{"list":"other","total":132,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"1612.00837","title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","created":"2016-12-02","cited_by_count":2516},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"1904.08920","title":"Towards VQA Models That Can Read","created":"2019-04-18","cited_by_count":1718},{"id":"2007.14062","title":"Big Bird: Transformers for Longer Sequences","created":"2020-07-28","cited_by_count":1684},{"id":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"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":"1709.06158","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","created":"2017-09-18","cited_by_count":1376},{"id":"2010.03768","title":"ALFWorld: Aligning Text and Embodied Environments for Interactive Learning","created":"2020-10-08","cited_by_count":1205},{"id":"1901.07291","title":"Cross-lingual Language Model Pretraining","created":"2019-01-22","cited_by_count":1090},{"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":"1908.08530","title":"VL-BERT: Pre-training of Generic Visual-Linguistic Representations","created":"2019-08-22","cited_by_count":954},{"id":"1712.05474","title":"AI2-THOR: An Interactive 3D Environment for Visual AI","created":"2017-12-14","cited_by_count":869},{"id":"1912.01734","title":"ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks","created":"2019-12-03","cited_by_count":783},{"id":"1405.4053","title":"Distributed Representations of Sentences and Documents","created":"2014-05-16","cited_by_count":678},{"id":"1906.00295","title":"Multimodal Transformer for Unaligned Multimodal Language Sequences","created":"2019-06-01","cited_by_count":645},{"id":"1811.10830","title":"From Recognition to Cognition: Visual Commonsense Reasoning","created":"2018-11-27","cited_by_count":556},{"id":"1705.05065","title":"AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles","created":"2017-05-15","cited_by_count":523},{"id":"2004.02984","title":"MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices","created":"2020-04-06","cited_by_count":482},{"id":"2004.02857","title":"Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environments","created":"2020-04-06","cited_by_count":441},{"id":"2010.07954","title":"Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding","created":"2020-10-15","cited_by_count":414},{"id":"1609.05143","title":"Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning","created":"2016-09-16","cited_by_count":366},{"id":"2210.05714","title":"Visual Language Maps for Robot Navigation","created":"2022-10-11","cited_by_count":365},{"id":"1911.00357","title":"DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames","created":"2019-11-01","cited_by_count":362},{"id":"1806.02724","title":"Speaker-Follower Models for Vision-and-Language Navigation","created":"2018-06-07","cited_by_count":340},{"id":"1711.11543","title":"Embodied Question Answering","created":"2017-11-30","cited_by_count":336},{"id":"1904.10151","title":"REVERIE: Remote Embodied Visual Referring Expression in Real Indoor Environments","created":"2019-04-23","cited_by_count":333},{"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":"2110.13309","title":"History Aware Multimodal Transformer for Vision-and-Language Navigation","created":"2021-10-25","cited_by_count":271},{"id":"1907.04957","title":"Vision-and-Dialog Navigation","created":"2019-07-10","cited_by_count":250},{"id":"1810.08272","title":"BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning","created":"2018-10-18","cited_by_count":244},{"id":"1904.04195","title":"Learning to Navigate Unseen Environments: Back Translation with Environmental Dropout","created":"2019-04-08","cited_by_count":244},{"id":"1811.12354","title":"Touchdown: Natural Language Navigation and Spatial Reasoning in Visual Street Environments","created":"2018-11-29","cited_by_count":239},{"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":"2110.00534","title":"TEACh: Task-driven Embodied Agents that Chat","created":"2021-10-01","cited_by_count":197},{"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":"1901.03035","title":"Self-Monitoring Navigation Agent via Auxiliary Progress Estimation","created":"2019-01-10","cited_by_count":176},{"id":"1909.10838","title":"Talk2Car: Taking Control of Your Self-Driving Car","created":"2019-09-24","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":"2108.09105","title":"Airbert: In-domain Pretraining for Vision-and-Language Navigation","created":"2021-08-20","cited_by_count":130},{"id":"1911.08670","title":"MMTM: Multimodal Transfer Module for CNN Fusion","created":"2019-11-20","cited_by_count":129},{"id":"2110.02207","title":"Waypoint Models for Instruction-guided Navigation in Continuous Environments","created":"2021-10-05","cited_by_count":129},{"id":"2307.12907","title":"GridMM: Grid Memory Map for Vision-and-Language Navigation","created":"2023-07-24","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":"2103.17138","title":"SOON: Scenario Oriented Object Navigation with Graph-based Exploration","created":"2021-03-31","cited_by_count":119},{"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":"1801.02209","title":"Building Generalizable Agents with a Realistic and Rich 3D Environment","created":"2018-01-07","cited_by_count":109},{"id":"1907.05446","title":"General Evaluation for Instruction Conditioned Navigation using Dynamic Time Warping","created":"2019-07-11","cited_by_count":105},{"id":"1804.00168","title":"Learning to Navigate in Cities Without a Map","created":"2018-03-31","cited_by_count":104},{"id":"1904.03461","title":"Embodied Question Answering in Photorealistic