{"list":"other","total":80,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2011.13961","title":"D-NeRF: Neural Radiance Fields for Dynamic Scenes","created":"2020-11-27","cited_by_count":1465},{"id":"1709.06158","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","created":"2017-09-18","cited_by_count":1376},{"id":"1711.07280","title":"Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments","created":"2017-11-20","cited_by_count":1027},{"id":"2312.12337","title":"pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction","created":"2023-12-19","cited_by_count":684},{"id":"2007.00643","title":"Object Goal Navigation using Goal-Oriented Semantic Exploration","created":"2020-07-01","cited_by_count":429},{"id":"2105.06468","title":"Dynamic View Synthesis from Dynamic Monocular Video","created":"2021-05-13","cited_by_count":420},{"id":"2103.15875","title":"In-Place Scene Labelling and Understanding with Implicit Scene Representation","created":"2021-03-29","cited_by_count":415},{"id":"2312.00732","title":"Gaussian Grouping: Segment and Edit Anything in 3D Scenes","created":"2023-12-01","cited_by_count":393},{"id":"2312.02126","title":"SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAM","created":"2023-12-04","cited_by_count":388},{"id":"2312.03203","title":"Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields","created":"2023-12-06","cited_by_count":364},{"id":"1806.02724","title":"Speaker-Follower Models for Vision-and-Language Navigation","created":"2018-06-07","cited_by_count":340},{"id":"1904.10151","title":"REVERIE: Remote Embodied Visual Referring Expression in Real Indoor Environments","created":"2019-04-23","cited_by_count":333},{"id":"2302.12251","title":"VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion","created":"2023-02-23","cited_by_count":313},{"id":"1811.10092","title":"Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation","created":"2018-11-25","cited_by_count":305},{"id":"2011.13922","title":"A Recurrent Vision-and-Language BERT for Navigation","created":"2020-11-26","cited_by_count":302},{"id":"2309.16585","title":"Text-to-3D using Gaussian Splatting","created":"2023-09-28","cited_by_count":299},{"id":"2311.11284","title":"LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching","created":"2023-11-19","cited_by_count":290},{"id":"2110.13309","title":"History Aware Multimodal Transformer for Vision-and-Language Navigation","created":"2021-10-25","cited_by_count":271},{"id":"1904.04195","title":"Learning to Navigate Unseen Environments: Back Translation with Environmental Dropout","created":"2019-04-08","cited_by_count":244},{"id":"2401.03890","title":"A Survey on 3D Gaussian Splatting","created":"2024-01-08","cited_by_count":224},{"id":"2105.06466","title":"Editing Conditional Radiance Fields","created":"2021-05-13","cited_by_count":222},{"id":"2311.18482","title":"Language Embedded 3D Gaussians for Open-Vocabulary Scene Understanding","created":"2023-11-30","cited_by_count":208},{"id":"2005.12256","title":"Neural Topological SLAM for Visual Navigation","created":"2020-05-25","cited_by_count":195},{"id":"2202.11742","title":"Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigation","created":"2022-02-23","cited_by_count":193},{"id":"1911.07883","title":"Vision-Language Navigation with Self-Supervised Auxiliary Reasoning Tasks","created":"2019-11-18","cited_by_count":179},{"id":"2304.03047","title":"ETPNav: Evolving Topological Planning for Vision-Language Navigation in Continuous Environments","created":"2023-04-06","cited_by_count":169},{"id":"2203.15224","title":"Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentation","created":"2022-03-29","cited_by_count":152},{"id":"2403.12722","title":"HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splatting","created":"2024-03-19","cited_by_count":142},{"id":"1905.12255","title":"Stay on the Path: Instruction Fidelity in Vision-and-Language Navigation","created":"2019-05-29","cited_by_count":130},{"id":"2104.00670","title":"Unconstrained Scene Generation with Locally Conditioned Radiance Fields","created":"2021-04-01","cited_by_count":130},{"id":"2108.09105","title":"Airbert: In-domain Pretraining for Vision-and-Language Navigation","created":"2021-08-20","cited_by_count":130},{"id":"2307.12907","title":"GridMM: Grid Memory Map for Vision-and-Language Navigation","created":"2023-07-24","cited_by_count":124},{"id":"2402.05408","title":"MIGC: Multi-Instance Generation Controller for Text-to-Image Synthesis","created":"2024-02-08","cited_by_count":124},{"id":"2212.04385","title":"BEVBert: Multimodal Map Pre-training for Language-guided Navigation","created":"2022-12-08","cited_by_count":122},{"id":"2107.04004","title":"3D Neural Scene Representations for Visuomotor Control","created":"2021-07-08","cited_by_count":111},{"id":"2008.09285","title":"Occupancy Anticipation for Efficient Exploration and Navigation","created":"2020-08-21","cited_by_count":106},{"id":"2010.09304","title":"Language and Visual Entity Relationship Graph for Agent Navigation","created":"2020-10-19","cited_by_count":100},{"id":"2103.03454","title":"Structured Scene Memory for Vision-Language Navigation","created":"2021-03-05","cited_by_count":95},{"id":"2203.05137","title":"Cross-modal