{"total":181,"rows":[{"id":"2405.14458","title":"YOLOv10: Real-Time End-to-End Object Detection","created":"2024-05-23","cited_by_count":515,"area":null},{"id":"2402.13616","title":"YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information","created":"2024-02-21","cited_by_count":425,"area":null},{"id":"2303.07399","title":"RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose","created":"2023-03-13","cited_by_count":175,"area":null},{"id":"2303.09030","title":"Large Selective Kernel Network for Remote Sensing Object Detection","created":"2023-03-16","cited_by_count":98,"area":null},{"id":"2412.04234","title":"DEIM: DETR with Improved Matching for Fast Convergence","created":"2024-12-05","cited_by_count":68,"area":null},{"id":"2403.13430","title":"MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining","created":"2024-03-20","cited_by_count":66,"area":null},{"id":"2403.06258","title":"Poly Kernel Inception Network for Remote Sensing Detection","created":"2024-03-10","cited_by_count":52,"area":null},{"id":"2403.11735","title":"LSKNet: A Foundation Lightweight Backbone for Remote Sensing","created":"2024-03-18","cited_by_count":44,"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":"2312.07526","title":"RTMO: Towards High-Performance One-Stage Real-Time Multi-Person Pose Estimation","created":"2023-12-12","cited_by_count":34,"area":null},{"id":"2308.05480","title":"YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-time Object Detection","created":"2023-08-10","cited_by_count":33,"area":null},{"id":"2408.04804","title":"Hyper-YOLO: When Visual Object Detection Meets Hypergraph Computation","created":"2024-08-09","cited_by_count":29,"area":null},{"id":"2311.14758","title":"Point2RBox: Combine Knowledge from Synthetic Visual Patterns for End-to-end Oriented Object Detection with Single Point Supervision","created":"2023-11-23","cited_by_count":21,"area":null},{"id":"2407.08634","title":"RTMW: Real-Time Multi-Person 2D and 3D Whole-body Pose Estimation","created":"2024-07-11","cited_by_count":19,"area":null},{"id":"2406.16039","title":"CholecInstanceSeg: A Tool Instance Segmentation Dataset for Laparoscopic Surgery","created":"2024-06-23","cited_by_count":16,"area":null},{"id":"2407.16424","title":"ESOD: Efficient Small Object Detection on High-Resolution Images","created":"2024-07-23","cited_by_count":15,"area":null},{"id":"2409.19833","title":"HazyDet: Open-Source Benchmark for Drone-View Object Detection with Depth-Cues in Hazy Scenes","created":"2024-09-30","cited_by_count":15,"area":null},{"id":"2306.01242","title":"Responsible Task Automation: Empowering Large Language Models as Responsible Task Automators","created":"2023-06-02","cited_by_count":14,"area":null},{"id":"2501.03775","title":"Strip R-CNN: Large Strip Convolution for Remote Sensing Object Detection","created":"2025-01-07","cited_by_count":14,"area":null},{"id":"2403.11127","title":"GRA: Detecting Oriented Objects through Group-wise Rotating and Attention","created":"2024-03-17","cited_by_count":13,"area":null},{"id":"2308.10561","title":"Spatial Transform Decoupling for Oriented Object Detection","created":"2023-08-21","cited_by_count":12,"area":null},{"id":"2407.01016","title":"SOOD++: Leveraging Unlabeled Data to Boost Oriented Object Detection","created":"2024-07-01","cited_by_count":12,"area":null},{"id":"2503.10078","title":"Image Quality Assessment: From Human to Machine Preference","created":"2025-03-13","cited_by_count":12,"area":null},{"id":"2501.16751","title":"HiBug2: Efficient and Interpretable Error Slice Discovery for Comprehensive Model Debugging","created":"2025-01-28","cited_by_count":11,"area":null},{"id":"2312.07006","title":"Mixed Pseudo Labels for Semi-Supervised Object Detection","created":"2023-12-12","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":"2305.07598","title":"Hausdorff Distance Matching with Adaptive Query Denoising for Rotated Detection