{"list":"other","total":59,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"1906.05797","title":"The Replica Dataset: A Digital Replica of Indoor Spaces","created":"2019-06-13","cited_by_count":904},{"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":"1612.03716","title":"COCO-Stuff: Thing and Stuff Classes in Context","created":"2016-12-12","cited_by_count":864},{"id":"1801.00868","title":"Panoptic Segmentation","created":"2018-01-03","cited_by_count":802},{"id":"2308.11417","title":"ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes","created":"2023-08-22","cited_by_count":764},{"id":"2303.09553","title":"LERF: Language Embedded Radiance Fields","created":"2023-03-16","cited_by_count":543},{"id":"1912.08830","title":"ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language","created":"2019-12-18","cited_by_count":452},{"id":"2309.16650","title":"ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning","created":"2023-09-28","cited_by_count":365},{"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":"2210.03105","title":"Mask3D: Mask Transformer for 3D Semantic Instance Segmentation","created":"2022-10-06","cited_by_count":303},{"id":"2212.05171","title":"ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding","created":"2022-12-10","cited_by_count":267},{"id":"2204.07761","title":"Language-Grounded Indoor 3D Semantic Segmentation in the Wild","created":"2022-04-16","cited_by_count":246},{"id":"2310.06773","title":"Uni3D: Exploring Unified 3D Representation at Scale","created":"2023-10-10","cited_by_count":237},{"id":"2112.14757","title":"A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model","created":"2021-12-29","cited_by_count":223},{"id":"2012.02206","title":"Scan2Cap: Context-aware Dense Captioning in RGB-D Scans","created":"2020-12-03","cited_by_count":218},{"id":"1812.07003","title":"3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans","created":"2018-12-17","cited_by_count":217},{"id":"2308.04352","title":"3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment","created":"2023-08-08","cited_by_count":204},{"id":"2403.17846","title":"Hierarchical Open-Vocabulary 3D Scene Graphs for Language-Grounded Robot Navigation","created":"2024-03-26","cited_by_count":196},{"id":"2003.06537","title":"OccuSeg: Occupancy-aware 3D Instance Segmentation","created":"2020-03-14","cited_by_count":177},{"id":"2211.16312","title":"PLA: Language-Driven Open-Vocabulary 3D Scene Understanding","created":"2022-11-29","cited_by_count":177},{"id":"2306.15880","title":"Towards Open Vocabulary Learning: A Survey","created":"2023-06-28","cited_by_count":166},{"id":"2103.14898","title":"SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequences","created":"2021-03-27","cited_by_count":163},{"id":"1906.01140","title":"Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds","created":"2019-06-04","cited_by_count":156},{"id":"2101.06894","title":"Kimera: from SLAM to Spatial Perception with 3D Dynamic Scene Graphs","created":"2021-01-18","cited_by_count":144},{"id":"2309.12311","title":"LLM-Grounder: Open-Vocabulary 3D Visual Grounding with Large Language Model as an Agent","created":"2023-09-21","cited_by_count":135},{"id":"2108.02350","title":"Hierarchical Aggregation for 3D Instance Segmentation","created":"2021-08-05","cited_by_count":127},{"id":"2405.10370","title":"Grounded 3D-LLM with Referent Tokens","created":"2024-05-16","cited_by_count":115},{"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":"1804.04011","title":"QuadricSLAM: Dual Quadrics from Object Detections as Landmarks in Object-oriented SLAM","created":"2018-04-10","cited_by_count":86},{"id":"1902.09852","title":"Associatively Segmenting Instances and Semantics in Point Clouds","created":"2019-02-26","cited_by_count":86},{"id":"2309.00616","title":"OpenIns3D: Snap and Lookup for 3D Open-vocabulary Instance Segmentation","created":"2023-09-01","cited_by_count":82},{"id":"2404.13696","title":"Clio: Real-time Task-Driven Open-Set 3D Scene Graphs","created":"2024-04-21","cited_by_count":81},{"id":"1903.00268","title":"Volumetric Instance-Aware Semantic Mapping and 3D Object Discovery","created":"2019-03-01","cited_by_count":80},{"id":"1906.08650","title":"3D Instance Segmentation via Multi-Task Metric Learning","created":"2019-06-20","cited_by_count":80},{"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":"2302.01838","title":"vMAP: Vectorised Object Mapping for Neural Field SLAM","created":"2023-02-03","cited_by_count":67},{"id":"1812.07976","title":"MID-Fusion: Octree-based Object-Level Multi-Instance Dynamic SLAM","created":"2018-12-19","cited_by_count":65},{"id":"2307.09220","title":"A Survey on Open-Vocabulary Detection and Segmentation: Past, Present, and Future","created":"2023-07-18","cited_by_count":61},{"id":"2407.06192","title":"Multi-Object Hallucination in Vision-Language Models","created":"2024-07-08","cited_by_count":60},{"id":"2401.07745","title":"MaskClustering: View Consensus based Mask Graph Clustering for Open-Vocabulary 3D Instance Segmentation","created":"2024-01-15","cited_by_count":56},{"id":"2404.08767","title":"LLM-Seg: Bridging Image Segmentation and Large Language Model Reasoning","created":"2024-04-12","cited_by_count":52},{"id":"2309.02999","title":"Vote2Cap-DETR++: Decoupling Localization and Describing for End-to-End 3D Dense Captioning","created":"2023-09-06","cited_by_count":39},{"id":"2306.00977","title":"AGILE3D: Attention Guided Interactive Multi-object 3D Segmentation","created":"2023-06-01","cited_by_count":33},{"id":"1904.02199","title":"3D-BEVIS: Bird's-Eye-View Instance Segmentation","created":"2019-04-03","cited_by_count":17},{"id":"2103.16095","title":"Reconstructing Interactive 3D Scenes by Panoptic Mapping and CAD Model Alignments","created":"2021-03-30","cited_by_count":15},{"id":"2310.16383","title":"Open-NeRF: Towards Open Vocabulary NeRF Decomposition","created":"2023-10-25","cited_by_count":13},{"id":"2309.14737","title":"Volumetric Semantically Consistent 3D Panoptic Mapping","created":"2023-09-26","cited_by_count":10},{"id":"2304.05735","title":"RO-MAP: Real-Time Multi-Object Mapping with Neural Radiance Fields","created":"2023-04-12","cited_by_count":9},{"id":"2402.11141","title":"Semantically-aware Neural Radiance Fields for Visual Scene Understanding: A Comprehensive Review","created":"2024-02-17","cited_by_count":9}],"next_cursor":null}