{"total":68,"rows":[{"id":"2502.12524","title":"YOLOv12: Attention-Centric Real-Time Object Detectors","created":"2025-02-18","cited_by_count":305,"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":"2510.15783","title":"ReCon: Region-Controllable Data Augmentation with Rectification and Alignment for Object Detection","created":"2025-10-17","cited_by_count":6,"area":"diffusion"},{"id":"2509.23700","title":"INSTINCT: Instance-Level Interaction Architecture for Query-Based Collaborative Perception","created":"2025-09-28","cited_by_count":5,"area":null},{"id":"2603.06917","title":"PaQ-DETR: Learning Pattern and Quality-Aware Dynamic Queries for Object Detection","created":"2026-03-06","cited_by_count":4,"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":"2603.07022","title":"OV-DEIM: Real-time DETR-Style Open-Vocabulary Object Detection with GridSynthetic Augmentation","created":"2026-03-07","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":"2604.03685","title":"DSERT-RoLL: Robust Multi-Modal Perception for Diverse Driving Conditions with Stereo Event-RGB-Thermal Cameras, 4D Radar, and Dual-LiDAR","created":"2026-04-04","cited_by_count":3,"area":null},{"id":"2507.03386","title":"MRC-DETR: An Adaptive Multi-Residual Coupled Transformer for Bare Board PCB Defect Detection","created":"2025-07-04","cited_by_count":2,"area":null},{"id":"2601.09247","title":"Integrating Diverse Assignment Strategies into DETRs","created":"2026-01-14","cited_by_count":2,"area":null},{"id":"2602.07827","title":"Open-Text Aerial Detection: A Unified Framework For Aerial Visual Grounding And Detection","created":"2026-02-08","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":"2603.28182","title":"A Closer Look at Cross-Domain Few-Shot Object Detection: Fine-Tuning Matters and Parallel Decoder Helps","created":"2026-03-30","cited_by_count":2,"area":null},{"id":"2605.21308","title":"Deformba: Vision State Space Model with Adaptive State Fusion","created":"2026-05-20","cited_by_count":2,"area":null},{"id":"2606.14841","title":"Multi-HMR 2: Multi-Person Camera-Centric Human Detection, Mesh Recovery and Tracking","created":"2026-06-12","cited_by_count":2,"area":null},{"id":"2506.13027","title":"DETRPose: Real-Time End-to-End Multi-Person Pose Estimation via Modified Transformer Decoder and Novel Denoising Keypoints","created":"2025-06-16","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":"2511.19889","title":"LiMT: A Multi-task Liver Image Benchmark Dataset","created":"2025-11-25","cited_by_count":1,"area":null},{"id":"2512.12281","title":"Cognitive-YOLO: LLM-Driven Architecture Synthesis from First Principles of Data for Object Detection","created":"2025-12-13","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":"2602.21141","title":"SynthRender and I-AsSET: Open-Source Framework and Dataset for Bidirectional Sim-Real Transfer in Industrial Object Perception","created":"2026-02-24","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":"2604.07759","title":"WUTDet: A 100K-Scale Ship Detection Dataset and Benchmarks with Dense Small Objects","created":"2026-04-09","cited_by_count":1,"area":null},{"id":"2606.09367","title":"RT-SDGOD: Real-Time Single-Domain Generalized Object Detection","created":"2026-06-08","cited_by_count":1,"area":null},{"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":"2503.14228","title":"Panoramic Distortion-Aware Tokenization for Person Detection and Localization in Overhead Fisheye Images","created":"2025-03-18","cited_by_count":0,"area":null},{"id":"2505.12007","title":"Multi-modal Collaborative Optimization and Expansion Network for Event-assisted Single-eye Expression Recognition","created":"2025-05-17","cited_by_count":0,"area":"moe"},{"id":"2509.17931","title":"Multi-needle Localization for Pelvic Seed Implant Brachytherapy based on Tip-handle Detection and Matching","created":"2025-09-22","cited_by_count":0,"area":null},{"id":"2509.22365","title":"HierLight-YOLO: A Hierarchical and Lightweight Object Detection Network for UAV Photography","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2509.23056","title":"FMC-DETR: Frequency-Decoupled Multi-Domain Coordination for Aerial-View Object Detection","created":"2025-09-27","cited_by_count":0,"area":null},{"id":"2511.19134","title":"MambaRefine-YOLO: A Dual-Modality Small Object Detector for UAV Imagery","created":"2025-11-24","cited_by_count":0,"area":null},{"id":"2512.13834","title":"VajraV1 -- The most accurate Real Time Object Detector of the YOLO family","created":"2025-12-15","cited_by_count":0,"area":null},{"id":"2601.02212","title":"Prior-Guided DETR for Ultrasound Nodule Detection","created":"2026-01-05","cited_by_count":0,"area":null},{"id":"2602.01754","title":"Spot-Wise Smart Parking: An Edge-Enabled Architecture with YOLOv11 and Digital Twin