Transformer","created":"2023-05-12","cited_by_count":9,"area":null},{"id":"2405.09883","title":"RoScenes: A Large-scale Multi-view 3D Dataset for Roadside Perception","created":"2024-05-16","cited_by_count":9,"area":null},{"id":"2407.20078","title":"Background Semantics Matter: Cross-Task Feature Exchange Network for Clustered Infrared Small Target Detection","created":"2024-07-29","cited_by_count":9,"area":null},{"id":"2501.05783","title":"UV-Attack: Physical-World Adversarial Attacks for Person Detection via Dynamic-NeRF-based UV Mapping","created":"2025-01-10","cited_by_count":9,"area":null},{"id":"2503.06146","title":"OpenRSD: Towards Open-prompts for Object Detection in Remote Sensing Images","created":"2025-03-08","cited_by_count":9,"area":null},{"id":"2507.16559","title":"Comparative validation of surgical phase recognition, instrument keypoint estimation, and instrument instance segmentation in endoscopy: Results of the PhaKIR 2024 challenge","created":"2025-07-22","cited_by_count":8,"area":null},{"id":"2403.05125","title":"Evaluating Text-to-Image Generative Models: An Empirical Study on Human Image Synthesis","created":"2024-03-08","cited_by_count":7,"area":null},{"id":"2503.06261","title":"Segment Anything, Even Occluded","created":"2025-03-08","cited_by_count":7,"area":null},{"id":"2508.13401","title":"AIM 2025 Rip Current Segmentation (RipSeg) Challenge Report","created":"2025-08-18","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":"2409.06259","title":"ALSS-YOLO: An Adaptive Lightweight Channel Split and Shuffling Network for TIR Wildlife Detection in UAV Imagery","created":"2024-09-10","cited_by_count":6,"area":null},{"id":"2410.13567","title":"CCUP: A Controllable Synthetic Data Generation Pipeline for Pretraining Cloth-Changing Person Re-Identification Models","created":"2024-10-17","cited_by_count":6,"area":null},{"id":"2510.07249","title":"TalkCuts: A Large-Scale Dataset for Multi-Shot Human Speech Video Generation","created":"2025-10-08","cited_by_count":6,"area":null},{"id":"2307.13901","title":"YOLOBench: Benchmarking Efficient Object Detectors on Embedded Systems","created":"2023-07-26","cited_by_count":5,"area":null},{"id":"2309.04708","title":"UnitModule: A Lightweight Joint Image Enhancement Module for Underwater Object Detection","created":"2023-09-09","cited_by_count":5,"area":null},{"id":"2403.05055","title":"MUC: Mixture of Uncalibrated Cameras for Robust 3D Human Body Reconstruction","created":"2024-03-08","cited_by_count":5,"area":null},{"id":"2407.04381","title":"Multi-Branch Auxiliary Fusion YOLO with Re-parameterization Heterogeneous Convolutional for accurate object detection","created":"2024-07-05","cited_by_count":5,"area":null},{"id":"2407.17956","title":"SaccadeDet: A Novel Dual-Stage Architecture for Rapid and Accurate Detection in Gigapixel Images","created":"2024-07-25","cited_by_count":5,"area":null},{"id":"2410.11774","title":"Fractal Calibration for long-tailed object detection","created":"2024-10-15","cited_by_count":5,"area":null},{"id":"2412.01721","title":"BroadTrack: Broadcast Camera Tracking for Soccer","created":"2024-12-02","cited_by_count":5,"area":null},{"id":"2505.15581","title":"Advancing Marine Research: UWSAM Framework and UIIS10K Dataset for Precise Underwater Instance Segmentation","created":"2025-05-21","cited_by_count":5,"area":null},{"id":"2401.07322","title":"RSUD20K: A Dataset for Road Scene Understanding In Autonomous Driving","created":"2024-01-14","cited_by_count":4,"area":null},{"id":"2407.04711","title":"MetaFruit Meets Foundation Models: Leveraging a Comprehensive Multi-Fruit Dataset for Advancing Agricultural Foundation Models","created":"2024-05-14","cited_by_count":4,"area":null},{"id":"2407.20124","title":"AxiomVision: Accuracy-Guaranteed Adaptive Visual Model Selection for Perspective-Aware Video Analytics","created":"2024-07-29","cited_by_count":4,"area":null},{"id":"2409.03022","title":"Boundless: Generating Photorealistic Synthetic