{"list":"other","total":54,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"1911.11763","title":"SuperGlue: Learning Feature Matching with Graph Neural Networks","created":"2019-11-26","cited_by_count":1443},{"id":"1712.07629","title":"SuperPoint: Self-Supervised Interest Point Detection and Description","created":"2017-12-20","cited_by_count":1320},{"id":"2104.00680","title":"LoFTR: Detector-Free Local Feature Matching with Transformers","created":"2021-04-01","cited_by_count":984},{"id":"1511.07247","title":"NetVLAD: CNN architecture for weakly supervised place recognition","created":"2015-11-23","cited_by_count":941},{"id":"2007.11898","title":"ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM","created":"2020-07-23","cited_by_count":878},{"id":"1610.06475","title":"ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras","created":"2016-10-20","cited_by_count":806},{"id":"1804.00607","title":"MegaDepth: Learning Single-View Depth Prediction from Internet Photos","created":"2018-04-02","cited_by_count":737},{"id":"2306.13643","title":"LightGlue: Local Feature Matching at Light Speed","created":"2023-06-23","cited_by_count":590},{"id":"1812.03506","title":"From Coarse to Fine: Robust Hierarchical Localization at Large Scale","created":"2018-12-09","cited_by_count":559},{"id":"1912.03458","title":"Dynamic Convolution: Attention over Convolution Kernels","created":"2019-12-07","cited_by_count":356},{"id":"1905.03561","title":"D2-Net: A Trainable CNN for Joint Detection and Description of Local Features","created":"2019-05-09","cited_by_count":326},{"id":"2006.13566","title":"DISK: Learning local features with policy gradient","created":"2020-06-24","cited_by_count":312},{"id":"1704.05939","title":"HPatches: A benchmark and evaluation of handcrafted and learned local descriptors","created":"2017-04-19","cited_by_count":264},{"id":"1906.06195","title":"R2D2: Repeatable and Reliable Detector and Descriptor","created":"2019-06-14","cited_by_count":207},{"id":"1810.10510","title":"Neighbourhood Consensus Networks","created":"2018-10-24","cited_by_count":174},{"id":"2208.14201","title":"ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformer","created":"2022-08-30","cited_by_count":171},{"id":"1908.04964","title":"Learning Two-View Correspondences and Geometry Using Order-Aware Network","created":"2019-08-14","cited_by_count":149},{"id":"2003.10071","title":"ASLFeat: Learning Local Features of Accurate Shape and Localization","created":"2020-03-23","cited_by_count":130},{"id":"2012.01909","title":"Patch2Pix: Epipolar-Guided Pixel-Level Correspondences","created":"2020-12-03","cited_by_count":129},{"id":"2201.02767","title":"QuadTree Attention for Vision Transformers","created":"2022-01-08","cited_by_count":129},{"id":"2203.09645","title":"MatchFormer: Interleaving Attention in Transformers for Feature Matching","created":"2022-03-17","cited_by_count":126},{"id":"2004.10566","title":"Efficient Neighbourhood Consensus Networks via Submanifold Sparse Convolutions","created":"2020-04-22","cited_by_count":93},{"id":"2108.08771","title":"Learning to Match Features with Seeded Graph Matching Network","created":"2021-08-19","cited_by_count":92},{"id":"2006.08844","title":"Dual-Resolution Correspondence Networks","created":"2020-06-16","cited_by_count":90},{"id":"2109.13912","title":"PDC-Net+: Enhanced Probabilistic Dense Correspondence Network","created":"2021-09-28","cited_by_count":80},{"id":"2112.02906","title":"ALIKE: Accurate and Lightweight Keypoint Detection and Descriptor Extraction","created":"2021-12-06","cited_by_count":77},{"id":"2204.11700","title":"ClusterGNN: Cluster-based Coarse-to-Fine Graph Neural Network for Efficient Feature Matching","created":"2022-04-25","cited_by_count":62},{"id":"2108.09084","title":"Fastformer: Additive Attention Can Be All You Need","created":"2021-08-20","cited_by_count":61},{"id":"2204.05585","title":"SwinNet: Swin Transformer drives edge-aware RGB-D and RGB-T salient object detection","created":"2022-04-12","cited_by_count":59},{"id":"2205.12785","title":"AO2-DETR: Arbitrary-Oriented Object Detection Transformer","created":"2022-05-25","cited_by_count":55},{"id":"2207.00328","title":"TopicFM: Robust and Interpretable Topic-Assisted Feature Matching","created":"2022-07-01","cited_by_count":32},{"id":"2207.08427","title":"Adaptive Assignment for Geometry Aware Local Feature Matching","created":"2022-07-18","cited_by_count":30},{"id":"2209.10218","title":"HiFuse: Hierarchical Multi-Scale Feature Fusion Network for Medical Image Classification","created":"2022-09-21","cited_by_count":30},{"id":"2301.02993","title":"DeepMatcher: A Deep Transformer-based Network for Robust and Accurate Local Feature Matching","created":"2023-01-08","cited_by_count":18},{"id":"2106.07791","title":"DFM: A Performance Baseline for Deep Feature Matching","created":"2021-06-14","cited_by_count":17},{"id":"2112.05999","title":"Curvature-guided dynamic scale networks for Multi-view Stereo","created":"2021-12-11","cited_by_count":17},{"id":"2207.02375","title":"3DG-STFM: 3D Geometric Guided Student-Teacher Feature Matching","created":"2022-07-06","cited_by_count":14},{"id":"2203.01178","title":"DCT-Former: Efficient Self-Attention with Discrete Cosine Transform","created":"2022-03-02","cited_by_count":12},{"id":"2112.06910","title":"DenseGAP: Graph-Structured Dense Correspondence Learning with Anchor Points","created":"2021-12-13","cited_by_count":8},{"id":"2302.05846","title":"OAMatcher: An Overlapping Areas-based Network for Accurate Local Feature Matching","created":"2023-02-12","cited_by_count":7},{"id":"2004.12317","title":"Online Mapping and Motion Planning under Uncertainty for Safe Navigation in Unknown Environments","created":"2020-04-26","cited_by_count":6},{"id":"2204.07731","title":"Efficient Linear Attention for Fast and Accurate Keypoint Matching","created":"2022-04-16","cited_by_count":6},{"id":"2109.08963","title":"SDTP: Semantic-aware Decoupled Transformer Pyramid for Dense Image Prediction","created":"2021-09-18","cited_by_count":5},{"id":"2306.04231","title":"Learning Probabilistic Coordinate Fields for Robust Correspondences","created":"2023-06-07","cited_by_count":3}],"next_cursor":null}