{"total":218,"rows":[{"id":"2207.02696","title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","created":"2022-07-06","cited_by_count":982,"area":null},{"id":"2405.14458","title":"YOLOv10: Real-Time End-to-End Object Detection","created":"2024-05-23","cited_by_count":515,"area":null},{"id":"2401.17270","title":"YOLO-World: Real-Time Open-Vocabulary Object Detection","created":"2024-01-30","cited_by_count":503,"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":"2502.12524","title":"YOLOv12: Attention-Centric Real-Time Object Detectors","created":"2025-02-18","cited_by_count":305,"area":null},{"id":"2209.02976","title":"YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications","created":"2022-09-07","cited_by_count":275,"area":null},{"id":"2212.07784","title":"RTMDet: An Empirical Study of Designing Real-Time Object Detectors","created":"2022-12-14","cited_by_count":195,"area":null},{"id":"2304.00501","title":"A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS","created":"2023-04-02","cited_by_count":151,"area":null},{"id":"2203.16513","title":"PromptDet: Towards Open-vocabulary Detection using Uncurated Images","created":"2022-03-30","cited_by_count":133,"area":null},{"id":"2207.14096","title":"Towards Large-Scale Small Object Detection: Survey and Benchmarks","created":"2022-07-28","cited_by_count":122,"area":null},{"id":"2202.06934","title":"Slicing Aided Hyper Inference and Fine-tuning for Small Object Detection","created":"2022-02-14","cited_by_count":105,"area":null},{"id":"2203.08777","title":"Object discovery and representation networks","created":"2022-03-16","cited_by_count":80,"area":null},{"id":"2303.12776","title":"Dense Distinct Query for End-to-End Object Detection","created":"2023-03-22","cited_by_count":77,"area":null},{"id":"2203.16250","title":"PP-YOLOE: An evolved version of YOLO","created":"2022-03-30","cited_by_count":75,"area":null},{"id":"2203.10593","title":"Open-Vocabulary One-Stage Detection with Hierarchical Visual-Language Knowledge Distillation","created":"2022-03-20","cited_by_count":68,"area":"distill"},{"id":"2412.04234","title":"DEIM: DETR with Improved Matching for Fast Convergence","created":"2024-12-05","cited_by_count":68,"area":null},{"id":"2307.09220","title":"A Survey on Open-Vocabulary Detection and Segmentation: Past, Present, and Future","created":"2023-07-18","cited_by_count":61,"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":"2306.11369","title":"CrossKD: Cross-Head Knowledge Distillation for Object Detection","created":"2023-06-20","cited_by_count":52,"area":"distill"},{"id":"2310.08854","title":"Rank-DETR for High Quality Object Detection","created":"2023-10-13","cited_by_count":50,"area":null},{"id":"2207.07097","title":"ReAct: Temporal Action Detection with Relational Queries","created":"2022-07-14","cited_by_count":48,"area":null},{"id":"2304.04742","title":"Detection Transformer with Stable Matching","created":"2023-04-10","cited_by_count":44,"area":null},{"id":"2209.01589","title":"Consistent-Teacher: Towards Reducing Inconsistent Pseudo-targets in Semi-supervised Object Detection","created":"2022-09-04","cited_by_count":43,"area":null},{"id":"2207.02039","title":"PKD: General Distillation Framework for Object Detectors via Pearson Correlation Coefficient","created":"2022-07-05","cited_by_count":41,"area":"distill"},{"id":"2304.01198","title":"Open-Vocabulary Semantic Segmentation with Decoupled One-Pass Network","created":"2023-04-03","cited_by_count":40,"area":null},{"id":"2211.15444","title":"DAMO-YOLO : A Report on Real-Time Object Detection Design","created":"2022-11-23","cited_by_count":38,"area":null},{"id":"2503.07465","title":"YOLOE: Real-Time Seeing Anything","created":"2025-03-10","cited_by_count":36,"area":null},{"id":"2403.16131","title":"Salience DETR: Enhancing Detection Transformer with Hierarchical Salience Filtering Refinement","created":"2024-03-24","cited_by_count":31,"area":null},{"id":"2406.09410","title":"STAR: A First-Ever Dataset and A Large-Scale Benchmark for Scene Graph Generation in Large-Size Satellite Imagery","created":"2024-06-13","cited_by_count":31,"area":null},{"id":"2211.05638","title":"Untargeted Backdoor Attack against Object Detection","created":"2022-11-02","cited_by_count":28,"area":null},{"id":"2305.15701","title":"Action Sensitivity Learning for Temporal Action Localization","created":"2023-05-25","cited_by_count":28,"area":null},{"id":"2407.11699","title":"Relation DETR: Exploring Explicit Position Relation Prior for Object Detection","created":"2024-07-16","cited_by_count":28,"area":null},{"id":"2307.08095","title":"Semi-DETR: Semi-Supervised Object Detection with Detection