{"list":"other","total":65,"rows":[{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"2508.10104","title":"DINOv3","created":"2025-08-13","cited_by_count":1414},{"id":"2203.03605","title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","created":"2022-03-07","cited_by_count":1319},{"id":"2511.16719","title":"SAM 3: Segment Anything with Concepts","created":"2025-11-20","cited_by_count":906},{"id":"2012.07177","title":"Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation","created":"2020-12-13","cited_by_count":596},{"id":"2304.08069","title":"DETRs Beat YOLOs on Real-time Object Detection","created":"2023-04-17","cited_by_count":533},{"id":"2405.14458","title":"YOLOv10: Real-Time End-to-End Object Detection","created":"2024-05-23","cited_by_count":515},{"id":"2402.13616","title":"YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information","created":"2024-02-21","cited_by_count":425},{"id":"2410.17725","title":"YOLOv11: An Overview of the Key Architectural Enhancements","created":"2024-10-23","cited_by_count":425},{"id":"2108.06152","title":"Conditional DETR for Fast Training Convergence","created":"2021-08-13","cited_by_count":424},{"id":"1905.13545","title":"High Frequency Component Helps Explain the Generalization of Convolutional Neural Networks","created":"2019-05-28","cited_by_count":310},{"id":"2202.06709","title":"How Do Vision Transformers Work?","created":"2022-02-14","cited_by_count":307},{"id":"2502.12524","title":"YOLOv12: Attention-Centric Real-Time Object Detectors","created":"2025-02-18","cited_by_count":305},{"id":"1906.08988","title":"A Fourier Perspective on Model Robustness in Computer Vision","created":"2019-06-21","cited_by_count":288},{"id":"2105.07581","title":"Vision Transformers are Robust Learners","created":"2021-05-17","cited_by_count":207},{"id":"2012.11879","title":"FcaNet: Frequency Channel Attention Networks","created":"2020-12-22","cited_by_count":179},{"id":"2203.05962","title":"Anti-Oversmoothing in Deep Vision Transformers via the Fourier Domain Analysis: From Theory to Practice","created":"2022-03-09","cited_by_count":136},{"id":"2303.09030","title":"Large Selective Kernel Network for Remote Sensing Object Detection","created":"2023-03-16","cited_by_count":98},{"id":"2407.17140","title":"RT-DETRv2: Improved Baseline with Bag-of-Freebies for Real-Time Detection Transformer","created":"2024-07-24","cited_by_count":91},{"id":"2509.25164","title":"YOLO26: Key Architectural Enhancements and Performance Benchmarking for Real-Time Object Detection","created":"2025-09-29","cited_by_count":79},{"id":"2511.09554","title":"RF-DETR: Neural Architecture Search for Real-Time Detection Transformers","created":"2025-11-12","cited_by_count":75},{"id":"2410.13842","title":"D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinement","created":"2024-10-17","cited_by_count":74},{"id":"2103.09136","title":"QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detection","created":"2021-03-16","cited_by_count":70},{"id":"2412.04234","title":"DEIM: DETR with Improved Matching for Fast Convergence","created":"2024-12-05","cited_by_count":68},{"id":"2506.17733","title":"YOLOv13: Real-Time Object Detection with Hypergraph-Enhanced Adaptive Visual Perception","created":"2025-06-21","cited_by_count":58},{"id":"2101.08158","title":"Focal and Efficient IOU Loss for Accurate Bounding Box Regression","created":"2021-01-20","cited_by_count":57},{"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},{"id":"2408.12879","title":"Frequency-aware Feature Fusion for Dense Image Prediction","created":"2024-08-23","cited_by_count":48},{"id":"2409.01686","title":"Frequency-Spatial Entanglement Learning for Camouflaged Object Detection","created":"2024-09-03","cited_by_count":46},{"id":"2307.14008","title":"Adaptive Frequency Filters As Efficient Global Token Mixers","created":"2023-07-26","cited_by_count":45},{"id":"2407.20892","title":"What is YOLOv5: A deep look into the internal features of the popular object detector","created":"2024-07-30","cited_by_count":37},{"id":"2303.07335","title":"Lite DETR : An Interleaved Multi-Scale Encoder for Efficient DETR","created":"2023-03-13","cited_by_count":36},{"id":"2401.03989","title":"MS-DETR: Efficient DETR Training