{"list":"other","total":59,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1612.00593","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","created":"2016-12-02","cited_by_count":5248},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"1412.2306","title":"Deep Visual-Semantic Alignments for Generating Image Descriptions","created":"2014-12-07","cited_by_count":968},{"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":"1505.00880","title":"Multi-view Convolutional Neural Networks for 3D Shape Recognition","created":"2015-05-05","cited_by_count":565},{"id":"1908.04616","title":"Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data","created":"2019-08-13","cited_by_count":532},{"id":"1701.02426","title":"Scene Graph Generation by Iterative Message Passing","created":"2017-01-10","cited_by_count":462},{"id":"1608.00187","title":"Visual Relationship Detection with Language Priors","created":"2016-07-31","cited_by_count":334},{"id":"1804.01622","title":"Image Generation from Scene Graphs","created":"2018-04-04","cited_by_count":324},{"id":"1808.00191","title":"Graph R-CNN for Scene Graph Generation","created":"2018-08-01","cited_by_count":298},{"id":"2103.02603","title":"Towards Open World Object Detection","created":"2021-03-03","cited_by_count":297},{"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":"1612.00496","title":"3D Bounding Box Estimation Using Deep Learning and Geometry","created":"2016-12-01","cited_by_count":278},{"id":"2004.03967","title":"Learning 3D Semantic Scene Graphs from 3D Indoor Reconstructions","created":"2020-04-08","cited_by_count":208},{"id":"1908.06109","title":"RIO: 3D Object Instance Re-Localization in Changing Indoor Environments","created":"2019-08-16","cited_by_count":188},{"id":"2201.13360","title":"Hydra: A Real-time Spatial Perception System for 3D Scene Graph Construction and Optimization","created":"2022-01-31","cited_by_count":178},{"id":"2002.12212","title":"Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image","created":"2020-02-27","cited_by_count":172},{"id":"2103.14898","title":"SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequences","created":"2021-03-27","cited_by_count":163},{"id":"2002.06289","title":"3D Dynamic Scene Graphs: Actionable Spatial Perception with Places, Objects, and Humans","created":"2020-02-15","cited_by_count":144},{"id":"2101.06894","title":"Kimera: from SLAM to Spatial Perception with 3D Dynamic Scene Graphs","created":"2021-01-18","cited_by_count":144},{"id":"1609.05130","title":"SemanticFusion: Dense 3D Semantic Mapping with Convolutional Neural Networks","created":"2016-09-16","cited_by_count":135},{"id":"2007.09548","title":"Kinematic 3D Object Detection in Monocular Video","created":"2020-07-19","cited_by_count":116},{"id":"1806.00557","title":"CubeSLAM: Monocular 3D Object SLAM","created":"2018-06-01","cited_by_count":102},{"id":"1904.00560","title":"Scene Graph Generation with External Knowledge and Image Reconstruction","created":"2019-04-01","cited_by_count":102},{"id":"2105.11320","title":"SuMa++: Efficient LiDAR-based Semantic SLAM","created":"2021-05-24","cited_by_count":100},{"id":"1808.08378","title":"Fusion++: Volumetric Object-Level SLAM","created":"2018-08-25","cited_by_count":98},{"id":"1903.01177","title":"PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things","created":"2019-03-04","cited_by_count":98},{"id":"1804.09194","title":"MaskFusion: Real-Time Recognition, Tracking and Reconstruction of Multiple Moving Objects","created":"2018-04-24","cited_by_count":95},{"id":"2103.06422","title":"Holistic 3D Scene Understanding from a Single Image with Implicit Representation","created":"2021-03-11","cited_by_count":94},{"id":"2012.00720","title":"Fully Convolutional Networks for Panoptic Segmentation","created":"2020-12-01","cited_by_count":92},{"id":"1804.04011","title":"QuadricSLAM: Dual Quadrics from Object Detections as Landmarks in Object-oriented SLAM","created":"2018-04-10","cited_by_count":86},{"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":"1903.10658","title":"Unpaired Image Captioning via Scene Graph Alignments","created":"2019-03-26","cited_by_count":82},{"id":"2004.03677","title":"Semantic Image Manipulation Using Scene Graphs","created":"2020-04-07","cited_by_count":82},{"id":"1903.00268","title":"Volumetric Instance-Aware Semantic Mapping and 3D Object Discovery","created":"2019-03-01","cited_by_count":80},{"id":"1811.10742","title":"Joint Monocular 3D Vehicle Detection and Tracking","created":"2018-11-26","cited_by_count":77},{"id":"1908.04929","title":"3-D Scene Graph: A Sparse and Semantic Representation of Physical Environments for Intelligent Agents","created":"2019-08-14","cited_by_count":74},{"id":"2107.14228","title":"Open-World Entity Segmentation","created":"2021-07-29","cited_by_count":74},{"id":"2109.02227","title":"Learning to Generate Scene Graph from Natural Language Supervision","created":"2021-09-06","cited_by_count":64},{"id":"2103.16083","title":"Fully Convolutional Scene Graph Generation","created":"2021-03-30","cited_by_count":57},{"id":"2108.01176","title":"Hierarchical Representations and Explicit Memory: Learning Effective Navigation Policies on 3D Scene Graphs using Graph Neural Networks","created":"2021-08-02","cited_by_count":52},{"id":"1803.08103","title":"A Unified Framework for Multi-View Multi-Class Object Pose Estimation","created":"2018-03-21","cited_by_count":49},{"id":"2203.11937","title":"4D-OR: Semantic Scene Graphs for OR Domain Modeling","created":"2022-03-22","cited_by_count":49},{"id":"2003.06233","title":"Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation","created":"2020-03-13","cited_by_count":40},{"id":"1807.05933","title":"Visual Graphs from Motion (VGfM): Scene understanding with object geometry reasoning","created":"2018-07-16","cited_by_count":27},{"id":"2004.12730","title":"EAO-SLAM: Monocular Semi-Dense Object SLAM Based on Ensemble Data Association","created":"2020-04-27","cited_by_count":24},{"id":"2108.05884","title":"Unconditional Scene Graph Generation","created":"2021-08-12","cited_by_count":22},{"id":"2108.10165","title":"ODAM: Object Detection, Association, and Mapping using Posed RGB Video","created":"2021-08-23","cited_by_count":22},{"id":"1804.00257","title":"Real-time Progressive 3D Semantic Segmentation for Indoor Scene","created":"2018-04-01","cited_by_count":18},{"id":"2012.05360","title":"MOLTR: Multiple Object Localisation, Tracking, and Reconstruction from Monocular RGB Videos","created":"2020-12-09","cited_by_count":18},{"id":"1804.09111","title":"Structure Aware SLAM using Quadrics and Planes","created":"2018-04-24","cited_by_count":17},{"id":"2108.07084","title":"Learning Canonical View Representation for 3D Shape Recognition with Arbitrary Views","created":"2021-08-16","cited_by_count":9},{"id":"2003.12735","title":"Exploit Clues from Views: Self-Supervised and Regularized Learning for Multiview Object Recognition","created":"2020-03-28","cited_by_count":6},{"id":"2106.15309","title":"Multimodal Semantic Scene Graphs for Holistic Modeling of Surgical Procedures","created":"2021-06-09","cited_by_count":6}],"next_cursor":null}