{"list":"other","total":69,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"1511.00561","title":"SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation","created":"2015-11-02","cited_by_count":1487},{"id":"1712.07629","title":"SuperPoint: Self-Supervised Interest Point Detection and Description","created":"2017-12-20","cited_by_count":1320},{"id":"1608.05442","title":"Semantic Understanding of Scenes through the ADE20K Dataset","created":"2016-08-18","cited_by_count":1069},{"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":"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":"1812.03506","title":"From Coarse to Fine: Robust Hierarchical Localization at Large Scale","created":"2018-12-09","cited_by_count":559},{"id":"1711.02512","title":"Fine-tuning CNN Image Retrieval with No Human Annotation","created":"2017-11-03","cited_by_count":499},{"id":"1607.02565","title":"Direct Sparse Odometry","created":"2016-07-09","cited_by_count":485},{"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":"1603.09114","title":"LIFT: Learned Invariant Feature Transform","created":"2016-03-30","cited_by_count":306},{"id":"2305.15404","title":"RoMa: Robust Dense Feature Matching","created":"2023-05-24","cited_by_count":302},{"id":"1611.05705","title":"DSAC - Differentiable RANSAC for Camera Localization","created":"2016-11-17","cited_by_count":266},{"id":"2103.01486","title":"Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition","created":"2021-03-02","cited_by_count":238},{"id":"1704.00390","title":"Geometric Loss Functions for Camera Pose Regression with Deep Learning","created":"2017-04-02","cited_by_count":224},{"id":"1906.06195","title":"R2D2: Repeatable and Reliable Detector and Descriptor","created":"2019-06-14","cited_by_count":207},{"id":"2103.09213","title":"Back to the Feature: Learning Robust Camera Localization from Pixels to Pose","created":"2021-03-16","cited_by_count":199},{"id":"1903.07504","title":"Understanding the Limitations of CNN-based Absolute Camera Pose Regression","created":"2019-03-18","cited_by_count":177},{"id":"2002.12324","title":"Visual Camera Re-Localization from RGB and RGB-D Images Using DSAC","created":"2020-02-27","cited_by_count":176},{"id":"2208.14201","title":"ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformer","created":"2022-08-30","cited_by_count":171},{"id":"1712.03342","title":"Geometry-Aware Learning of Maps for Camera Localization","created":"2017-12-09","cited_by_count":161},{"id":"1711.10228","title":"Learning Less is More - 6D Camera Localization via 3D Surface Regression","created":"2017-11-28","cited_by_count":146},{"id":"2003.10071","title":"ASLFeat: Learning Local Features of Accurate Shape and Localization","created":"2020-03-23","cited_by_count":130},{"id":"2110.06558","title":"LENS: Localization enhanced by NeRF synthesis","created":"2021-10-13","cited_by_count":117},{"id":"2103.11468","title":"Learning Multi-Scene Absolute Pose Regression with Transformers","created":"2021-03-21","cited_by_count":108},{"id":"2305.14059","title":"Accelerated Coordinate Encoding: Learning to Relocalize in Minutes using RGB and Poses","created":"2023-05-23","cited_by_count":107},{"id":"1904.02216","title":"DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation","created":"2019-04-03","cited_by_count":100},{"id":"1909.06216","title":"Hierarchical Scene Coordinate Classification and Regression for Visual Localization","created":"2019-09-13","cited_by_count":93},{"id":"2004.10566","title":"Efficient Neighbourhood Consensus Networks via Submanifold Sparse Convolutions","created":"2020-04-22","cited_by_count":93},{"id":"1909.03557","title":"AtLoc: Attention Guided Camera Localization","created":"2019-09-08","cited_by_count":92},{"id":"2108.08771","title":"Learning to Match Features with Seeded Graph Matching Network","created":"2021-08-19","cited_by_count":92},{"id":"2204.00559","title":"DFNet: Enhance Absolute Pose Regression with Direct Feature Matching","created":"2022-04-01","cited_by_count":82},{"id":"1908.02484","title":"Expert Sample Consensus Applied to Camera