{"list":"other","total":53,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1612.00593","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","created":"2016-12-02","cited_by_count":5248},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"1901.05103","title":"DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation","created":"2019-01-16","cited_by_count":2689},{"id":"2204.01691","title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","created":"2022-04-04","cited_by_count":2348},{"id":"1812.03828","title":"Occupancy Networks: Learning 3D Reconstruction in Function Space","created":"2018-12-10","cited_by_count":2041},{"id":"1911.11763","title":"SuperGlue: Learning Feature Matching with Graph Neural Networks","created":"2019-11-26","cited_by_count":1443},{"id":"1511.07247","title":"NetVLAD: CNN architecture for weakly supervised place recognition","created":"2015-11-23","cited_by_count":941},{"id":"2003.04618","title":"Convolutional Occupancy Networks","created":"2020-03-10","cited_by_count":761},{"id":"1812.03506","title":"From Coarse to Fine: Robust Hierarchical Localization at Large Scale","created":"2018-12-09","cited_by_count":559},{"id":"1909.03211","title":"Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View","created":"2019-09-07","cited_by_count":545},{"id":"2009.03509","title":"Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification","created":"2020-09-08","cited_by_count":506},{"id":"1912.08830","title":"ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language","created":"2019-12-18","cited_by_count":452},{"id":"2112.10482","title":"ScanQA: 3D Question Answering for Spatial Scene Understanding","created":"2021-12-20","cited_by_count":346},{"id":"2210.07474","title":"SQA3D: Situated Question Answering in 3D Scenes","created":"2022-10-14","cited_by_count":314},{"id":"1910.02527","title":"3D Scene Graph: A Structure for Unified Semantics, 3D Space, and Camera","created":"2019-10-06","cited_by_count":281},{"id":"1611.05705","title":"DSAC - Differentiable RANSAC for Camera Localization","created":"2016-11-17","cited_by_count":266},{"id":"2303.10993","title":"A Survey on Oversmoothing in Graph Neural Networks","created":"2023-03-20","cited_by_count":247},{"id":"1704.00390","title":"Geometric Loss Functions for Camera Pose Regression with Deep Learning","created":"2017-04-02","cited_by_count":224},{"id":"2012.02206","title":"Scan2Cap: Context-aware Dense Captioning in RGB-D Scans","created":"2020-12-03","cited_by_count":218},{"id":"2004.03967","title":"Learning 3D Semantic Scene Graphs from 3D Indoor Reconstructions","created":"2020-04-08","cited_by_count":208},{"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":"1908.06109","title":"RIO: 3D Object Instance Re-Localization in Changing Indoor Environments","created":"2019-08-16","cited_by_count":188},{"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":"1711.10228","title":"Learning Less is More - 6D Camera Localization via 3D Surface Regression","created":"2017-11-28","cited_by_count":146},{"id":"2204.02174","title":"Multi-View Transformer for 3D Visual Grounding","created":"2022-04-05","cited_by_count":140},{"id":"1611.07890","title":"Image-based localization using LSTMs for structured feature correlation","created":"2016-11-23","cited_by_count":136},{"id":"2110.06558","title":"LENS: Localization enhanced by NeRF synthesis","created":"2021-10-13","cited_by_count":117},{"id":"2107.03438","title":"LanguageRefer: Spatial-Language Model for 3D Visual Grounding","created":"2021-07-07","cited_by_count":89},{"id":"2108.08841","title":"Graph-to-3D: End-to-End Generation and Manipulation of 3D Scenes Using Scene Graphs","created":"2021-08-19","cited_by_count":84},{"id":"2103.16381","title":"Free-form Description Guided 3D Visual Graph Network for Object Grounding in Point Cloud","created":"2021-03-30","cited_by_count":81},{"id":"2303.16894","title":"ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and Prototype Guidance","created":"2023-03-29","cited_by_count":70},{"id":"2207.05006","title":"TASKOGRAPHY: Evaluating robot task planning over large 3D scene graphs","created":"2022-07-11","cited_by_count":59},{"id":"1712.05773","title":"Semantic Visual Localization","created":"2017-12-15","cited_by_count":54},{"id":"2309.04077","title":"SayNav: Grounding Large Language Models for Dynamic Planning to Navigation in New Environments","created":"2023-09-08","cited_by_count":53},{"id":"2011.14791","title":"NeuralFusion: Online Depth Fusion in Latent Space","created":"2020-11-30","cited_by_count":46},{"id":"1907.00338","title":"Large-scale, real-time visual-inertial localization revisited","created":"2019-06-30","cited_by_count":45},{"id":"2011.11946","title":"Benchmarking Image Retrieval for Visual Localization","created":"2020-11-24","cited_by_count":42},{"id":"2203.15125","title":"Text2Pos: Text-to-Point-Cloud Cross-Modal Localization","created":"2022-03-28","cited_by_count":40},{"id":"2204.10688","title":"Spatiality-guided Transformer for 3D Dense Captioning on Point Clouds","created":"2022-04-22","cited_by_count":40},{"id":"2203.17251","title":"Continuous Scene Representations for Embodied AI","created":"2022-03-31","cited_by_count":39},{"id":"2311.15977","title":"Text2Loc: 3D Point Cloud Localization from Natural Language","created":"2023-11-27","cited_by_count":35},{"id":"1906.08744","title":"Let's Take This Online: Adapting Scene Coordinate Regression Network Predictions for Online RGB-D Camera Relocalisation","created":"2019-06-20","cited_by_count":28},{"id":"1907.03965","title":"Sparse-to-Dense Hypercolumn Matching for Long-Term Visual Localization","created":"2019-07-09","cited_by_count":20},{"id":"2301.05372","title":"Text to Point Cloud Localization with Relation-Enhanced Transformer","created":"2023-01-13","cited_by_count":20},{"id":"2207.04364","title":"Sequential Manipulation Planning on Scene Graph","created":"2022-07-10","cited_by_count":17},{"id":"2103.06535","title":"Calibrated and Partially Calibrated Semi-Generalized Homographies","created":"2021-03-11","cited_by_count":12},{"id":"2402.06092","title":"CLIP-Loc: Multi-modal Landmark Association for Global Localization in Object-based Maps","created":"2024-02-08","cited_by_count":8},{"id":"2011.10452","title":"Bridging Scene Understanding and Task Execution with Flexible Simulation Environments","created":"2020-11-20","cited_by_count":3}],"next_cursor":null}