with Mixed Supervision","created":"2024-01-08","cited_by_count":35},{"id":"2403.05369","title":"Frequency-Adaptive Dilated Convolution for Semantic Segmentation","created":"2024-03-08","cited_by_count":34},{"id":"2412.16986","title":"Pinwheel-shaped Convolution and Scale-based Dynamic Loss for Infrared Small Target Detection","created":"2024-12-22","cited_by_count":34},{"id":"2409.08475","title":"RT-DETRv3: Real-time End-to-End Object Detection with Hierarchical Dense Positive Supervision","created":"2024-09-13","cited_by_count":32},{"id":"2301.10051","title":"Wise-IoU: Bounding Box Regression Loss with Dynamic Focusing Mechanism","created":"2023-01-24","cited_by_count":30},{"id":"2509.20787","title":"Real-Time Object Detection Meets DINOv3","created":"2025-09-25","cited_by_count":27},{"id":"2303.03932","title":"FFT-based Dynamic Token Mixer for Vision","created":"2023-03-07","cited_by_count":22},{"id":"2412.10116","title":"HS-FPN: High Frequency and Spatial Perception FPN for Tiny Object Detection","created":"2024-12-13","cited_by_count":22},{"id":"2406.05835","title":"Mamba YOLO: A Simple Baseline for Object Detection with State Space Model","created":"2024-06-09","cited_by_count":19},{"id":"2503.18783","title":"Frequency Dynamic Convolution for Dense Image Prediction","created":"2025-03-24","cited_by_count":19},{"id":"2110.13675","title":"Alpha-IoU: A Family of Power Intersection over Union Losses for Bounding Box Regression","created":"2021-10-26","cited_by_count":18},{"id":"2504.02555","title":"Noise Calibration and Spatial-Frequency Interactive Network for STEM Image Enhancement","created":"2025-04-03","cited_by_count":16},{"id":"2103.05959","title":"Beyond Self-Supervision: A Simple Yet Effective Network Distillation Alternative to Improve Backbones","created":"2021-03-10","cited_by_count":15},{"id":"2501.01855","title":"UAV-DETR: Efficient End-to-End Object Detection for Unmanned Aerial Vehicle Imagery","created":"2025-01-03","cited_by_count":15},{"id":"2510.25257","title":"RT-DETRv4: Painlessly Furthering Real-Time Object Detection with Vision Foundation Models","created":"2025-10-29","cited_by_count":15},{"id":"2508.19294","title":"Object Detection with Multimodal Large Vision-Language Models: An In-depth Review","created":"2025-08-25","cited_by_count":14},{"id":"2504.20670","title":"FBRT-YOLO: Faster and Better for Real-Time Aerial Image Detection","created":"2025-04-29","cited_by_count":13},{"id":"2509.18493","title":"MK-UNet: Multi-kernel Lightweight CNN for Medical Image Segmentation","created":"2025-09-23","cited_by_count":12},{"id":"2601.17237","title":"C-RADIOv4 (Tech Report)","created":"2026-01-24","cited_by_count":12},{"id":"2507.12006","title":"Frequency-Dynamic Attention Modulation for Dense Prediction","created":"2025-07-16","cited_by_count":10},{"id":"2512.05494","title":"Decoding with Structured Awareness: Integrating Directional, Frequency-Spatial, and Structural Attention for Medical Image Segmentation","created":"2025-12-05","cited_by_count":9},{"id":"2412.16645","title":"Complementary Advantages: Exploiting Cross-Field Frequency Correlation for NIR-Assisted Image Denoising","created":"2024-12-21","cited_by_count":5},{"id":"2511.06593","title":"Spatial-Frequency Enhanced Mamba for Multi-Modal Image Fusion","created":"2025-11-10","cited_by_count":5},{"id":"2601.08602","title":"WaveFormer: Frequency-Time Decoupled Vision Modeling with Wave Equation","created":"2026-01-13","cited_by_count":5},{"id":"2502.01303","title":"Partial Channel Network: Compute Fewer, Perform Better","created":"2025-02-03","cited_by_count":3},{"id":"2507.11893","title":"Spatial Frequency Modulation for Semantic Segmentation","created":"2025-07-16","cited_by_count":3},{"id":"2507.22477","title":"LIDAR: Lightweight Adaptive Cue-Aware Fusion Vision Mamba for Multimodal Segmentation of Structural Cracks","created":"2025-07-30","cited_by_count":3},{"id":"2410.21813","title":"SAM-Swin: SAM-Driven Dual-Swin Transformers with Adaptive Lesion Enhancement for Laryngo-Pharyngeal Tumor Detection","created":"2024-10-29","cited_by_count":2},{"id":"2504.15165","title":"An Efficient Aerial Image Detection with Variable Receptive Fields","created":"2025-04-21","cited_by_count":2}],"next_cursor":null}