Transformers","created":"2023-07-16","cited_by_count":27,"area":null},{"id":"2406.14482","title":"Visible-Thermal Tiny Object Detection: A Benchmark Dataset and Baselines","created":"2024-06-20","cited_by_count":27,"area":null},{"id":"2203.09730","title":"A Dual Weighting Label Assignment Scheme for Object Detection","created":"2022-03-18","cited_by_count":26,"area":null},{"id":"2402.05937","title":"InstaGen: Enhancing Object Detection by Training on Synthetic Dataset","created":"2024-02-08","cited_by_count":26,"area":"diffusion"},{"id":"2403.05346","title":"VLM-PL: Advanced Pseudo Labeling Approach for Class Incremental Object Detection via Vision-Language Model","created":"2024-03-08","cited_by_count":23,"area":"mllm"},{"id":"2207.07609","title":"DOLPHINS: Dataset for Collaborative Perception enabled Harmonious and Interconnected Self-driving","created":"2022-07-15","cited_by_count":21,"area":null},{"id":"2210.06433","title":"Self-supervised video pretraining yields robust and more human-aligned visual representations","created":"2022-10-12","cited_by_count":20,"area":null},{"id":"2211.12501","title":"AeDet: Azimuth-invariant Multi-view 3D Object Detection","created":"2022-11-22","cited_by_count":19,"area":null},{"id":"2212.07593","title":"Enhanced Training of Query-Based Object Detection via Selective Query Recollection","created":"2022-12-15","cited_by_count":18,"area":null},{"id":"2211.10763","title":"PIDray: A Large-scale X-ray Benchmark for Real-World Prohibited Item Detection","created":"2022-11-19","cited_by_count":17,"area":null},{"id":"2303.13518","title":"Three ways to improve feature alignment for open vocabulary detection","created":"2023-03-23","cited_by_count":17,"area":null},{"id":"2312.02481","title":"Learning to Holistically Detect Bridges from Large-Size VHR Remote Sensing Imagery","created":"2023-12-05","cited_by_count":17,"area":null},{"id":"2412.16955","title":"NumbOD: A Spatial-Frequency Fusion Attack Against Object Detectors","created":"2024-12-22","cited_by_count":17,"area":null},{"id":"2211.13508","title":"1st Workshop on Maritime Computer Vision (MaCVi) 2023: Challenge Results","created":"2022-11-24","cited_by_count":15,"area":null},{"id":"2311.01619","title":"InsPLAD: A Dataset and Benchmark for Power Line Asset Inspection in UAV Images","created":"2023-11-02","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":"2303.14960","title":"Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detection","created":"2023-03-27","cited_by_count":14,"area":null},{"id":"2303.09061","title":"MixTeacher: Mining Promising Labels with Mixed Scale Teacher for Semi-Supervised Object Detection","created":"2023-03-16","cited_by_count":13,"area":null},{"id":"2304.05071","title":"Fracture Detection in Pediatric Wrist Trauma X-ray Images Using YOLOv8 Algorithm","created":"2023-04-11","cited_by_count":12,"area":null},{"id":"2310.14154","title":"Affine-Consistent Transformer for Multi-Class Cell Nuclei Detection","created":"2023-10-22","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":"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":"2306.08370","title":"Object Detection in Hyperspectral Image via Unified Spectral-Spatial Feature Aggregation","created":"2023-06-14","cited_by_count":10,"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":"2209.08716","title":"GLARE: A Dataset for Traffic Sign Detection in Sun Glare","created":"2022-09-19","cited_by_count":9,"area":null},{"id":"2309.13242","title":"UniHead: Unifying Multi-Perception for Detection Heads","created":"2023-09-23","cited_by_count":9,"area":null},{"id":"2311.18814","title":"Is Underwater Image Enhancement All Object Detectors Need?","created":"2023-11-30","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":"2408.00350","title":"A Simple Background Augmentation Method for Object Detection with Diffusion Model","created":"2024-08-01","cited_by_count":9,"area":"diffusion"},{"id":"2410.18398","title":"You Only Look Around: Learning Illumination Invariant Feature for Low-light Object Detection","created":"2024-10-24","cited_by_count":9,"area":null},{"id":"2203.07973","title":"MOBDrone: a Drone Video Dataset for Man OverBoard Rescue","created":"2022-03-15","cited_by_count":8,"area":null},{"id":"2303.11567","title":"One-to-Few Label Assignment for End-to-End Dense Detection","created":"2023-03-21","cited_by_count":8,"area":null},{"id":"2310.15955","title":"Decoupled DETR: Spatially Disentangling Localization and Classification for Improved End-to-End Object Detection","created":"2023-10-24","cited_by_count":8,"area":null},{"id":"2406.02833","title":"DenoDet: Attention as Deformable Multi-Subspace Feature Denoising for Target Detection in SAR