Integration","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2602.01843","title":"SPIRIT: Adapting Vision Foundation Models for Unified Single- and Multi-Frame Infrared Small Target Detection","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2602.02850","title":"Self-Supervised Uncalibrated Multi-View Video Anonymization in the Operating Room","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2603.01524","title":"Better Matching, Less Forgetting: A Quality-Guided Matcher for Transformer-based Incremental Object Detection","created":"2026-03-02","cited_by_count":0,"area":null},{"id":"2603.02924","title":"HDINO: A Concise and Efficient Open-Vocabulary Detector","created":"2026-03-03","cited_by_count":0,"area":null},{"id":"2604.04127","title":"SARES-DEIM: Sparse Mixture-of-Experts Meets DETR for Robust SAR Ship Detection","created":"2026-04-05","cited_by_count":0,"area":null},{"id":"2605.04635","title":"UniPCB: A Generation-Assisted Vision-Based Measurement Framework for PCB Defect Inspection","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2605.10229","title":"VPD-100K: Towards Generalizable and Fine-grained Visual Privacy Protection","created":"2026-05-11","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":"2605.27893","title":"SIGMA: Bridging Structural and Distributional Gaps for Vision Foundation Model Adaptation","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.01173","title":"Bridging Multimodal Fusion and Expert Routing via Spectral Reliability Descriptors for Robust Object Detection","created":"2026-05-31","cited_by_count":0,"area":"moe"},{"id":"2606.04282","title":"FindIt: A Format-Informed Visual Detection Benchmark for Generalist Multimodal LLMs","created":"2026-06-02","cited_by_count":0,"area":"mllm"},{"id":"2606.11546","title":"VL-DINO: Leveraging CLIP Vision-Language Knowledge for Open-Vocabulary Object Detectio","created":"2026-06-10","cited_by_count":0,"area":"mllm"},{"id":"2606.14005","title":"Context-Guided Semantic Alignment for Feature Fusion Networks","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2606.22702","title":"Modular Diffusion Models for Structured Visual Recognition","created":"2026-06-21","cited_by_count":0,"area":"diffusion"},{"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":"2608.02495","title":"DyFrDet: Towards Accurate Small Object Detection via Dynamic Frequency Suppression with Label Disambiguation","created":"2026-08-03","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":"2608.16632","title":"DRAFE: Domain-Robust Asymmetric Fusion of Heterogeneous Detection Transformers for Cross-City Fine-Grained Traffic Object Detection","created":"2026-08-17","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":"2608.30709","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":"2608.30727","title":"RailGen: Improving Railway Intrusion Detection via Agent-Guided Small-Scale Foreign Object Generation","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.02212","title":"FuDU: A Fuzzy Dual-dimensional Uncertainty Framework for Streaming Active Learning in Industrial Defect Detection","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.06581","title":"Reading Decoder Trajectories: Training-Free Counterfactual Query-Trajectory Reliability for Small-Object Detection","created":"2026-09-06","cited_by_count":0,"area":null},{"id":"2609.13647","title":"YOLO12-MambaScan: An Efficient Object Detector with High-Frequency Enhancement and State-Space Modeling","created":"2026-09-12","cited_by_count":0,"area":null},{"id":"2609.14383","title":"Contour-Guided Spectral Routing for Robust Real-Time Pedestrian Detection","created":"2026-09-13","cited_by_count":0,"area":null},{"id":"2609.19964","title":"Enhanced Knowledge Distillation for Detection Transformer via Teacher Prediction Refinement","created":"2026-09-17","cited_by_count":0,"area":"distill"},{"id":"2609.26590","title":"GTR: Gated Token Recurrence for Efficient Dense Prediction","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.29813","title":"S2Planner: Multi-Scale Semantic Planner for End-to-End Autonomous Driving","created":"2026-09-24","cited_by_count":0,"area":"driving"},{"id":"2609.36894","title":"DiffReID: Discriminative Diffusion Model for Object Re-Identification","created":"2026-09-29","cited_by_count":0,"area":"diffusion"},{"id":"2609.39467","title":"DensePed-Lite: Quality-Aware Adaptive Detection for Dense Pedestrians under Occlusion","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.00067","title":"Robust Online Aero-Engine Blade Defect Detection via Dual-Alignment Test-Time Adaptation","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2610.05191","title":"Order Matters: Competition-Guided Query Ordering for RNN-Based Object Detection","created":"2026-10-04","cited_by_count":0,"area":null}],"next_cursor":null}