Re-Localization","created":"2019-08-07","cited_by_count":70},{"id":"2304.02008","title":"GlueStick: Robust Image Matching by Sticking Points and Lines Together","created":"2023-04-04","cited_by_count":66},{"id":"1603.05772","title":"Learning to Navigate the Energy Landscape","created":"2016-03-18","cited_by_count":62},{"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":"1712.05773","title":"Semantic Visual Localization","created":"2017-12-15","cited_by_count":54},{"id":"2303.04869","title":"CROSSFIRE: Camera Relocalization On Self-Supervised Features from an Implicit Representation","created":"2023-03-08","cited_by_count":45},{"id":"2003.10629","title":"KFNet: Learning Temporal Camera Relocalization using Kalman Filtering","created":"2020-03-24","cited_by_count":43},{"id":"2104.02538","title":"Visual Camera Re-Localization Using Graph Neural Networks and Relative Pose Supervision","created":"2021-04-06","cited_by_count":37},{"id":"2303.10087","title":"Neural Refinement for Absolute Pose Regression with Feature Synthesis","created":"2023-03-17","cited_by_count":37},{"id":"2208.06933","title":"Visual Localization via Few-Shot Scene Region Classification","created":"2022-08-14","cited_by_count":36},{"id":"2403.09577","title":"The NeRFect Match: Exploring NeRF Features for Visual Localization","created":"2024-03-14","cited_by_count":32},{"id":"2105.10886","title":"VS-Net: Voting with Segmentation for Visual Localization","created":"2021-05-23","cited_by_count":29},{"id":"2304.07979","title":"NeRF-Loc: Visual Localization with Conditional Neural Radiance Field","created":"2023-04-17","cited_by_count":29},{"id":"2103.16792","title":"Learning Camera Localization via Dense Scene Matching","created":"2021-03-31","cited_by_count":28},{"id":"2207.05530","title":"Camera Pose Auto-Encoders for Improving Pose Regression","created":"2022-07-12","cited_by_count":28},{"id":"2304.14845","title":"SFD2: Semantic-guided Feature Detection and Description","created":"2023-04-28","cited_by_count":28},{"id":"1904.01892","title":"Beyond Tracking: Selecting Memory and Refining Poses for Deep Visual Odometry","created":"2019-04-03","cited_by_count":27},{"id":"2211.11177","title":"NeuMap: Neural Coordinate Mapping by Auto-Transdecoder for Camera Localization","created":"2022-11-21","cited_by_count":26},{"id":"1908.04391","title":"Local Supports Global: Deep Camera Relocalization with Sequence Enhancement","created":"2019-08-06","cited_by_count":25},{"id":"1908.06387","title":"Fine-Grained Segmentation Networks: Self-Supervised Segmentation for Improved Long-Term Visual Localization","created":"2019-08-18","cited_by_count":24},{"id":"1904.06635","title":"Localizing Discriminative Visual Landmarks for Place Recognition","created":"2019-04-14","cited_by_count":21},{"id":"2210.01044","title":"SPARC: Sparse Render-and-Compare for CAD model alignment in a single RGB image","created":"2022-10-03","cited_by_count":19},{"id":"1908.08704","title":"Sequential Adversarial Learning for Self-Supervised Deep Visual Odometry","created":"2019-08-23","cited_by_count":18},{"id":"1908.06141","title":"Cascaded Parallel Filtering for Memory-Efficient Image-Based Localization","created":"2019-08-16","cited_by_count":17},{"id":"1801.05269","title":"Long-term Visual Localization using Semantically Segmented Images","created":"2018-01-16","cited_by_count":15},{"id":"2210.12748","title":"SC-wLS: Towards Interpretable Feed-forward Camera Re-localization","created":"2022-10-23","cited_by_count":14},{"id":"1909.10239","title":"Large Scale Joint Semantic Re-Localisation and Scene Understanding via Globally Unique Instance Coordinate Regression","created":"2019-09-23","cited_by_count":12},{"id":"2304.14837","title":"IMP: Iterative Matching and Pose Estimation with Adaptive Pooling","created":"2023-04-28","cited_by_count":10},{"id":"1904.03803","title":"Visual Localization Using Sparse Semantic 3D Map","created":"2019-04-08","cited_by_count":9},{"id":"2310.11184","title":"Sparse Multi-Object Render-and-Compare","created":"2023-10-17","cited_by_count":3}],"next_cursor":null}