{"list":"other","total":55,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"1705.07115","title":"Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics","created":"2017-05-19","cited_by_count":1358},{"id":"1712.07629","title":"SuperPoint: Self-Supervised Interest Point Detection and Description","created":"2017-12-20","cited_by_count":1320},{"id":"1609.05158","title":"Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network","created":"2016-09-16","cited_by_count":1204},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"id":"1906.05797","title":"The Replica Dataset: A Digital Replica of Indoor Spaces","created":"2019-06-13","cited_by_count":904},{"id":"1804.00607","title":"MegaDepth: Learning Single-View Depth Prediction from Internet Photos","created":"2018-04-02","cited_by_count":737},{"id":"2109.08238","title":"Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI","created":"2021-09-16","cited_by_count":592},{"id":"1812.03506","title":"From Coarse to Fine: Robust Hierarchical Localization at Large Scale","created":"2018-12-09","cited_by_count":559},{"id":"2106.14405","title":"Habitat 2.0: Training Home Assistants to Rearrange their Habitat","created":"2021-06-28","cited_by_count":511},{"id":"2111.08897","title":"ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data","created":"2021-11-17","cited_by_count":454},{"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":"1611.05705","title":"DSAC - Differentiable RANSAC for Camera Localization","created":"2016-11-17","cited_by_count":266},{"id":"1704.00390","title":"Geometric Loss Functions for Camera Pose Regression with Deep Learning","created":"2017-04-02","cited_by_count":224},{"id":"2007.10042","title":"Non-Local Spatial Propagation Network for Depth Completion","created":"2020-07-20","cited_by_count":195},{"id":"1902.11020","title":"DPOD: 6D Pose Object Detector and Refiner","created":"2019-02-28","cited_by_count":189},{"id":"1906.07589","title":"Learning with Average Precision: Training Image Retrieval with a Listwise Loss","created":"2019-06-18","cited_by_count":185},{"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":"2211.10408","title":"CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow","created":"2022-11-18","cited_by_count":166},{"id":"1712.03342","title":"Geometry-Aware Learning of Maps for Camera Localization","created":"2017-12-09","cited_by_count":161},{"id":"2210.10716","title":"CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion","created":"2022-10-19","cited_by_count":160},{"id":"1805.09662","title":"LF-Net: Learning Local Features from Images","created":"2018-05-24","cited_by_count":151},{"id":"1711.10228","title":"Learning Less is More - 6D Camera Localization via 3D Surface Regression","created":"2017-11-28","cited_by_count":146},{"id":"2103.00783","title":"PENet: Towards Precise and Efficient Image Guided Depth Completion","created":"2021-03-01","cited_by_count":146},{"id":"1904.05019","title":"SOSNet: Second Order Similarity Regularization for Local Descriptor Learning","created":"2019-04-10","cited_by_count":131},{"id":"2003.10071","title":"ASLFeat: Learning Local Features of Accurate Shape and Localization","created":"2020-03-23","cited_by_count":130},{"id":"2210.05494","title":"Map-free Visual Relocalization: Metric Pose Relative to a Single Image","created":"2022-10-11","cited_by_count":114},{"id":"1911.05377","title":"CSPN++: Learning Context and Resource Aware Convolutional Spatial Propagation Networks for Depth Completion","created":"2019-11-13","cited_by_count":110},{"id":"2004.13324","title":"Learning Feature Descriptors using Camera Pose Supervision","created":"2020-04-28","cited_by_count":104},{"id":"1909.06216","title":"Hierarchical Scene Coordinate Classification and Regression for Visual Localization","created":"2019-09-13","cited_by_count":93},{"id":"1909.03557","title":"AtLoc: Attention Guided Camera Localization","created":"2019-09-08","cited_by_count":92},{"id":"1902.05356","title":"Sparse and noisy LiDAR completion with RGB guidance and uncertainty","created":"2019-02-14","cited_by_count":79},{"id":"1908.02484","title":"Expert Sample Consensus Applied to Camera Re-Localization","created":"2019-08-07","cited_by_count":70},{"id":"2007.13867","title":"Robust Image Retrieval-based Visual Localization using Kapture","created":"2020-07-27","cited_by_count":66},{"id":"1908.01293","title":"To Learn or Not to Learn: Visual Localization from Essential Matrices","created":"2019-08-04","cited_by_count":61},{"id":"2007.13172","title":"Learning and aggregating deep local descriptors for instance-level recognition","created":"2020-07-26","cited_by_count":55},{"id":"1807.06294","title":"GeoDesc: Learning Local Descriptors by Integrating Geometry Constraints","created":"2018-07-17","cited_by_count":52},{"id":"2003.10629","title":"KFNet: Learning Temporal Camera Relocalization using Kalman Filtering","created":"2020-03-24","cited_by_count":43},{"id":"1807.07512","title":"Hybrid Scene Compression for Visual Localization","created":"2018-07-19","cited_by_count":40},{"id":"2208.06933","title":"Visual Localization via Few-Shot Scene Region Classification","created":"2022-08-14","cited_by_count":36},{"id":"2201.13182","title":"Learning Super-Features for Image Retrieval","created":"2022-01-31","cited_by_count":35},{"id":"2105.10886","title":"VS-Net: Voting with Segmentation for Visual Localization","created":"2021-05-23","cited_by_count":29},{"id":"2103.16792","title":"Learning Camera Localization via Dense Scene Matching","created":"2021-03-31","cited_by_count":28},{"id":"2201.02861","title":"Decoupling Makes Weakly Supervised Local Feature Better","created":"2022-01-08","cited_by_count":28},{"id":"2211.11177","title":"NeuMap: Neural Coordinate Mapping by Auto-Transdecoder for Camera Localization","created":"2022-11-21","cited_by_count":26},{"id":"2204.13635","title":"SemAttNet: Towards Attention-based Semantic Aware Guided Depth Completion","created":"2022-04-28","cited_by_count":23},{"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":"1908.06141","title":"Cascaded Parallel Filtering for Memory-Efficient Image-Based Localization","created":"2019-08-16","cited_by_count":17},{"id":"2210.12748","title":"SC-wLS: Towards Interpretable Feed-forward Camera Re-localization","created":"2022-10-23","cited_by_count":14},{"id":"2011.13894","title":"Efficient Scene Compression for Visual-based Localization","created":"2020-11-27","cited_by_count":12}],"next_cursor":null}