Images","created":"2024-06-05","cited_by_count":8,"area":null},{"id":"2211.08248","title":"3D Cascade RCNN: High Quality Object Detection in Point Clouds","created":"2022-11-15","cited_by_count":7,"area":null},{"id":"2302.13519","title":"CBA: Contextual Background Attack against Optical Aerial Detection in the Physical World","created":"2023-02-27","cited_by_count":7,"area":null},{"id":"2306.03400","title":"G-CAME: Gaussian-Class Activation Mapping Explainer for Object Detectors","created":"2023-06-06","cited_by_count":7,"area":null},{"id":"2402.00703","title":"Vehicle Perception from Satellite","created":"2024-02-01","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":"2412.00622","title":"Visual Modality Prompt for Adapting Vision-Language Object Detectors","created":"2024-12-01","cited_by_count":7,"area":null},{"id":"2502.01785","title":"AquaticCLIP: A Vision-Language Foundation Model for Underwater Scene Analysis","created":"2025-02-03","cited_by_count":7,"area":"mllm"},{"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":"2212.13136","title":"Fewer is More: Efficient Object Detection in Large Aerial Images","created":"2022-12-26","cited_by_count":6,"area":null},{"id":"2301.05124","title":"Poses of People in Art: A Data Set for Human Pose Estimation in Digital Art History","created":"2023-01-12","cited_by_count":6,"area":null},{"id":"2308.09242","title":"ASAG: Building Strong One-Decoder-Layer Sparse Detectors via Adaptive Sparse Anchor Generation","created":"2023-08-18","cited_by_count":6,"area":null},{"id":"2405.10148","title":"SpecDETR: A transformer-based hyperspectral point object detection network","created":"2024-05-16","cited_by_count":6,"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":"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":"2204.08745","title":"Augmentation of Atmospheric Turbulence Effects on Thermal Adapted Object Detection Models","created":"2022-04-19","cited_by_count":5,"area":null},{"id":"2206.06829","title":"Efficient Decoder-free Object Detection with Transformers","created":"2022-06-14","cited_by_count":5,"area":null},{"id":"2208.03006","title":"Task-Balanced Distillation for Object Detection","created":"2022-08-05","cited_by_count":5,"area":"distill"},{"id":"2211.02386","title":"PP-YOLOE-R: An Efficient Anchor-Free Rotated Object Detector","created":"2022-11-04","cited_by_count":5,"area":null},{"id":"2304.07527","title":"Align-DETR: Enhancing End-to-end Object Detection with Aligned Loss","created":"2023-04-15","cited_by_count":5,"area":null},{"id":"2306.12111","title":"A Comprehensive Study on the Robustness of Image Classification and Object Detection in Remote Sensing: Surveying and Benchmarking","created":"2023-06-21","cited_by_count":5,"area":null},{"id":"2308.00931","title":"WaterFlow: Heuristic Normalizing Flow for Underwater Image Enhancement and Beyond","created":"2023-08-02","cited_by_count":5,"area":null},{"id":"2308.11918","title":"AMSP-UOD: When Vortex Convolution and Stochastic Perturbation Meet Underwater Object Detection","created":"2023-08-23","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":"2406.05791","title":"OD-DETR: Online Distillation for Stabilizing Training of Detection Transformer","created":"2024-06-09","cited_by_count":5,"area":null},{"id":"2407.02394","title":"Similarity Distance-Based Label Assignment for Tiny Object Detection","created":"2024-07-02","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":"2503.17700","title":"MAMAT: 3D Mamba-Based Atmospheric Turbulence Removal and its Object Detection Capability","created":"2025-03-22","cited_by_count":5,"area":"ssm"},{"id":"2504.11999","title":"A Complex-valued SAR Foundation Model Based on Physically Inspired Representation Learning","created":"2025-04-16","cited_by_count":5,"area":null},{"id":"2206.01232","title":"What Are Expected Queries in End-to-End Object Detection?","created":"2022-06-02","cited_by_count":4,"area":null},{"id":"2210.14318","title":"Object recognition in atmospheric turbulence scenes","created":"2022-10-25","cited_by_count":4,"area":null},{"id":"2211.13859","title":"DATE: Dual Assignment for End-to-End Fully Convolutional Object Detection","created":"2022-11-25","cited_by_count":4,"area":null},{"id":"2301.01019","title":"Correlation Loss: Enforcing Correlation between Classification and Localization","created":"2023-01-03","cited_by_count":4,"area":null},{"id":"2308.14922","title":"Automated Conversion of Music Videos into Lyric Videos","created":"2023-08-28","cited_by_count":4,"area":null},{"id":"2312.10515","title":"PETDet: Proposal Enhancement for Two-Stage Fine-Grained Object Detection","created":"2023-12-16","cited_by_count":4,"area":null}],"next_cursor":"100"}