{"list":"other","total":141,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1612.00593","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","created":"2016-12-02","cited_by_count":5248},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1709.06158","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","created":"2017-09-18","cited_by_count":1376},{"id":"1906.05797","title":"The Replica Dataset: A Digital Replica of Indoor Spaces","created":"2019-06-13","cited_by_count":904},{"id":"1712.05474","title":"AI2-THOR: An Interactive 3D Environment for Visual AI","created":"2017-12-14","cited_by_count":869},{"id":"2308.11417","title":"ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes","created":"2023-08-22","cited_by_count":764},{"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":"2303.09553","title":"LERF: Language Embedded Radiance Fields","created":"2023-03-16","cited_by_count":543},{"id":"2401.17270","title":"YOLO-World: Real-Time Open-Vocabulary Object Detection","created":"2024-01-30","cited_by_count":503},{"id":"1808.10654","title":"Gibson Env: Real-World Perception for Embodied Agents","created":"2018-08-31","cited_by_count":481},{"id":"1912.08830","title":"ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language","created":"2019-12-18","cited_by_count":452},{"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":"2206.06994","title":"ProcTHOR: Large-Scale Embodied AI Using Procedural Generation","created":"2022-06-14","cited_by_count":380},{"id":"2309.16650","title":"ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning","created":"2023-09-28","cited_by_count":365},{"id":"2306.03514","title":"Recognize Anything: A Strong Image Tagging Model","created":"2023-06-06","cited_by_count":309},{"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":"2004.03967","title":"Learning 3D Semantic Scene Graphs from 3D Indoor Reconstructions","created":"2020-04-08","cited_by_count":208},{"id":"2212.08333","title":"AnyGrasp: Robust and Efficient Grasp Perception in Spatial and Temporal Domains","created":"2022-12-16","cited_by_count":208},{"id":"2403.17846","title":"Hierarchical Open-Vocabulary 3D Scene Graphs for Language-Grounded Robot Navigation","created":"2024-03-26","cited_by_count":196},{"id":"2004.06799","title":"RoboTHOR: An Open Simulation-to-Real Embodied AI Platform","created":"2020-04-14","cited_by_count":193},{"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":"2103.14898","title":"SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequences","created":"2021-03-27","cited_by_count":163},{"id":"2012.02924","title":"iGibson 1.0: a Simulation Environment for Interactive Tasks in Large Realistic Scenes","created":"2020-12-05","cited_by_count":155},{"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":"2104.01111","title":"A Comprehensive Survey of Scene Graphs: Generation and Application","created":"2021-03-17","cited_by_count":125},{"id":"2410.08189","title":"SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigation","created":"2024-10-10","cited_by_count":109},{"id":"2309.07970","title":"Language Embedded Radiance Fields for Zero-Shot Task-Oriented Grasping","created":"2023-09-14","cited_by_count":91},{"id":"2510.07077","title":"Vision-Language-Action Models for Robotics: A Review Towards Real-World Applications","created":"2025-10-08","cited_by_count":84},{"id":"2404.13696","title":"Clio: Real-time Task-Driven Open-Set 3D Scene Graphs","created":"2024-04-21","cited_by_count":81},{"id":"2402.12259","title":"Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationships","created":"2024-02-19","cited_by_count":80},{"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":"2403.15941","title":"Explore until Confident: Efficient Exploration for Embodied Question Answering","created":"2024-03-23","cited_by_count":74},{"id":"2201.00443","title":"Scene Graph Generation: A Comprehensive Survey","created":"2022-01-03","cited_by_count":73},{"id":"2403.08605","title":"Language-Grounded Dynamic Scene Graphs for Interactive Object Search with Mobile Manipulation","created":"2024-03-13","cited_by_count":70},{"id":"2405.00915","title":"EchoScene: Indoor Scene Generation via Information Echo over Scene Graph Diffusion","created":"2024-05-02","cited_by_count":67},{"id":"2409.13682","title":"ReMEmbR: Building and Reasoning Over Long-Horizon Spatio-Temporal Memory for Robot Navigation","created":"2024-09-20","cited_by_count":67},{"id":"2509.07996","title":"3D and 4D World Modeling: A Survey","created":"2025-09-04","cited_by_count":67},{"id":"2207.00254","title":"A Survey on Active Simultaneous Localization and Mapping: State of the Art and New Frontiers","created":"2022-07-01","cited_by_count":66},{"id":"2207.05006","title":"TASKOGRAPHY: Evaluating robot task planning over large 3D scene graphs","created":"2022-07-11","cited_by_count":59},{"id":"2503.10630","title":"UniGoal: Towards Universal Zero-shot Goal-oriented Navigation","created":"2025-03-13","cited_by_count":57},{"id":"2101.00443","title":"Semantics for Robotic Mapping, Perception and Interaction: A Survey","created":"2021-01-02","cited_by_count":56},{"id":"2503.19199","title":"Open-Vocabulary Functional 3D Scene Graphs for Real-World Indoor Spaces","created":"2025-03-24","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":"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":"2103.05558","title":"Exploiting Edge-Oriented Reasoning for 3D Point-based Scene Graph Analysis","created":"2021-03-09","cited_by_count":49},{"id":"2402.15487","title":"RoboEXP: Action-Conditioned Scene Graph via Interactive Exploration for Robotic Manipulation","created":"2024-02-23","cited_by_count":48},{"id":"2409.18313","title":"Embodied-RAG: General Non-parametric Embodied Memory for Retrieval and Generation","created":"2024-09-26","cited_by_count":44},{"id":"2303.14408","title":"VL-SAT: Visual-Linguistic Semantics Assisted Training for 3D Semantic Scene Graph Prediction in Point Cloud","created":"2023-03-25","cited_by_count":43},{"id":"2405.10255","title":"When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Models","created":"2024-05-16","cited_by_count":43},{"id":"2410.11989","title":"Dynamic Open-Vocabulary 3D Scene Graphs for Long-term Language-Guided Mobile Manipulation","created":"2024-10-15","cited_by_count":39},{"id":"2412.14480","title":"GraphEQA: Using 3D Semantic Scene Graphs for Real-time Embodied Question Answering","created":"2024-12-19","cited_by_count":37},{"id":"2402.13817","title":"Khronos: A Unified Approach for Spatio-Temporal Metric-Semantic SLAM in Dynamic Environments","created":"2024-02-21","cited_by_count":36},{"id":"2309.06635","title":"Collaborative Dynamic 3D Scene Graphs for Automated Driving","created":"2023-09-12","cited_by_count":34},{"id":"2309.15940","title":"Context-Aware Entity Grounding with Open-Vocabulary 3D Scene Graphs","created":"2023-09-27","cited_by_count":33},{"id":"2404.03275","title":"DELTA: Decomposed Efficient Long-Term Robot Task Planning using Large Language Models","created":"2024-04-04","cited_by_count":33},{"id":"2405.21066","title":"Mixed Diffusion for 3D Indoor Scene Synthesis","created":"2024-05-31","cited_by_count":32},{"id":"2406.07113","title":"Beyond Bare Queries: Open-Vocabulary Object Grounding with 3D Scene Graph","created":"2024-06-11","cited_by_count":32},{"id":"2304.14880","title":"SGAligner : 3D Scene Alignment with Scene Graphs","created":"2023-04-28","cited_by_count":30},{"id":"2404.00469","title":"SceneGraphLoc: Cross-Modal Coarse Visual Localization on 3D Scene Graphs","created":"2024-03-30","cited_by_count":29},{"id":"2212.11770","title":"S-Graphs+: Real-time Localization and Mapping leveraging Hierarchical Representations","created":"2022-12-22","cited_by_count":28},{"id":"2303.11048","title":"SGFormer: Semantic Graph Transformer for Point Cloud-based 3D Scene Graph Generation","created":"2023-03-20","cited_by_count":27},{"id":"2309.09182","title":"Optimal Scene Graph Planning with Large Language Model Guidance","created":"2023-09-17","cited_by_count":27},{"id":"2412.18450","title":"3DGraphLLM: Combining Semantic Graphs and Large Language Models for 3D Scene Understanding","created":"2024-12-24","cited_by_count":27},{"id":"2312.11713","title":"Indoor and Outdoor 3D Scene Graph Generation via Language-Enabled