{"list":"other","total":90,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"id":"1709.06158","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","created":"2017-09-18","cited_by_count":1376},{"id":"1902.09630","title":"Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression","created":"2019-02-25","cited_by_count":1368},{"id":"2203.17270","title":"BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers","created":"2022-03-31","cited_by_count":1218},{"id":"1904.07850","title":"Objects as Points","created":"2019-04-16","cited_by_count":1175},{"id":"2008.05711","title":"Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D","created":"2020-08-13","cited_by_count":1044},{"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":"1809.01999","title":"Recurrent World Models Facilitate Policy Evolution","created":"2018-09-04","cited_by_count":785},{"id":"1611.08974","title":"Semantic Scene Completion from a Single Depth Image","created":"2016-11-28","cited_by_count":472},{"id":"2004.02857","title":"Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environments","created":"2020-04-06","cited_by_count":441},{"id":"2302.07817","title":"Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction","created":"2023-02-15","cited_by_count":409},{"id":"2003.08981","title":"Local Implicit Grid Representations for 3D Scenes","created":"2020-03-19","cited_by_count":373},{"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":"2304.14365","title":"Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Driving","created":"2023-04-27","cited_by_count":332},{"id":"2004.05155","title":"Learning to Explore using Active Neural SLAM","created":"2020-04-10","cited_by_count":316},{"id":"2303.09551","title":"SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving","created":"2023-03-16","cited_by_count":316},{"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":"2305.16986","title":"NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models","created":"2023-05-26","cited_by_count":280},{"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":"2002.10638","title":"Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-training","created":"2020-02-25","cited_by_count":231},{"id":"2306.02851","title":"Scene as Occupancy","created":"2023-06-05","cited_by_count":209},{"id":"2004.03967","title":"Learning 3D Semantic Scene Graphs from 3D Indoor Reconstructions","created":"2020-04-08","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":"2004.14973","title":"Improving Vision-and-Language Navigation with Image-Text Pairs from the Web","created":"2020-04-30","cited_by_count":177},{"id":"2304.03047","title":"ETPNav: Evolving Topological Planning for Vision-Language Navigation in Continuous Environments","created":"2023-04-06","cited_by_count":169},{"id":"2105.06453","title":"Episodic Transformer for Vision-and-Language Navigation","created":"2021-05-13","cited_by_count":156},{"id":"2312.16170","title":"EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI","created":"2023-12-26","cited_by_count":147},{"id":"2007.10323","title":"Pillar-based Object Detection for Autonomous Driving","created":"2020-07-20","cited_by_count":137},{"id":"1905.12255","title":"Stay on the Path: Instruction Fidelity in Vision-and-Language Navigation","created":"2019-05-29","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":"2209.05324","title":"Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipe","created":"2022-09-12","cited_by_count":122},{"id":"2212.04385","title":"BEVBert: Multimodal Map Pre-training for Language-guided Navigation","created":"2022-12-08","cited_by_count":122},{"id":"2308.06735","title":"AerialVLN: Vision-and-Language Navigation for UAVs","created":"2023-08-13","cited_by_count":121},{"id":"2105.08756","title":"Pathdreamer: A World Model for Indoor Navigation","created":"2021-05-18","cited_by_count":118},{"id":"2203.12667","title":"Vision-and-Language Navigation: A Survey of Tasks, Methods, and Future Directions","created":"2022-03-22","cited_by_count":117},{"id":"2307.15644","title":"Scaling Data Generation in Vision-and-Language Navigation","created":"2023-07-28","cited_by_count":117},{"id":"2012.05292","title":"Topological Planning with Transformers for Vision-and-Language