{"list":"other","total":94,"rows":[{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1606.00915","title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","created":"2016-06-02","cited_by_count":3241},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"id":"1511.00561","title":"SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation","created":"2015-11-02","cited_by_count":1487},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"1612.08242","title":"YOLO9000: Better, Faster, Stronger","created":"2016-12-25","cited_by_count":1431},{"id":"1712.06584","title":"End-to-end Recovery of Human Shape and Pose","created":"2017-12-18","cited_by_count":885},{"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":"1607.08822","title":"SPICE: Semantic Propositional Image Caption Evaluation","created":"2016-07-29","cited_by_count":824},{"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":"1801.00868","title":"Panoptic Segmentation","created":"2018-01-03","cited_by_count":802},{"id":"1801.09847","title":"Open3D: A Modern Library for 3D Data Processing","created":"2018-01-30","cited_by_count":721},{"id":"1607.08128","title":"Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image","created":"2016-07-27","cited_by_count":695},{"id":"1909.12828","title":"Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop","created":"2019-09-27","cited_by_count":627},{"id":"1912.05656","title":"VIBE: Video Inference for Human Body Pose and Shape Estimation","created":"2019-12-11","cited_by_count":620},{"id":"1701.02426","title":"Scene Graph Generation by Iterative Message Passing","created":"2017-01-10","cited_by_count":462},{"id":"1708.03852","title":"VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimator","created":"2017-08-13","cited_by_count":423},{"id":"1606.05830","title":"Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Age","created":"2016-06-19","cited_by_count":411},{"id":"1608.00187","title":"Visual Relationship Detection with Language Priors","created":"2016-07-31","cited_by_count":334},{"id":"1511.03416","title":"Visual7W: Grounded Question Answering in Images","created":"2015-11-11","cited_by_count":318},{"id":"1908.06963","title":"Resolving 3D Human Pose Ambiguities with 3D Scene Constraints","created":"2019-08-20","cited_by_count":295},{"id":"1606.02147","title":"ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation","created":"2016-06-07","cited_by_count":291},{"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":"2001.07715","title":"TEASER: Fast and Certifiable Point Cloud Registration","created":"2020-01-21","cited_by_count":274},{"id":"1905.03244","title":"Convolutional Mesh Regression for Single-Image Human Shape Reconstruction","created":"2019-05-08","cited_by_count":270},{"id":"1606.01847","title":"Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding","created":"2016-06-06","cited_by_count":243},{"id":"1805.04092","title":"Learning to Estimate 3D Human Pose and Shape from a Single Color Image","created":"2018-05-10","cited_by_count":226},{"id":"2004.03967","title":"Learning 3D Semantic Scene Graphs from 3D Indoor Reconstructions","created":"2020-04-08","cited_by_count":208},{"id":"1701.02468","title":"Unite the People: Closing the Loop Between 3D and 2D Human Representations","created":"2017-01-10","cited_by_count":205},{"id":"1808.05942","title":"Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimation","created":"2018-08-17","cited_by_count":185},{"id":"1910.02490","title":"Kimera: an Open-Source Library for Real-Time Metric-Semantic Localization and Mapping","created":"2019-10-06","cited_by_count":184},{"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":"1704.03847","title":"Semantic3D.net: A new Large-scale Point Cloud Classification Benchmark","created":"2017-04-12","cited_by_count":158},{"id":"1707.09700","title":"Scene Graph Generation from Objects, Phrases and Region Captions","created":"2017-07-31","cited_by_count":154},{"id":"1704.03489","title":"CNN-SLAM: Real-time dense monocular SLAM with