{"total":88,"rows":[{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139,"area":null},{"id":"2111.14791","title":"Self-Supervised Pre-Training of Swin Transformers for 3D Medical Image Analysis","created":"2021-11-29","cited_by_count":422,"area":null},{"id":"2112.06375","title":"Embracing Single Stride 3D Object Detector with Sparse Transformer","created":"2021-12-13","cited_by_count":193,"area":null},{"id":"2106.08322","title":"Dynamic Head: Unifying Object Detection Heads with Attentions","created":"2021-06-15","cited_by_count":187,"area":null},{"id":"2103.10039","title":"RangeDet:In Defense of Range View for LiDAR-based 3D Object Detection","created":"2021-03-18","cited_by_count":140,"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":"2103.09460","title":"You Only Look One-level Feature","created":"2021-03-17","cited_by_count":116,"area":null},{"id":"2103.09136","title":"QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detection","created":"2021-03-16","cited_by_count":70,"area":null},{"id":"2103.17115","title":"Dense Relation Distillation with Context-aware Aggregation for Few-Shot Object Detection","created":"2021-03-30","cited_by_count":53,"area":null},{"id":"2110.13389","title":"A Normalized Gaussian Wasserstein Distance for Tiny Object Detection","created":"2021-10-26","cited_by_count":53,"area":null},{"id":"2208.08738","title":"RFLA: Gaussian Receptive Field based Label Assignment for Tiny Object Detection","created":"2022-08-18","cited_by_count":51,"area":null},{"id":"2304.08876","title":"Dynamic Coarse-to-Fine Learning for Oriented Tiny Object Detection","created":"2023-04-18","cited_by_count":43,"area":null},{"id":"2103.13516","title":"Tracking Pedestrian Heads in Dense Crowd","created":"2021-03-24","cited_by_count":42,"area":null},{"id":"2203.15187","title":"ASM-Loc: Action-aware Segment Modeling for Weakly-Supervised Temporal Action Localization","created":"2022-03-29","cited_by_count":40,"area":null},{"id":"2204.11582","title":"Graph-DETR3D: Rethinking Overlapping Regions for Multi-View 3D Object Detection","created":"2022-04-25","cited_by_count":35,"area":null},{"id":"2112.10415","title":"UFPMP-Det: Toward Accurate and Efficient Object Detection on Drone Imagery","created":"2021-12-20","cited_by_count":34,"area":null},{"id":"2208.03641","title":"No More Strided Convolutions or Pooling: A New CNN Building Block for Low-Resolution Images and Small Objects","created":"2022-08-07","cited_by_count":27,"area":null},{"id":"2109.06875","title":"Multi-Scale Aligned Distillation for Low-Resolution Detection","created":"2021-09-14","cited_by_count":24,"area":"distill"},{"id":"2103.17220","title":"Scale-aware Automatic Augmentation for Object Detection","created":"2021-03-31","cited_by_count":23,"area":null},{"id":"2301.02830","title":"Image Data Augmentation Approaches: A Comprehensive Survey and Future directions","created":"2023-01-07","cited_by_count":23,"area":null},{"id":"2304.12160","title":"End-to-End Spatio-Temporal Action Localisation with Video Transformers","created":"2023-04-24","cited_by_count":20,"area":null},{"id":"2202.04256","title":"GiraffeDet: A Heavy-Neck Paradigm for Object Detection","created":"2022-02-09","cited_by_count":17,"area":null},{"id":"2303.08747","title":"Cascaded Zoom-in Detector for High Resolution Aerial Images","created":"2023-03-15","cited_by_count":17,"area":null},{"id":"2203.12244","title":"Scale-Equivalent Distillation for Semi-Supervised Object Detection","created":"2022-03-23","cited_by_count":15,"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":"2201.04620","title":"SparseDet: Improving Sparsely Annotated Object Detection with Pseudo-positive Mining","created":"2022-01-12","cited_by_count":14,"area":null},{"id":"2410.11301","title":"Open World Object Detection: A Survey","created":"2024-10-15","cited_by_count":13,"area":null},{"id":"2112.11798","title":"YOLO-Z: Improving small object detection in YOLOv5 for autonomous vehicles","created":"2021-12-22","cited_by_count":12,"area":null},{"id":"2207.07889","title":"You Should Look at All Objects","created":"2022-07-16","cited_by_count":12,"area":null},{"id":"2406.10722","title":"GenMM: Geometrically and Temporally Consistent Multimodal Data Generation for Video and LiDAR","created":"2024-06-15","cited_by_count":12,"area":null},{"id":"2106.10409","title":"AdaZoom: Adaptive Zoom Network for Multi-Scale Object Detection in Large Scenes","created":"2021-06-19","cited_by_count":11,"area":null},{"id":"2112.08782","title":"Improved YOLOv5 network for real-time multi-scale traffic sign detection","created":"2021-12-16","cited_by_count":11,"area":null},{"id":"2404.06180","title":"YOLC: You Only Look Clusters for Tiny Object Detection in Aerial Images","created":"2024-04-09","cited_by_count":11,"area":null},{"id":"2111.00201","title":"A Comparative Review of Recent Few-Shot Object Detection Algorithms","created":"2021-10-30","cited_by_count":10,"area":null},{"id":"2208.11356","title":"Towards Efficient Use of Multi-Scale Features in Transformer-Based Object Detectors","created":"2022-08-24","cited_by_count":10,"area":null},{"id":"2108.10175","title":"Towards Balanced Learning for Instance Recognition","created":"2021-08-23","cited_by_count":9,"area":null},{"id":"2211.00945","title":"CarDD: A New Dataset for Vision-based Car Damage Detection","created":"2022-11-02","cited_by_count":9,"area":null},{"id":"2304.12406","title":"AutoFocusFormer: Image Segmentation off the Grid","created":"2023-04-24","cited_by_count":9,"area":null},{"id":"2203.14205","title":"Recent Few-Shot Object Detection Algorithms: A Survey with Performance Comparison","created":"2022-03-27","cited_by_count":8,"area":null},{"id":"2302.10473","title":"Oriented object detection in optical remote sensing images using deep learning: a survey","created":"2023-02-21","cited_by_count":8,"area":null},{"id":"2406.04330","title":"Parameter-Inverted Image Pyramid Networks","created":"2024-06-06","cited_by_count":8,"area":null},{"id":"2501.07783","title":"Parameter-Inverted Image Pyramid Networks for Visual Perception and Multimodal Understanding","created":"2025-01-14","cited_by_count":8,"area":null},{"id":"2104.14805","title":"Few-Shot Video Object Detection","created":"2021-04-30","cited_by_count":7,"area":null},{"id":"2105.12694","title":"Deep Learning for Weakly-Supervised Object Detection and Object Localization: A Survey","created":"2021-05-26","cited_by_count":6,"area":null},{"id":"2208.03062","title":"Exploring Resolution and Degradation Clues as Self-supervised Signal for Low Quality Object Detection","created":"2022-08-05","cited_by_count":6,"area":null},{"id":"2102.05646","title":"Scale Normalized Image Pyramids with AutoFocus for Object Detection","created":"2021-02-10","cited_by_count":5,"area":null},{"id":"2208.11975","title":"Bottom-Up 2D Pose Estimation via Dual Anatomical Centers for Small-Scale Persons","created":"2022-08-25","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":"2305.03716","title":"3D Small Object Detection with Dynamic Spatial Pruning","created":"2023-05-05","cited_by_count":4,"area":null},{"id":"2401.08056","title":"Robust Tiny Object Detection in Aerial Images amidst Label Noise","created":"2024-01-16","cited_by_count":4,"area":null},{"id":"2404.13311","title":"STAT: Towards Generalizable Temporal Action Localization","created":"2024-04-20","cited_by_count":4,"area":null},{"id":"2510.18229","title":"Unbiased Object Detection Beyond Frequency with Visually Prompted Image Synthesis","created":"2025-10-21","cited_by_count":4,"area":null},{"id":"2104.05031","title":"Deformable Capsules for Object Detection","created":"2021-04-11","cited_by_count":3,"area":null},{"id":"2104.14082","title":"Pseudo-IoU: Improving Label Assignment in Anchor-Free Object Detection","created":"2021-04-29","cited_by_count":3,"area":null},{"id":"2107.07927","title":"A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets","created":"2021-07-16","cited_by_count":3,"area":null},{"id":"2303.11267","title":"Rethinking the backbone architecture for tiny object detection","created":"2023-03-20","cited_by_count":3,"area":null},{"id":"2306.05807","title":"A Gated Attention Transformer for Multi-Person Pose Tracking","created":"2023-06-09","cited_by_count":3,"area":null},{"id":"2307.09562","title":"Rethinking Intersection Over Union for Small Object Detection in Few-Shot Regime","created":"2023-07-17","cited_by_count":3,"area":null},{"id":"2311.05029","title":"S$^3$AD: Semi-supervised Small Apple Detection in Orchard Environments","created":"2023-11-08","cited_by_count":3,"area":null},{"id":"2405.18299","title":"Deep Learning Innovations for Underwater Waste Detection: An In-Depth