Navigation","created":"2020-12-09","cited_by_count":116},{"id":"2306.10013","title":"PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentation","created":"2023-06-16","cited_by_count":115},{"id":"2107.04004","title":"3D Neural Scene Representations for Visuomotor Control","created":"2021-07-08","cited_by_count":111},{"id":"2010.09304","title":"Language and Visual Entity Relationship Graph for Agent Navigation","created":"2020-10-19","cited_by_count":100},{"id":"1803.08999","title":"LayoutNet: Reconstructing the 3D Room Layout from a Single RGB Image","created":"2018-03-23","cited_by_count":95},{"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":"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":"2305.19195","title":"PanoGen: Text-Conditioned Panoramic Environment Generation for Vision-and-Language Navigation","created":"2023-05-30","cited_by_count":77},{"id":"2103.07466","title":"3D Semantic Scene Completion: a Survey","created":"2021-03-12","cited_by_count":74},{"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":"1907.05091","title":"Efficient Semantic Scene Completion Network with Spatial Group Convolution","created":"2019-07-11","cited_by_count":66},{"id":"2308.07997","title":"$A^2$Nav: Action-Aware Zero-Shot Robot Navigation by Exploiting Vision-and-Language Ability of Foundation Models","created":"2023-08-15","cited_by_count":62},{"id":"2210.03112","title":"A New Path: Scaling Vision-and-Language Navigation with Synthetic Instructions and Imitation Learning","created":"2022-10-06","cited_by_count":60},{"id":"2010.01191","title":"Semantic MapNet: Building Allocentric Semantic Maps and Representations from Egocentric Views","created":"2020-10-02","cited_by_count":58},{"id":"2207.11201","title":"Target-Driven Structured Transformer Planner for Vision-Language Navigation","created":"2022-07-19","cited_by_count":58},{"id":"2101.00443","title":"Semantics for Robotic Mapping, Perception and Interaction: A Survey","created":"2021-01-02","cited_by_count":56},{"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":"2208.11781","title":"Learning from Unlabeled 3D Environments for Vision-and-Language Navigation","created":"2022-08-24","cited_by_count":50},{"id":"2103.12944","title":"Scene-Intuitive Agent for Remote Embodied Visual Grounding","created":"2021-03-24","cited_by_count":49},{"id":"2108.11945","title":"SASRA: Semantically-aware Spatio-temporal Reasoning Agent for Vision-and-Language Navigation in Continuous Environments","created":"2021-08-26","cited_by_count":48},{"id":"2108.06685","title":"Vector-Decomposed Disentanglement for Domain-Invariant Object Detection","created":"2021-08-15","cited_by_count":47},{"id":"2307.12335","title":"Learning Navigational Visual Representations with Semantic Map Supervision","created":"2023-07-23","cited_by_count":43},{"id":"1907.02022","title":"Chasing Ghosts: Instruction Following as Bayesian State Tracking","created":"2019-07-03","cited_by_count":41},{"id":"2303.08409","title":"Lana: A Language-Capable Navigator for Instruction Following and Generation","created":"2023-03-15","cited_by_count":40},{"id":"2011.01968","title":"Learning 3D Dynamic Scene Representations for Robot Manipulation","created":"2020-11-03","cited_by_count":39},{"id":"2210.16822","title":"Towards Versatile Embodied Navigation","created":"2022-10-30","cited_by_count":26},{"id":"2305.17102","title":"GeoVLN: Learning Geometry-Enhanced Visual Representation with Slot Attention for Vision-and-Language Navigation","created":"2023-05-26","cited_by_count":24},{"id":"2307.13510","title":"HeightFormer: Explicit Height Modeling without Extra Data for Camera-only 3D Object Detection in Bird's Eye View","created":"2023-07-25","cited_by_count":19},{"id":"2308.10306","title":"Omnidirectional Information Gathering for Knowledge Transfer-based Audio-Visual Navigation","created":"2023-08-20","cited_by_count":19},{"id":"1304.1098","title":"Occupancy Grids: A Stochastic Spatial Representation for Active Robot Perception","created":"2013-03-27","cited_by_count":10},{"id":"2201.10788","title":"Self-supervised 3D Semantic Representation Learning for Vision-and-Language Navigation","created":"2022-01-26","cited_by_count":6}],"next_cursor":null}