Environments with Point Cloud Perception","created":"2019-04-06","cited_by_count":103},{"id":"1809.00786","title":"Mapping Instructions to Actions in 3D Environments with Visual Goal Prediction","created":"2018-09-04","cited_by_count":101},{"id":"1909.01871","title":"Help, Anna! Visual Navigation with Natural Multimodal Assistance via Retrospective Curiosity-Encouraging Imitation Learning","created":"2019-09-04","cited_by_count":100},{"id":"2010.09304","title":"Language and Visual Entity Relationship Graph for Agent Navigation","created":"2020-10-19","cited_by_count":100},{"id":"2004.02788","title":"Self-Supervised Scene De-occlusion","created":"2020-04-06","cited_by_count":96},{"id":"2103.03454","title":"Structured Scene Memory for Vision-Language Navigation","created":"2021-03-05","cited_by_count":95},{"id":"2010.06775","title":"Vokenization: Improving Language Understanding with Contextualized, Visual-Grounded Supervision","created":"2020-10-14","cited_by_count":94},{"id":"2109.15207","title":"Language-Aligned Waypoint (LAW) Supervision for Vision-and-Language Navigation in Continuous Environments","created":"2021-09-30","cited_by_count":94},{"id":"2311.06430","title":"GOAT: GO to Any Thing","created":"2023-11-10","cited_by_count":89},{"id":"1803.07729","title":"Look Before You Leap: Bridging Model-Free and Model-Based Reinforcement Learning for Planned-Ahead Vision-and-Language Navigation","created":"2018-03-21","cited_by_count":84},{"id":"1903.02547","title":"Tactical Rewind: Self-Correction via Backtracking in Vision-and-Language Navigation","created":"2019-03-06","cited_by_count":81},{"id":"1812.04155","title":"Vision-based Navigation with Language-based Assistance via Imitation Learning with Indirect Intervention","created":"2018-12-10","cited_by_count":77},{"id":"2007.14626","title":"Object-and-Action Aware Model for Visual Language Navigation","created":"2020-07-29","cited_by_count":77},{"id":"2007.05655","title":"Evolving Graphical Planner: Contextual Global Planning for Vision-and-Language Navigation","created":"2020-07-11","cited_by_count":71},{"id":"1910.03655","title":"Executing Instructions in Situated Collaborative Interactions","created":"2019-10-08","cited_by_count":69},{"id":"1902.07742","title":"From Language to Goals: Inverse Reinforcement Learning for Vision-Based Instruction Following","created":"2019-02-20","cited_by_count":67},{"id":"2004.02707","title":"Sub-Instruction Aware Vision-and-Language Navigation","created":"2020-04-06","cited_by_count":66},{"id":"2202.13330","title":"DialFRED: Dialogue-Enabled Agents for Embodied Instruction Following","created":"2022-02-27","cited_by_count":63},{"id":"2104.04167","title":"The Road to Know-Where: An Object-and-Room Informed Sequential BERT for Indoor Vision-Language Navigation","created":"2021-04-09","cited_by_count":61},{"id":"1906.00347","title":"Are You Looking? Grounding to Multiple Modalities in Vision-and-Language Navigation","created":"2019-06-02","cited_by_count":55},{"id":"2007.08037","title":"Active Visual Information Gathering for Vision-Language Navigation","created":"2020-07-15","cited_by_count":55},{"id":"1912.00915","title":"Just Ask:An Interactive Learning Framework for Vision and Language Navigation","created":"2019-12-02","cited_by_count":53},{"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":"2107.07201","title":"Neighbor-view Enhanced Model for Vision and Language Navigation","created":"2021-07-15","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":"1908.03409","title":"Transferable Representation Learning in Vision-and-Language Navigation","created":"2019-08-09","cited_by_count":48},{"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":"2104.10674","title":"Hierarchical Cross-Modal Agent for Robotics Vision-and-Language Navigation","created":"2021-04-21","cited_by_count":47},{"id":"2307.11984","title":"Learning Vision-and-Language Navigation from YouTube Videos","created":"2023-07-22","cited_by_count":47},{"id":"1807.03367","title":"Talk the Walk: Navigating New York City through Grounded Dialogue","created":"2018-07-09","cited_by_count":44},{"id":"1910.09664","title":"Learning to Map Natural Language Instructions to Physical Quadcopter Control using Simulated Flight","created":"2019-10-21","cited_by_count":43},{"id":"1903.01292","title":"The StreetLearn Environment and Dataset","created":"2019-03-04","cited_by_count":42},{"id":"1907.02022","title":"Chasing Ghosts: Instruction Following as Bayesian State Tracking","created":"2019-07-03","cited_by_count":41},{"id":"2005.03086","title":"Diagnosing the Environment Bias in Vision-and-Language Navigation","created":"2020-05-06","cited_by_count":41},{"id":"2103.16561","title":"Diagnosing Vision-and-Language Navigation: What Really Matters","created":"2021-03-30","cited_by_count":36},{"id":"1811.04179","title":"Mapping Navigation Instructions to Continuous Control Actions with Position-Visitation Prediction","created":"2018-11-10","cited_by_count":35},{"id":"2110.15245","title":"From Machine Learning to Robotics: Challenges and Opportunities for Embodied Intelligence","created":"2021-10-28","cited_by_count":35},{"id":"2011.06698","title":"Robust Policies via Mid-Level Visual Representations: An Experimental Study in Manipulation and Navigation","created":"2020-11-13","cited_by_count":32},{"id":"1811.00613","title":"Shifting the Baseline: Single Modality Performance on Visual Navigation & QA","created":"2018-11-01","cited_by_count":30},{"id":"2007.15543","title":"PixL2R: Guiding Reinforcement Learning Using Natural Language by Mapping Pixels to Rewards","created":"2020-07-30","cited_by_count":30}],"next_cursor":"100"}