Analysis","created":"2024-05-28","cited_by_count":3,"area":null},{"id":"2207.00837","title":"UTD-Yolov5: A Real-time Underwater Targets Detection Method based on Attention Improved YOLOv5","created":"2022-07-02","cited_by_count":2,"area":null},{"id":"2405.06260","title":"Precise Apple Detection and Localization in Orchards using YOLOv5 for Robotic Harvesting Systems","created":"2024-05-10","cited_by_count":2,"area":null},{"id":"2210.04574","title":"ARUBA: An Architecture-Agnostic Balanced Loss for Aerial Object Detection","created":"2022-10-10","cited_by_count":1,"area":null},{"id":"2212.07560","title":"Multi-level and multi-modal feature fusion for accurate 3D object detection in Connected and Automated Vehicles","created":"2022-12-15","cited_by_count":1,"area":null},{"id":"2303.01219","title":"A Coarse to Fine Framework for Object Detection in High Resolution Image","created":"2023-03-02","cited_by_count":1,"area":null},{"id":"2311.17098","title":"DyRA: Portable Dynamic Resolution Adjustment Network for Existing Detectors","created":"2023-11-28","cited_by_count":1,"area":null},{"id":"2408.07455","title":"Infra-YOLO: Efficient Neural Network Structure with Model Compression for Real-Time Infrared Small Object Detection","created":"2024-08-14","cited_by_count":1,"area":null},{"id":"2505.21868","title":"Cross-DINO: Cross the Deep MLP and Transformer for Small Object Detection","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2510.27649","title":"Gaussian Combined Distance: A Generic Metric for Object Detection","created":"2025-10-31","cited_by_count":1,"area":null},{"id":"2102.09796","title":"A GAN-Based Input-Size Flexibility Model for Single Image Dehazing","created":"2021-02-19","cited_by_count":0,"area":null},{"id":"2110.13892","title":"HR-RCNN: Hierarchical Relational Reasoning for Object Detection","created":"2021-10-26","cited_by_count":0,"area":null},{"id":"2205.13272","title":"FCN-Pose: A Pruned and Quantized CNN for Robot Pose Estimation for Constrained Devices","created":"2022-05-26","cited_by_count":0,"area":null},{"id":"2303.16637","title":"MuRAL: Multi-Scale Region-based Active Learning for Object Detection","created":"2023-03-29","cited_by_count":0,"area":null},{"id":"2306.16201","title":"Low-Confidence Samples Mining for Semi-supervised Object Detection","created":"2023-06-28","cited_by_count":0,"area":null},{"id":"2308.05032","title":"Density Crop-guided Semi-supervised Object Detection in Aerial Images","created":"2023-08-09","cited_by_count":0,"area":null},{"id":"2312.16943","title":"Multi-scale direction-aware SAR object detection network via global information fusion","created":"2023-12-28","cited_by_count":0,"area":null},{"id":"2406.19394","title":"HUWSOD: Holistic Self-training for Unified Weakly Supervised Object Detection","created":"2024-06-27","cited_by_count":0,"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":"2505.02797","title":"DPNet: Dynamic Pooling Network for Tiny Object Detection","created":"2025-05-05","cited_by_count":0,"area":null},{"id":"2506.09897","title":"CEM-FBGTinyDet: Context-Enhanced Foreground Balance with Gradient Tuning for tiny Objects","created":"2025-06-11","cited_by_count":0,"area":null},{"id":"2509.17182","title":"PMRT: A Training Recipe for Fast, 3D High-Resolution Aerodynamic Prediction","created":"2025-09-21","cited_by_count":0,"area":null},{"id":"2512.11727","title":"ECCO: Leveraging Cross-Camera Correlations for Efficient Live Video Continuous Learning","created":"2025-12-12","cited_by_count":0,"area":null},{"id":"2601.05747","title":"FlyPose: Towards Robust Human Pose Estimation From Aerial Views","created":"2026-01-09","cited_by_count":0,"area":null},{"id":"2604.26806","title":"ViCrop-Det: Spatial Attention Entropy Guided Cropping for Training-Free Small-Object Detection","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2606.01822","title":"Hierarchically Decoupled Mixture-of-Experts for Robust Traffic Sign Recognition in Complex Driving Scenarios","created":"2026-06-01","cited_by_count":0,"area":"moe"},{"id":"2608.28706","title":"Variable-Granularity Tokenization for High-Resolution Object Detection","created":"2026-08-27","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":"2610.04346","title":"Any-scale Object Detection using Arbitrary-scaled Images","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}