{"list":"other","total":56,"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"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":"1506.03134","title":"Pointer Networks","created":"2015-06-09","cited_by_count":895},{"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":"1806.07011","title":"VirtualHome: Simulating Household Activities via Programs","created":"2018-06-19","cited_by_count":415},{"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":"2011.13922","title":"A Recurrent Vision-and-Language BERT for Navigation","created":"2020-11-26","cited_by_count":302},{"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":"1803.00653","title":"Semi-parametric Topological Memory for Navigation","created":"2018-03-01","cited_by_count":209},{"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":"2105.06453","title":"Episodic Transformer for Vision-and-Language Navigation","created":"2021-05-13","cited_by_count":156},{"id":"1712.03316","title":"IQA: Visual Question Answering in Interactive Environments","created":"2017-12-09","cited_by_count":155},{"id":"1905.12255","title":"Stay on the Path: Instruction Fidelity in Vision-and-Language Navigation","created":"2019-05-29","cited_by_count":130},{"id":"1810.06543","title":"Visual Semantic Navigation using Scene Priors","created":"2018-10-15","cited_by_count":128},{"id":"2110.07342","title":"FILM: Following Instructions in Language with Modular Methods","created":"2021-10-12","cited_by_count":121},{"id":"1903.01602","title":"The Regretful Agent: Heuristic-Aided Navigation through Progress Estimation","created":"2019-03-05","cited_by_count":105},{"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":"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":"2107.05612","title":"A Persistent Spatial Semantic Representation for High-level Natural Language Instruction Execution","created":"2021-07-12","cited_by_count":91},{"id":"1903.02547","title":"Tactical Rewind: Self-Correction via Backtracking in Vision-and-Language Navigation","created":"2019-03-06","cited_by_count":81},{"id":"1909.02244","title":"Robust Navigation with Language Pretraining and Stochastic Sampling","created":"2019-09-05","cited_by_count":77},{"id":"1909.10649","title":"Portuguese Named Entity Recognition using BERT-CRF","created":"2019-09-23","cited_by_count":73},{"id":"2004.02707","title":"Sub-Instruction Aware Vision-and-Language Navigation","created":"2020-04-06","cited_by_count":66},{"id":"2108.04927","title":"Embodied BERT: A Transformer Model for Embodied, Language-guided Visual Task Completion","created":"2021-08-10","cited_by_count":58},{"id":"1810.11181","title":"Neural Modular Control for Embodied Question Answering","created":"2018-10-26","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":"2106.03427","title":"Hierarchical Task Learning from Language Instructions with Unified Transformers and Self-Monitoring","created":"2021-06-07","cited_by_count":53},{"id":"2005.04625","title":"BabyWalk: Going Farther in Vision-and-Language Navigation by Taking Baby Steps","created":"2020-05-10","cited_by_count":49},{"id":"1705.08080","title":"Visual Semantic Planning using Deep Successor Representations","created":"2017-05-23","cited_by_count":45},{"id":"2104.09807","title":"Visual Navigation with Spatial Attention","created":"2021-04-20","cited_by_count":43},{"id":"1903.00445","title":"A Behavioral Approach to Visual Navigation with Graph Localization Networks","created":"2019-03-01","cited_by_count":40},{"id":"1911.07450","title":"Unsupervised Reinforcement Learning of Transferable Meta-Skills for Embodied Navigation","created":"2019-11-18","cited_by_count":40},{"id":"2104.09580","title":"Improving Cross-Modal Alignment in Vision Language Navigation via Syntactic Information","created":"2021-04-19","cited_by_count":31},{"id":"2012.03208","title":"Factorizing Perception and Policy for Interactive Instruction Following","created":"2020-12-06","cited_by_count":29},{"id":"1806.00047","title":"Following High-level Navigation Instructions on a Simulated Quadcopter with Imitation Learning","created":"2018-05-31","cited_by_count":27},{"id":"2010.08525","title":"Analogous Process Structure Induction for Sub-event Sequence Prediction","created":"2020-10-16","cited_by_count":26},{"id":"2106.00596","title":"Look Wide and Interpret Twice: Improving Performance on Interactive Instruction-following Tasks","created":"2021-06-01","cited_by_count":26},{"id":"2009.07783","title":"Generative Language-Grounded Policy in Vision-and-Language Navigation with Bayes' Rule","created":"2020-09-16","cited_by_count":22},{"id":"2009.13112","title":"Learning to Stop: A Simple yet Effective Approach to Urban Vision-Language Navigation","created":"2020-09-28","cited_by_count":20},{"id":"2011.07384","title":"Few-shot Object Grounding and Mapping for Natural Language Robot Instruction Following","created":"2020-11-14","cited_by_count":18},{"id":"2109.02161","title":"Modular Framework for Visuomotor Language Grounding","created":"2021-09-05","cited_by_count":9}],"next_cursor":null}