{"total":120,"rows":[{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139,"area":null},{"id":"2102.12219","title":"Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges","created":"2021-02-24","cited_by_count":204,"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":"2212.00968","title":"UIU-Net: U-Net in U-Net for Infrared Small Object Detection","created":"2022-12-02","cited_by_count":127,"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":"2106.02637","title":"Aligning Pretraining for Detection via Object-Level Contrastive Learning","created":"2021-06-04","cited_by_count":110,"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":"2103.06122","title":"Spatially Consistent Representation Learning","created":"2021-03-10","cited_by_count":64,"area":null},{"id":"2112.10809","title":"Lite Vision Transformer with Enhanced Self-Attention","created":"2021-12-20","cited_by_count":64,"area":null},{"id":"2206.13996","title":"Detecting tiny objects in aerial images: A normalized Wasserstein distance and a new benchmark","created":"2022-06-28","cited_by_count":56,"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":"2401.15855","title":"Cross-Scale MAE: A Tale of Multi-Scale Exploitation in Remote Sensing","created":"2024-01-29","cited_by_count":47,"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":"2212.00776","title":"ResFormer: Scaling ViTs with Multi-Resolution Training","created":"2022-12-01","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":"2110.00249","title":"Synergizing between Self-Training and Adversarial Learning for Domain Adaptive Object Detection","created":"2021-10-01","cited_by_count":24,"area":null},{"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":"2108.13576","title":"Dead Pixel Test Using Effective Receptive Field","created":"2021-08-31","cited_by_count":18,"area":null},{"id":"2106.06418","title":"Scale-invariant scale-channel networks: Deep networks that generalise to previously unseen scales","created":"2021-06-11","cited_by_count":17,"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":"2110.12093","title":"Circle Representation for Medical Object Detection","created":"2021-10-22","cited_by_count":15,"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":"2207.11493","title":"Active Pointly-Supervised Instance Segmentation","created":"2022-07-23","cited_by_count":15,"area":null},{"id":"2208.02019","title":"YOLO-FaceV2: A Scale and Occlusion Aware Face Detector","created":"2022-08-03","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":"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":"2109.14379","title":"Infrared Small-Dim Target Detection with Transformer under Complex Backgrounds","created":"2021-09-29","cited_by_count":12,"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":"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":"2103.11139","title":"MogFace: Towards a Deeper Appreciation on Face Detection","created":"2021-03-20","cited_by_count":10,"area":null},{"id":"2103.14027","title":"USB: Universal-Scale Object Detection Benchmark","created":"2021-03-25","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":"2111.09204","title":"Tiny Obstacle Discovery by Occlusion-Aware Multilayer Regression","created":"2021-11-17","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":"2405.11276","title":"Visible and Clear: Finding Tiny Objects in Difference Map","created":"2024-05-18","cited_by_count":9,"area":null},{"id":"2101.12694","title":"Gaining Scale Invariance in UAV Bird's Eye View Object Detection by Adaptive Resizing","created":"2021-01-29","cited_by_count":8,"area":null},{"id":"2103.10643","title":"CE-FPN: Enhancing Channel Information for Object Detection","created":"2021-03-19","cited_by_count":8,"area":null},{"id":"2207.03807","title":"Beyond Transfer Learning: Co-finetuning for Action Localisation","created":"2022-07-08","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":"2410.05577","title":"Underwater Object Detection in the Era of Artificial Intelligence: Current, Challenge, and Future","created":"2024-10-08","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":"2203.03195","title":"Unpaired Image Captioning by Image-level Weakly-Supervised Visual Concept Recognition","created":"2022-03-07","cited_by_count":7,"area":null},{"id":"2207.06673","title":"Detecting Volunteer Cotton Plants in a Corn Field with Deep Learning on UAV Remote-Sensing Imagery","created":"2022-07-14","cited_by_count":7,"area":null},{"id":"2403.12712","title":"Instance-Warp: Saliency Guided Image Warping for Unsupervised Domain Adaptation","created":"2024-03-19","cited_by_count":7,"area":null},{"id":"2410.01539","title":"Multi-Scale Fusion for Object Representation","created":"2024-10-02","cited_by_count":7,"area":null},{"id":"2502.07216","title":"SparseFormer: Detecting Objects in HRW Shots via Sparse Vision Transformer","created":"2025-02-11","cited_by_count":7,"area":null},{"id":"2103.05137","title":"Contemplating real-world object classification","created":"2021-03-08","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":"2311.04815","title":"Domain Adaptive Object Detection via Balancing Between Self-Training and Adversarial Learning","created":"2023-11-08","cited_by_count":6,"area":null},{"id":"2405.18240","title":"MSPE: Multi-Scale Patch Embedding Prompts Vision Transformers to Any Resolution","created":"2024-05-28","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":"2104.13876","title":"PDNet: Toward Better One-Stage Object Detection With Prediction Decoupling","created":"2021-04-28","cited_by_count":5,"area":null},{"id":"2112.04709","title":"Implicit Feature Refinement for Instance Segmentation","created":"2021-12-09","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":"2212.09408","title":"Universal Object Detection with Large Vision Model","created":"2022-12-19","cited_by_count":5,"area":null},{"id":"2401.15885","title":"Rectify the Regression Bias in Long-Tailed Object Detection","created":"2024-01-29","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":"2505.12820","title":"Rethinking Features-Fused-Pyramid-Neck for Object Detection","created":"2025-05-19","cited_by_count":5,"area":null},{"id":"2207.05290","title":"Trusted Multi-Scale Classification Framework for Whole Slide Image","created":"2022-07-12","cited_by_count":4,"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":"2103.09488","title":"Revisiting the Loss Weight Adjustment in Object Detection","created":"2021-03-17","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":"2210.02808","title":"Effective Self-supervised Pre-training on Low-compute Networks without Distillation","created":"2022-10-06","cited_by_count":3,"area":null},{"id":"2303.01047","title":"Task-Specific Context Decoupling for Object Detection","created":"2023-03-02","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":"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":"2303.01803","title":"Uncertainty-Aware Gradient Stabilization for Small Object Detection","created":"2023-03-03","cited_by_count":2,"area":null},{"id":"2311.16346","title":"Small and Dim Target Detection in IR Imagery: A Review","created":"2023-11-27","cited_by_count":2,"area":null},{"id":"2409.14090","title":"Window-based Channel Attention for Wavelet-enhanced Learned Image Compression","created":"2024-09-21","cited_by_count":2,"area":null},{"id":"2109.05021","title":"A Deep Learning-Based Unified Framework for Red Lesions Detection on Retinal Fundus Images","created":"2021-09-10","cited_by_count":1,"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":"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":"2304.06925","title":"YOLO-Drone:Airborne real-time detection of dense small objects from high-altitude perspective","created":"2023-04-14","cited_by_count":1,"area":null},{"id":"2311.07955","title":"Deep Learning-Based Object Detection in Maritime Unmanned Aerial Vehicle Imagery: Review and Experimental Comparisons","created":"2023-11-14","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":"2411.16326","title":"Brain-like emergent properties in deep networks: impact of network architecture, datasets and training","created":"2024-11-25","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":"2102.12213","title":"Unsupervised semantic discovery through visual patterns detection","created":"2021-02-24","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":"2206.11473","title":"Complementary datasets to COCO for object detection","created":"2022-06-23","cited_by_count":0,"area":null}],"next_cursor":"100"}