage Assessment from UAV Imagery","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.02177","title":"GSRAIN: Physically Calibrated High-/Low-Frequency Rainfall Synthesis for 3D Gaussian Driving Scenes","created":"2026-08-03","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":"2608.13047","title":"Topology-Unified 2D Pose Estimation across Intact, Residual and Prosthetic Limbs","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.14770","title":"Artificial Intelligence as a Tool for Combating Child Labour: A Real-Time Edge Vision Pipeline for Child Detection and Age Estimation","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2608.18035","title":"Plug-and-Play Traffic Element Awareness for End-to-End Autonomous Driving","created":"2026-08-18","cited_by_count":0,"area":"driving"},{"id":"2608.28662","title":"FRAC-MAS: A Safe and Explainable Multi-Agent System for Fracture Diagnosis","created":"2026-08-22","cited_by_count":0,"area":"agents"},{"id":"2609.02705","title":"A Top-Down Framework for Metric-Scale Athlete Localization from Single Broadcast Frames","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.06208","title":"From Gaze to Meaning: A Training-Free AI Agent for Unified Grounding and Explanation","created":"2026-09-05","cited_by_count":0,"area":"agents"},{"id":"2609.07780","title":"DroneGround: Open-Vocabulary Drone Payload Characterization Using Synthetic Data and Grounded Vision-Language Models","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.11126","title":"Beyond Benchmarks: Using VLMs to Reveal Systematic Classification Failures Under Real World Conditions","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.13595","title":"Predictive audio representations for early detection and tracking of hidden dynamic objects","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.15221","title":"MAST: Label-Efficient, Robust, and Generalizable Sound Detection for Biodiversity Monitoring via Masked Audio Pretraining and Self-Training","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.23714","title":"Infectious Bovine Pinkeye Detection Using Computer Vision and Imbalance-Aware Learning","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2609.29648","title":"Albireo: Adaptive, Energy-Efficient Inference Framework for Video Object Detection on the Edge","created":"2026-08-29","cited_by_count":0,"area":null},{"id":"2609.33991","title":"A Multi-Dataset Benchmark of YOLO-Based Weed Detection in Precision Agriculture","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.35726","title":"Impact of Patient Orientation in Single- and Multi-View Camera Environments for AI-based Rehabilitation Monitoring","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.05074","title":"ReDiffNet: Differential RGB-Infrared Learning for Low-Light UAV Oriented Vehicle Detection","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.07117","title":"R2RI: A Multi-View Event and RGB Dataset for Robot-to-Robot Interaction","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.09511","title":"LiG-DETR: Local-in-Global Reassembly in Latent Space for Aerial Object Detection","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.14846","title":"Towards Privacy-Preserving Thermal Human Perception from Dataset to Deployment","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}