{"list":"other","total":59,"rows":[{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"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":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"2006.10739","title":"Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains","created":"2020-06-18","cited_by_count":2200},{"id":"1904.01355","title":"FCOS: Fully Convolutional One-Stage Object Detection","created":"2019-04-02","cited_by_count":1577},{"id":"1703.06211","title":"Deformable Convolutional Networks","created":"2017-03-17","cited_by_count":1488},{"id":"1806.08734","title":"On the Spectral Bias of Neural Networks","created":"2018-06-22","cited_by_count":1341},{"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":"1712.00726","title":"Cascade R-CNN: Delving into High Quality Object Detection","created":"2017-12-03","cited_by_count":1276},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"1602.07576","title":"Group Equivariant Convolutional Networks","created":"2016-02-24","cited_by_count":1165},{"id":"1811.11168","title":"Deformable ConvNets v2: More Deformable, Better Results","created":"2018-11-27","cited_by_count":670},{"id":"2012.09161","title":"Learning Continuous Image Representation with Local Implicit Image Function","created":"2020-12-16","cited_by_count":552},{"id":"1912.02424","title":"Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection","created":"2019-12-05","cited_by_count":540},{"id":"2211.05778","title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","created":"2022-11-10","cited_by_count":482},{"id":"1911.08251","title":"General $E(2)$-Equivariant Steerable CNNs","created":"2019-11-19","cited_by_count":446},{"id":"2502.12524","title":"YOLOv12: Attention-Centric Real-Time Object Detectors","created":"2025-02-18","cited_by_count":305},{"id":"2211.12860","title":"DETRs with Collaborative Hybrid Assignments Training","created":"2022-11-22","cited_by_count":274},{"id":"1904.11490","title":"RepPoints: Point Set Representation for Object Detection","created":"2019-04-25","cited_by_count":264},{"id":"2008.13367","title":"VarifocalNet: An IoU-aware Dense Object Detector","created":"2020-08-31","cited_by_count":231},{"id":"2108.05699","title":"Oriented R-CNN for Object Detection","created":"2021-08-12","cited_by_count":231},{"id":"2108.10831","title":"LLVIP: A Visible-infrared Paired Dataset for Low-light Vision","created":"2021-08-24","cited_by_count":231},{"id":"2108.07755","title":"TOOD: Task-aligned One-stage Object Detection","created":"2021-08-17","cited_by_count":218},{"id":"2103.07733","title":"ReDet: A Rotation-equivariant Detector for Aerial Object Detection","created":"2021-03-13","cited_by_count":203},{"id":"2212.07784","title":"RTMDet: An Empirical Study of Designing Real-Time Object Detectors","created":"2022-12-14","cited_by_count":195},{"id":"1908.05612","title":"R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object","created":"2019-08-15","cited_by_count":194},{"id":"2008.09397","title":"Align Deep Features for Oriented Object Detection","created":"2020-08-21","cited_by_count":187},{"id":"2101.11952","title":"Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss","created":"2021-01-28","cited_by_count":156},{"id":"2003.02437","title":"Drone-based RGB-Infrared Cross-Modality Vehicle Detection via Uncertainty-Aware Learning","created":"2020-03-05","cited_by_count":152},{"id":"1911.09358","title":"Gliding vertex on the horizontal bounding box for multi-oriented object detection","created":"2019-11-21","cited_by_count":134},{"id":"2106.01883","title":"Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence","created":"2021-06-03","cited_by_count":130},{"id":"2103.09460","title":"You Only Look One-level Feature","created":"2021-03-17","cited_by_count":116},{"id":"2105.11111","title":"Oriented RepPoints for Aerial Object