{"total":54,"rows":[{"id":"2606.25763","title":"ShutterMuse: Capture-Time Photography Guidance with MLLMs","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2607.17799","title":"Toward Optimal Adenovirus Detection Using YOLO26","created":"2026-07-20","cited_by_count":1,"area":null},{"id":"2608.21429","title":"Measuring Gender Representation in Animated Films","created":"2026-08-17","cited_by_count":1,"area":null},{"id":"2606.21568","title":"A Smart Classroom Behavior Analysis Framework with a New Highly Congested Classroom Dataset","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2607.10575","title":"Why Domain Matters: Domain-Aware Benchmarking of Underwater Object Detection and Annotation Quality","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2607.12544","title":"Edge-Aware Thermal Infrared UAV Swarm Tracking","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2607.14445","title":"Cotton-SF YOLO: Learning Structural and Frequency Cues for Early Cotton Square Detection in Complex Field Environments","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2607.14934","title":"Still image and spatial-temporal tomato data enabling detection, segmentation, tracking, and video-instance segmentation using strong and weak labels","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2607.19040","title":"Gaze-DETR: Top-Down Guidance Through Priority Maps for Infrared Weak-Small UAV Detection with DETR","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2607.19069","title":"Delineate Anything v2: A Global Foundation Model for Field Delineation","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2607.22913","title":"Small-Pollinator Detection in Cluttered Field Video","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2608.00257","title":"MDWD: A Street-Level Dataset for Municipal Solid Waste Detection in Dense Urban Environments","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.00508","title":"RadYOLO: Computationally Efficient 3D Object Detection and Segmentation in CT and MRI","created":"2026-08-01","cited_by_count":0,"area":null},{"id":"2608.06801","title":"AdvTiles: Physical Adversarial Camouflage Clothing against Person Detectors via Learnable Tiles","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.07382","title":"SkySeaLand: A Wide-Format Satellite Transportation Benchmark with an Ultra-Lightweight Detection Baseline","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.10801","title":"Evaluating Semantic and Spatial Guidance for Foundation Model Segmentation of Small-Scale PV in Remote Sensing Imagery","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.13343","title":"AmalthAI: An Open-Source Computer Vision Platform for Cultural Heritage","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.15713","title":"YOLO26-RD: An End-to-End Road Damage Detection Network With Learnable Contrast Enhancement and Edge-Guided Downsampling","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2608.20608","title":"A Dataset-Centric Benchmark of Deep Learning Methods for Grape Leaf Disease Classification and Detection","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2608.21099","title":"A2DINOv3: Rethinking Multi-Modal Object Detection via Socialized Collaboration","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2608.23636","title":"Optimizing YOLO27, YOLO26, YOLO11, and YOLOv8 for Fine-Grained Small-Object Detection and Segmentation in Complex Orchard Environments","created":"2026-08-23","cited_by_count":0,"area":null},{"id":"2608.29210","title":"Imag-Eval: a language-grounded framework for interpretable Text-to-Image instruction following evaluation","created":"2026-08-29","cited_by_count":0,"area":null},{"id":"2608.30709","title":"RailSyn: Diagnosis-Guided Image Generation for Traceable Data Completion in Railway Foreign Object Detection","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.00646","title":"DramaChain Bench: An End-to-End Benchmark for Short-Drama Generation","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.01257","title":"Measuring the Behavioral Fidelity of Long-Horizon Human Activity Simulations","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.02251","title":"Handwriting Trajectory Recovery via Autoregressive Ordered Stroke Instance Prediction","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.05323","title":"Scalable Detection of Fossil Palynomorphs in Multifocal Digital Microscopy Images","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.06774","title":"NEO-BENCH: A New Multi-Source Benchmark for Generalizable Astronomical Streak Detection","created":"2026-09-06","cited_by_count":0,"area":null},{"id":"2609.12202","title":"QuPAINT: Physics-Aware Multimodal Reasoning for Quantum Material Characterization","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.14025","title":"Quantum-Gated LiteSSD: A Parameter-Efficient Lightweight Hybrid Quantum-Classical Framework for Forward-Looking Sonar Object Detection","created":"2026-09-12","cited_by_count":0,"area":null},{"id":"2609.17168","title":"HuMemSLAM: Efficient Human-Inspired Semantic Place Recognition for Robust Visual SLAM","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.17189","title":"EventEgoHands++: Event-based Egocentric 3D Hand Mesh Reconstruction with Real Dataset","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.19592","title":"Selective Cotton Boll Localization for Robotic Harvesting: Evaluation of Deep Learning Vision Models Under Field Conditions","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.20509","title":"Automated Goldsmith's Mark Retrieval in Silverware","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.20615","title":"INSPECT: Learning Robot View Selection from Assistant Use","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.23017","title":"Reconstructed holograms and explanation-aware evaluation for low-cost computational pollen analysis in veterinary cytology","created":"2026-09-19","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":"2609.24668","title":"Ev-YOLO: Uncertainty-Aware Object Detection via a Unified Evidential Formulation","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.26590","title":"GTR: Gated Token Recurrence for Efficient Dense Prediction","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.28358","title":"MicroQonv: Reshaping Convolution Tensors for Efficient Microscaling in Training and Inference","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.29447","title":"Frame-to-Panorama Localization and Context-Aware Sampling for Scene-Specific Ship Detection in a Smart Marina Testbed","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.31702","title":"CLC-YOLO: A Compact Channel-Gated Prototype Network for Real-Time Leakage-Aware Breast Ultrasound Lesion Segmentation","created":"2026-09-19","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":"2609.37801","title":"ByteTraX: Enhancing the ByteTrack Architecture with Optimised Thresholding","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38347","title":"TrackFish3D: Self-Supervised 3D Tracking of Schooling Fish from Multi-view Videos","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.00451","title":"PACT: End-to-End Learning of Human Pose, Contacts, and Forces from Video","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.02799","title":"FUSEye: Training-Light Fisheye Detection with Overlapping Views and Zero-Initialized Adapters","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.03051","title":"BeeWhere: Segmenting Bumble Bee Colonies to Quantify Behavioral Effects","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.04356","title":"SelectOccFlow: Selective Spatiotemporal Aggregation for 3D Occupancy and Scene Flow Prediction","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.05505","title":"Robust 2D Traversability Mapping for Construction AMRs via Failure-Mode-Aware Fusion of LiDAR Geometry and Monocular Semantics","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.07705","title":"What Frame-Level Labels Can and Cannot Do for Small-UAV Point Detection in Thermal Video","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.08570","title":"Less Is More: A Leakage-Controlled Study of Dermoscopic Preprocessing for Joint Skin Lesion Classification and Segmentation with YOLO26","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.08756","title":"Post-Training Semantic Lifting for 3D Gaussian Splatting: Separating Detector, Lifting and Representation Error","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.20603","title":"CommerceGen-Studio: An End-to-End Framework for Commercial-Grade Main-Image Generation","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}