Spatial Ontologies","created":"2023-12-18","cited_by_count":25},{"id":"2209.07896","title":"3D VSG: Long-term Semantic Scene Change Prediction through 3D Variable Scene Graphs","created":"2022-09-16","cited_by_count":24},{"id":"2503.07909","title":"FunGraph: Functionality Aware 3D Scene Graphs for Language-Prompted Scene Interaction","created":"2025-03-10","cited_by_count":23},{"id":"2403.09412","title":"OpenGraph: Open-Vocabulary Hierarchical 3D Graph Representation in Large-Scale Outdoor Environments","created":"2024-03-14","cited_by_count":22},{"id":"2202.12197","title":"Situational Graphs for Robot Navigation in Structured Indoor Environments","created":"2022-02-24","cited_by_count":21},{"id":"2304.13487","title":"Hydra-Multi: Collaborative Online Construction of 3D Scene Graphs with Multi-Robot Teams","created":"2023-04-26","cited_by_count":21},{"id":"2309.15702","title":"SGRec3D: Self-Supervised 3D Scene Graph Learning via Object-Level Scene Reconstruction","created":"2023-09-27","cited_by_count":21},{"id":"2310.16494","title":"Lang3DSG: Language-based contrastive pre-training for 3D Scene Graph prediction","created":"2023-10-25","cited_by_count":19},{"id":"2512.00565","title":"Describe Anything Anywhere At Any Moment","created":"2025-11-29","cited_by_count":19},{"id":"2211.15501","title":"Proactive Robot Assistance via Spatio-Temporal Object Modeling","created":"2022-11-28","cited_by_count":18},{"id":"2103.05041","title":"Advances in Inference and Representation for Simultaneous Localization and Mapping","created":"2021-03-08","cited_by_count":16},{"id":"2412.13652","title":"RelationField: Relate Anything in Radiance Fields","created":"2024-12-18","cited_by_count":16},{"id":"2404.14565","title":"\"Where am I?\" Scene Retrieval with Language","created":"2024-04-22","cited_by_count":15},{"id":"2405.00552","title":"Long-Term Human Trajectory Prediction using 3D Dynamic Scene Graphs","created":"2024-05-01","cited_by_count":15},{"id":"2508.04678","title":"Open Scene Graphs for Open-World Object-Goal Navigation","created":"2025-08-06","cited_by_count":14},{"id":"2403.08094","title":"Task and Motion Planning in Hierarchical 3D Scene Graphs","created":"2024-03-12","cited_by_count":12},{"id":"2503.15005","title":"Universal Scene Graph Generation","created":"2025-03-19","cited_by_count":11},{"id":"2602.16356","title":"Articulated 3D Scene Graphs for Open-World Mobile Manipulation","created":"2026-02-18","cited_by_count":11},{"id":"2411.19162","title":"Lost & Found: Tracking Changes from Egocentric Observations in 3D Dynamic Scene Graphs","created":"2024-11-28","cited_by_count":10},{"id":"2507.19993","title":"FROSS: Faster-than-Real-Time Online 3D Semantic Scene Graph Generation from RGB-D Images","created":"2025-07-26","cited_by_count":10},{"id":"2510.01049","title":"KeySG: Hierarchical Keyframe-Based 3D Scene Graphs","created":"2025-10-01","cited_by_count":10},{"id":"2410.06108","title":"ConceptAgent: LLM-Driven Precondition Grounding and Tree Search for Robust Task Planning and Execution","created":"2024-10-08","cited_by_count":8},{"id":"2503.04034","title":"GaussianGraph: 3D Gaussian-based Scene Graph Generation for Open-world Scene Understanding","created":"2025-03-06","cited_by_count":8},{"id":"2503.17406","title":"IRef-VLA: A Benchmark for Interactive Referential Grounding with Imperfect Language in 3D Scenes","created":"2025-03-20","cited_by_count":8},{"id":"2504.06553","title":"ASHiTA: Automatic Scene-grounded HIerarchical Task Analysis","created":"2025-04-09","cited_by_count":8},{"id":"2502.15309","title":"DynamicGSG: Dynamic 3D Gaussian Scene Graphs for Environment Adaptation","created":"2025-02-21","cited_by_count":7},{"id":"2506.07454","title":"Language-Grounded Hierarchical Planning and Execution with Multi-Robot 3D Scene Graphs","created":"2025-06-09","cited_by_count":6},{"id":"2508.06990","title":"Imaginative World Modeling with Scene Graphs for Embodied Agent Navigation","created":"2025-08-09","cited_by_count":6},{"id":"2603.28732","title":"Pandora: Articulated 3D Scene Graphs from Egocentric Vision","created":"2026-03-30","cited_by_count":6}],"next_cursor":"100"}