Detection","created":"2021-05-24","cited_by_count":102},{"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":"2308.07504","title":"ICAFusion: Iterative Cross-Attention Guided Feature Fusion for Multispectral Object Detection","created":"2023-08-15","cited_by_count":76},{"id":"2306.16175","title":"$\\mathbf{C}^2$Former: Calibrated and Complementary Transformer for RGB-Infrared Object Detection","created":"2023-06-28","cited_by_count":58},{"id":"2103.12716","title":"UltraSR: Spatial Encoding is a Missing Key for Implicit Image Function-based Arbitrary-Scale Super-Resolution","created":"2021-03-23","cited_by_count":57},{"id":"2205.12785","title":"AO2-DETR: Arbitrary-Oriented Object Detection Transformer","created":"2022-05-25","cited_by_count":55},{"id":"2401.06197","title":"Efficient Deformable ConvNets: Rethinking Dynamic and Sparse Operator for Vision Applications","created":"2024-01-11","cited_by_count":50},{"id":"2403.11735","title":"LSKNet: A Foundation Lightweight Backbone for Remote Sensing","created":"2024-03-18","cited_by_count":44},{"id":"2304.08876","title":"Dynamic Coarse-to-Fine Learning for Oriented Tiny Object Detection","created":"2023-04-18","cited_by_count":43},{"id":"1904.03797","title":"FoveaBox: Beyond Anchor-based Object Detector","created":"2019-04-08","cited_by_count":37},{"id":"2303.04989","title":"ARS-DETR: Aspect Ratio-Sensitive Detection Transformer for Aerial Oriented Object Detection","created":"2023-03-09","cited_by_count":32},{"id":"2407.08132","title":"DMM: Disparity-guided Multispectral Mamba for Oriented Object Detection in Remote Sensing","created":"2024-07-11","cited_by_count":20},{"id":"2312.15701","title":"Rotation Equivariant Proximal Operator for Deep Unfolding Methods in Image Restoration","created":"2023-12-25","cited_by_count":17},{"id":"2501.03775","title":"Strip R-CNN: Large Strip Convolution for Remote Sensing Object Detection","created":"2025-01-07","cited_by_count":14},{"id":"2507.18173","title":"WaveMamba: Wavelet-Driven Mamba Fusion for RGB-Infrared Object Detection","created":"2025-07-24","cited_by_count":14},{"id":"2312.08692","title":"SpectralNeRF: Physically Based Spectral Rendering with Neural Radiance Field","created":"2023-12-14","cited_by_count":13},{"id":"2304.02767","title":"MethaneMapper: Spectral Absorption aware Hyperspectral Transformer for Methane Detection","created":"2023-04-05","cited_by_count":12},{"id":"2306.08370","title":"Object Detection in Hyperspectral Image via Unified Spectral-Spatial Feature Aggregation","created":"2023-06-14","cited_by_count":10},{"id":"2404.15174","title":"Fourier-enhanced Implicit Neural Fusion Network for Multispectral and Hyperspectral Image Fusion","created":"2024-04-23","cited_by_count":10},{"id":"2305.07598","title":"Hausdorff Distance Matching with Adaptive Query Denoising for Rotated Detection Transformer","created":"2023-05-12","cited_by_count":9},{"id":"2407.08489","title":"Projecting Points to Axes: Oriented Object Detection via Point-Axis Representation","created":"2024-07-11","cited_by_count":8},{"id":"2401.06159","title":"FRED: Towards a Full Rotation-Equivariance in Aerial Image Object Detection","created":"2023-12-22","cited_by_count":7},{"id":"2408.11760","title":"R2Det: Exploring Relaxed Rotation Equivariance in 2D object detection","created":"2024-08-21","cited_by_count":4},{"id":"2408.12454","title":"Relaxed Rotational Equivariance via $G$-Biases in Vision","created":"2024-08-22","cited_by_count":4},{"id":"2507.09896","title":"Measuring the Impact of Rotation Equivariance on Aerial Object Detection","created":"2025-07-14","cited_by_count":4},{"id":"2411.01624","title":"PreCM: The Padding-based Rotation Equivariant Convolution Mode for Semantic Segmentation","created":"2024-11-03","cited_by_count":1},{"id":"2512.09489","title":"MODA: The First Challenging Benchmark for Multispectral Object Detection in Aerial Images","created":"2025-12-10","cited_by_count":1}],"next_cursor":null}