Map Learning for Vision and Language Navigation","created":"2022-03-10","cited_by_count":91},{"id":"2310.11448","title":"4K4D: Real-Time 4D View Synthesis at 4K Resolution","created":"2023-10-17","cited_by_count":91},{"id":"1702.08360","title":"Neural Map: Structured Memory for Deep Reinforcement Learning","created":"2017-02-27","cited_by_count":90},{"id":"2210.07506","title":"Weakly-Supervised Multi-Granularity Map Learning for Vision-and-Language Navigation","created":"2022-10-14","cited_by_count":86},{"id":"2308.07498","title":"DREAMWALKER: Mental Planning for Continuous Vision-Language Navigation","created":"2023-08-14","cited_by_count":85},{"id":"2203.15685","title":"EnvEdit: Environment Editing for Vision-and-Language Navigation","created":"2022-03-29","cited_by_count":83},{"id":"2308.04758","title":"Bird's-Eye-View Scene Graph for Vision-Language Navigation","created":"2023-08-09","cited_by_count":72},{"id":"2007.05655","title":"Evolving Graphical Planner: Contextual Global Planning for Vision-and-Language Navigation","created":"2020-07-11","cited_by_count":71},{"id":"2106.07876","title":"Vision-Language Navigation with Random Environmental Mixup","created":"2021-06-15","cited_by_count":70},{"id":"2203.11591","title":"HOP: History-and-Order Aware Pre-training for Vision-and-Language Navigation","created":"2022-03-22","cited_by_count":70},{"id":"2312.03461","title":"HiFi4G: High-Fidelity Human Performance Rendering via Compact Gaussian Splatting","created":"2023-12-06","cited_by_count":70},{"id":"2404.01943","title":"Lookahead Exploration with Neural Radiance Representation for Continuous Vision-Language Navigation","created":"2024-04-02","cited_by_count":65},{"id":"2403.14158","title":"Volumetric Environment Representation for Vision-Language Navigation","created":"2024-03-21","cited_by_count":63},{"id":"2207.11201","title":"Target-Driven Structured Transformer Planner for Vision-Language Navigation","created":"2022-07-19","cited_by_count":58},{"id":"2007.08037","title":"Active Visual Information Gathering for Vision-Language Navigation","created":"2020-07-15","cited_by_count":55},{"id":"2110.14143","title":"SOAT: A Scene- and Object-Aware Transformer for Vision-and-Language Navigation","created":"2021-10-27","cited_by_count":53},{"id":"2203.16586","title":"Counterfactual Cycle-Consistent Learning for Instruction Following and Generation in Vision-Language Navigation","created":"2022-03-30","cited_by_count":51},{"id":"2303.00304","title":"Renderable Neural Radiance Map for Visual Navigation","created":"2023-03-01","cited_by_count":51},{"id":"2103.12944","title":"Scene-Intuitive Agent for Remote Embodied Visual Grounding","created":"2021-03-24","cited_by_count":49},{"id":"2108.06685","title":"Vector-Decomposed Disentanglement for Domain-Invariant Object Detection","created":"2021-08-15","cited_by_count":47},{"id":"2206.01634","title":"Reinforcement Learning with Neural Radiance Fields","created":"2022-06-03","cited_by_count":43},{"id":"2307.12335","title":"Learning Navigational Visual Representations with Semantic Map Supervision","created":"2023-07-23","cited_by_count":43},{"id":"2303.08409","title":"Lana: A Language-Capable Navigator for Instruction Following and Generation","created":"2023-03-15","cited_by_count":40},{"id":"2007.09841","title":"Seeing the Un-Scene: Learning Amodal Semantic Maps for Room Navigation","created":"2020-07-20","cited_by_count":34},{"id":"2203.16895","title":"Deformation and Correspondence Aware Unsupervised Synthetic-to-Real Scene Flow Estimation for Point Clouds","created":"2022-03-31","cited_by_count":28},{"id":"2202.07135","title":"Compositional Scene Representation Learning via Reconstruction: A Survey","created":"2022-02-15","cited_by_count":27},{"id":"2210.16822","title":"Towards Versatile Embodied Navigation","created":"2022-10-30","cited_by_count":26},{"id":"2412.20977","title":"UnrealZoo: Enriching Photo-realistic Virtual Worlds for Embodied AI","created":"2024-12-30","cited_by_count":25},{"id":"2404.09857","title":"Empowering Embodied Visual Tracking with Visual Foundation Models and Offline RL","created":"2024-04-15","cited_by_count":23},{"id":"2210.07505","title":"Learning Active Camera for Multi-Object Navigation","created":"2022-10-14","cited_by_count":21},{"id":"2407.07433","title":"Controllable Navigation Instruction Generation with Chain of Thought Prompting","created":"2024-07-10","cited_by_count":21},{"id":"2407.15087","title":"Navigation Instruction Generation with BEV Perception and Large Language Models","created":"2024-07-21","cited_by_count":21},{"id":"2503.14483","title":"Multi-view Reconstruction via SfM-guided Monocular Depth Estimation","created":"2025-03-18","cited_by_count":20},{"id":"2410.14250","title":"Vision-Language Navigation with Energy-Based Policy","created":"2024-10-18","cited_by_count":19},{"id":"2301.11520","title":"SNeRL: Semantic-aware Neural Radiance Fields for Reinforcement Learning","created":"2023-01-27","cited_by_count":16},{"id":"2311.13793","title":"Evidential Active Recognition: Intelligent and Prudent Open-World Embodied Perception","created":"2023-11-23","cited_by_count":15}],"next_cursor":null}