Data for Object Detection in Urban Streetscapes","created":"2024-09-04","cited_by_count":4,"area":null},{"id":"2411.18288","title":"Optimizing Multispectral Object Detection: A Bag of Tricks and Comprehensive Benchmarks","created":"2024-11-27","cited_by_count":4,"area":null},{"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":"2503.06522","title":"SGA-INTERACT: A 3D Skeleton-based Benchmark for Group Activity Understanding in Modern Basketball Tactic","created":"2025-03-09","cited_by_count":4,"area":null},{"id":"2505.17473","title":"InfoDet: A Dataset for Infographic Element Detection","created":"2025-05-23","cited_by_count":4,"area":null},{"id":"2507.09896","title":"Measuring the Impact of Rotation Equivariance on Aerial Object Detection","created":"2025-07-14","cited_by_count":4,"area":null},{"id":"2509.12965","title":"ICDAR 2025 Competition on FEw-Shot Text line segmentation of ancient handwritten documents (FEST)","created":"2025-09-16","cited_by_count":4,"area":null},{"id":"2301.05856","title":"EARL: An Elliptical Distribution aided Adaptive Rotation Label Assignment for Oriented Object Detection in Remote Sensing Images","created":"2023-01-14","cited_by_count":3,"area":null},{"id":"2311.05410","title":"Linear Gaussian Bounding Box Representation and Ring-Shaped Rotated Convolution for Oriented Object Detection","created":"2023-11-09","cited_by_count":3,"area":null},{"id":"2403.03390","title":"Performance Evaluation of Semi-supervised Learning Frameworks for Multi-Class Weed Detection","created":"2024-03-06","cited_by_count":3,"area":null},{"id":"2406.02385","title":"Low-Rank Adaption on Transformer-based Oriented Object Detector for Satellite Onboard Processing of Remote Sensing Images","created":"2024-06-04","cited_by_count":3,"area":null},{"id":"2410.09885","title":"Occluded Human Pose Estimation based on Limb Joint Augmentation","created":"2024-10-13","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":"2310.04749","title":"ConvNeXtv2 Fusion with Mask R-CNN for Automatic Region Based Coronary Artery Stenosis Detection for Disease Diagnosis","created":"2023-10-07","cited_by_count":2,"area":null},{"id":"2312.03327","title":"Building Category Graphs Representation with Spatial and Temporal Attention for Visual Navigation","created":"2023-12-06","cited_by_count":2,"area":null},{"id":"2401.02606","title":"Exploiting Polarized Material Cues for Robust Car Detection","created":"2024-01-05","cited_by_count":2,"area":null},{"id":"2404.14344","title":"On-the-Fly Point Annotation for Fast Medical Video Labeling","created":"2024-04-22","cited_by_count":2,"area":null},{"id":"2404.16944","title":"Constellation Dataset: Benchmarking High-Altitude Object Detection for an Urban Intersection","created":"2024-04-25","cited_by_count":2,"area":null},{"id":"2408.04922","title":"UAV-Enhanced Combination to Application: Comprehensive Analysis and Benchmarking of a Human Detection Dataset for Disaster Scenarios","created":"2024-08-09","cited_by_count":2,"area":null},{"id":"2408.05124","title":"A Simulation Framework for Electromagnetic Signal Injection Attacks on Image Sensors","created":"2024-08-09","cited_by_count":2,"area":null},{"id":"2410.14612","title":"MultiOrg: A Multi-rater Organoid-detection Dataset","created":"2024-10-18","cited_by_count":2,"area":null},{"id":"2412.01562","title":"Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle","created":"2024-12-02","cited_by_count":2,"area":null},{"id":"2503.16426","title":"DynamicVis: Dynamic Visual Perception for Efficient Remote Sensing Foundation Models","created":"2025-03-20","cited_by_count":2,"area":null},{"id":"2506.03134","title":"Controllable Radar Simulation with Waveform Parameter Embedding","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2508.16239","title":"EM3M: An Electron Micrograph Dataset for Microstructural Segmentation and Generation","created":"2025-08-22","cited_by_count":2,"area":null},{"id":"2511.17045","title":"RacketVision: A Multiple Racket Sports Benchmark for Unified Ball and Racket Analysis","created":"2025-11-21","cited_by_count":2,"area":null},{"id":"2512.15542","title":"BLANKET: Anonymizing Faces in Infant Video Recordings","created":"2025-12-17","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":"2305.00223","title":"PathRTM: Real-time prediction of KI-67 and tumor-infiltrated lymphocytes","created":"2023-04-23","cited_by_count":1,"area":null},{"id":"2308.07717","title":"Real-time Automatic M-mode Echocardiography Measurement with Panel Attention from Local-to-Global Pixels","created":"2023-08-15","cited_by_count":1,"area":null},{"id":"2312.11231","title":"Global Feature Pyramid Network","created":"2023-12-18","cited_by_count":1,"area":null},{"id":"2405.16580","title":"A Study on Unsupervised Anomaly Detection and Defect Localization using Generative Model in Ultrasonic Non-Destructive Testing","created":"2024-05-26","cited_by_count":1,"area":null},{"id":"2406.12285","title":"DASSF: Dynamic-Attention Scale-Sequence Fusion for Aerial Object Detection","created":"2024-06-18","cited_by_count":1,"area":null},{"id":"2407.05575","title":"Towards Reflected Object Detection: A Benchmark","created":"2024-07-08","cited_by_count":1,"area":null},{"id":"2408.12048","title":"ISETHDR: A Physics-based Synthetic Radiance Dataset for High Dynamic Range Driving Scenes","created":"2024-08-22","cited_by_count":1,"area":null},{"id":"2409.07907","title":"From COCO to COCO-FP: A Deep Dive into Background False Positives for COCO Detectors","created":"2024-09-12","cited_by_count":1,"area":null},{"id":"2411.00485","title":"LAM-YOLO: Drones-based Small Object Detection on Lighting-Occlusion Attention Mechanism YOLO","created":"2024-11-01","cited_by_count":1,"area":null},{"id":"2412.03055","title":"Real-Time AIoT for AAV Antenna Interference Detection via Edge-Cloud Collaboration","created":"2024-12-04","cited_by_count":1,"area":null},{"id":"2412.03434","title":"BIMCaP: BIM-based AI-supported LiDAR-Camera Pose Refinement","created":"2024-12-04","cited_by_count":1,"area":null},{"id":"2412.10453","title":"Analysis of Object Detection Models for Tiny Object in Satellite Imagery: A Dataset-Centric Approach","created":"2024-12-12","cited_by_count":1,"area":null},{"id":"2501.02822","title":"RDD4D: 4D Attention-Guided Road Damage Detection And Classification","created":"2025-01-06","cited_by_count":1,"area":null},{"id":"2503.04308","title":"Shaken, Not Stirred: A Novel Dataset for Visual Understanding of Glasses in Human-Robot Bartending Tasks","created":"2025-03-06","cited_by_count":1,"area":null},{"id":"2503.13344","title":"STEP: Simultaneous Tracking and Estimation of Pose for Animals and Humans","created":"2025-03-17","cited_by_count":1,"area":null},{"id":"2505.20687","title":"VisAlgae 2023: A Dataset and Challenge for Algae Detection in Microscopy Images","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2506.19747","title":"Systematic Comparison of Projection Methods for Monocular 3D Human Pose Estimation on Fisheye Images","created":"2025-06-24","cited_by_count":1,"area":null},{"id":"2507.12396","title":"OD-VIRAT: A Large-Scale Benchmark for Object Detection in Realistic Surveillance Environments","created":"2025-07-16","cited_by_count":1,"area":null},{"id":"2508.20447","title":"MSMVD: Exploiting Multi-scale Image Features via Multi-scale BEV Features for Multi-view Pedestrian Detection","created":"2025-08-28","cited_by_count":1,"area":null},{"id":"2509.19990","title":"SDE-DET: A Precision Network for Shatian Pomelo Detection in Complex Orchard Environments","created":"2025-09-24","cited_by_count":1,"area":null},{"id":"2511.09022","title":"RadHARSimulator V2: Video to Doppler Generator","created":"2025-11-12","cited_by_count":1,"area":null},{"id":"2601.08982","title":"SAM-pose2seg: Pose-Guided Human Instance Segmentation in Crowds","created":"2026-01-13","cited_by_count":1,"area":null}],"next_cursor":"100"}