learned depth prediction","created":"2017-04-11","cited_by_count":152},{"id":"1611.03631","title":"Voxblox: Incremental 3D Euclidean Signed Distance Fields for On-Board MAV Planning","created":"2016-11-11","cited_by_count":150},{"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":"1609.05130","title":"SemanticFusion: Dense 3D Semantic Mapping with Convolutional Neural Networks","created":"2016-09-16","cited_by_count":135},{"id":"1806.05620","title":"DynaSLAM: Tracking, Mapping and Inpainting in Dynamic Scenes","created":"2018-06-14","cited_by_count":134},{"id":"1912.02923","title":"Generating 3D People in Scenes without People","created":"2019-12-05","cited_by_count":127},{"id":"1704.06857","title":"A Review on Deep Learning Techniques Applied to Semantic Segmentation","created":"2017-04-22","cited_by_count":122},{"id":"1604.01093","title":"BundleFusion: Real-time Globally Consistent 3D Reconstruction using On-the-fly Surface Re-integration","created":"2016-04-05","cited_by_count":116},{"id":"1702.08319","title":"Visual Translation Embedding Network for Visual Relation Detection","created":"2017-02-27","cited_by_count":112},{"id":"1805.01956","title":"Motion Planning Among Dynamic, Decision-Making Agents with Deep Reinforcement Learning","created":"2018-05-04","cited_by_count":111},{"id":"1905.04266","title":"Exploiting temporal context for 3D human pose estimation in the wild","created":"2019-05-10","cited_by_count":110},{"id":"1611.06607","title":"A Hierarchical Approach for Generating Descriptive Image Paragraphs","created":"2016-11-20","cited_by_count":104},{"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":"1512.02363","title":"On-Manifold Preintegration for Real-Time Visual-Inertial Odometry","created":"2015-12-08","cited_by_count":95},{"id":"1804.09194","title":"MaskFusion: Real-Time Recognition, Tracking and Reconstruction of Multiple Moving Objects","created":"2018-04-24","cited_by_count":95},{"id":"1807.11699","title":"SegStereo: Exploiting Semantic Information for Disparity Estimation","created":"2018-07-31","cited_by_count":88},{"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":"1612.07386","title":"SE-Sync: A Certifiably Correct Algorithm for Synchronization over the Special Euclidean Group","created":"2016-12-21","cited_by_count":80},{"id":"1903.00268","title":"Volumetric Instance-Aware Semantic Mapping and 3D Object Discovery","created":"2019-03-01","cited_by_count":80},{"id":"1603.08161","title":"VolumeDeform: Real-time Volumetric Non-rigid Reconstruction","created":"2016-03-27","cited_by_count":75},{"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":"1808.02201","title":"Holistic 3D Scene Parsing and Reconstruction from a Single RGB Image","created":"2018-08-07","cited_by_count":69},{"id":"1711.10370","title":"Learning to Segment Every Thing","created":"2017-11-28","cited_by_count":65},{"id":"1812.07976","title":"MID-Fusion: Octree-based Object-Level Multi-Instance Dynamic SLAM","created":"2018-12-19","cited_by_count":65},{"id":"1909.06121","title":"Dual Graph Convolutional Network for Semantic Segmentation","created":"2019-09-13","cited_by_count":59},{"id":"1907.12273","title":"Interlaced Sparse Self-Attention for Semantic Segmentation","created":"2019-07-29","cited_by_count":53},{"id":"1810.13049","title":"Cooperative Holistic Scene Understanding: Unifying 3D Object, Layout, and Camera Pose Estimation","created":"2018-10-31","cited_by_count":51},{"id":"1904.06504","title":"Visual-Inertial Mapping with Non-Linear Factor Recovery","created":"2019-04-13","cited_by_count":50},{"id":"2003.13743","title":"Combining detection and tracking for human pose estimation in videos","created":"2020-03-30","cited_by_count":49},{"id":"1706.06629","title":"Co-Fusion: Real-time Segmentation, Tracking and Fusion of Multiple Objects","created":"2017-06-20","cited_by_count":47},{"id":"2010.07820","title":"DynaSLAM II: Tightly-Coupled Multi-Object Tracking and SLAM","created":"2020-10-15","cited_by_count":47},{"id":"1701.02354","title":"MonoCap: Monocular Human Motion Capture using a CNN Coupled with a Geometric Prior","created":"2017-01-09","cited_by_count":36},{"id":"1803.11288","title":"FutureMapping: The Computational Structure of Spatial AI Systems","created":"2018-03-29","cited_by_count":36},{"id":"1804.00090","title":"FloorNet: A Unified Framework for Floorplan Reconstruction from 3D Scans","created":"2018-03-31","cited_by_count":35},{"id":"1803.02009","title":"MIS-SLAM: Real-time Large Scale Dense Deformable SLAM System in Minimal Invasive Surgery Based on Heterogeneous Computing","created":"2018-03-06","cited_by_count":30},{"id":"1703.03054","title":"Deep Variation-structured Reinforcement Learning for Visual Relationship and Attribute Detection","created":"2017-03-08","cited_by_count":28},{"id":"1807.02062","title":"Stereo Vision-based Semantic 3D Object and Ego-motion Tracking for Autonomous Driving","created":"2018-07-05","cited_by_count":26},{"id":"1812.01192","title":"Learning to Fuse Things and Stuff","created":"2018-12-04","cited_by_count":26},{"id":"2004.13154","title":"Voxgraph: Globally Consistent, Volumetric Mapping using Signed Distance Function Submaps","created":"2020-04-27","cited_by_count":26},{"id":"1704.00112","title":"Configurable 3D Scene Synthesis and 2D Image Rendering with Per-Pixel Ground Truth using Stochastic Grammars","created":"2017-04-01","cited_by_count":25},{"id":"1905.11377","title":"FlightGoggles: A Modular Framework for Photorealistic Camera, Exteroceptive Sensor, and Dynamics Simulation","created":"2019-05-27","cited_by_count":22},{"id":"1804.09557","title":"SegMap: 3D Segment Mapping using Data-Driven Descriptors","created":"2018-04-25","cited_by_count":21},{"id":"1911.11924","title":"In Perfect Shape: Certifiably Optimal 3D Shape Reconstruction from 2D Landmarks","created":"2019-11-27","cited_by_count":17},{"id":"1903.01067","title":"Incremental Visual-Inertial 3D Mesh Generation with Structural Regularities","created":"2019-03-04","cited_by_count":11},{"id":"1905.11068","title":"Value Iteration Networks on Multiple Levels of Abstraction","created":"2019-05-27","cited_by_count":11},{"id":"1906.07409","title":"Active Scene Understanding via Online Semantic Reconstruction","created":"2019-06-18","cited_by_count":11},{"id":"1906.07029","title":"Semi-Supervised Semantic Mapping through Label Propagation with Semantic Texture Meshes","created":"2019-06-17","cited_by_count":9},{"id":"1904.10324","title":"VITAMIN-E: VIsual Tracking And MappINg with Extremely Dense Feature Points","created":"2019-04-23","cited_by_count":8},{"id":"1803.04345","title":"Sparse 3D Topological Graphs for Micro-Aerial Vehicle Planning","created":"2018-03-12","cited_by_count":6},{"id":"1806.07889","title":"iMapper: Interaction-guided Joint Scene and Human Motion Mapping from Monocular Videos","created":"2018-06-20","cited_by_count":6},{"id":"1812.11866","title":"From Pixels to Buildings: End-to-end Probabilistic Deep Networks for Large-scale Semantic Mapping","created":"2018-12-31","cited_by_count":6},{"id":"2007.15107","title":"OrcVIO: Object residual constrained Visual-Inertial Odometry","created":"2020-07-29","cited_by_count":5},{"id":"1411.7460","title":"Fast Algorithms for the Maximum Clique Problem on Massive Graphs with Applications to Overlapping Community Detection","created":"2014-11-27","cited_by_count":4},{"id":"1712.01097","title":"Generalized Grounding Graphs: A Probabilistic Framework for Understanding Grounded Commands","created":"2017-11-29","cited_by_count":4},{"id":"1810.11689","title":"Accelerated Inference in Markov Random Fields via Smooth Riemannian Optimization","created":"2018-10-27","cited_by_count":3},{"id":"1910.00063","title":"Q-Search Trees: An Information-Theoretic Approach Towards Hierarchical Abstractions for Agents with Computational Limitations","created":"2019-09-30","cited_by_count":2},{"id":"2001.05422","title":"Indoor Layout Estimation by 2D LiDAR and Camera Fusion","created":"2020-01-15","cited_by_count":2}],"next_cursor":null}