{"list":"other","total":52,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"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":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"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":"1607.01759","title":"Bag of Tricks for Efficient Text Classification","created":"2016-07-06","cited_by_count":876},{"id":"1712.05474","title":"AI2-THOR: An Interactive 3D Environment for Visual AI","created":"2017-12-14","cited_by_count":869},{"id":"1807.06757","title":"On Evaluation of Embodied Navigation Agents","created":"2018-07-18","cited_by_count":547},{"id":"2007.00643","title":"Object Goal Navigation using Goal-Oriented Semantic Exploration","created":"2020-07-01","cited_by_count":429},{"id":"1609.05143","title":"Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning","created":"2016-09-16","cited_by_count":366},{"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":"2004.05155","title":"Learning to Explore using Active Neural SLAM","created":"2020-04-10","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":"1702.03920","title":"Cognitive Mapping and Planning for Visual Navigation","created":"2017-02-13","cited_by_count":212},{"id":"1803.00653","title":"Semi-parametric Topological Memory for Navigation","created":"2018-03-01","cited_by_count":209},{"id":"1611.03673","title":"Learning to Navigate in Complex Environments","created":"2016-11-11","cited_by_count":198},{"id":"2005.12256","title":"Neural Topological SLAM for Visual Navigation","created":"2020-05-25","cited_by_count":195},{"id":"2004.06799","title":"RoboTHOR: An Open Simulation-to-Real Embodied AI Platform","created":"2020-04-14","cited_by_count":193},{"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":"2010.09890","title":"Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration","created":"2020-10-19","cited_by_count":133},{"id":"1810.06543","title":"Visual Semantic Navigation using Scene Priors","created":"2018-10-15","cited_by_count":128},{"id":"1804.08606","title":"Zero-Shot Visual Imitation","created":"2018-04-23","cited_by_count":117},{"id":"1903.01959","title":"Learning Exploration Policies for Navigation","created":"2019-03-05","cited_by_count":116},{"id":"1903.03878","title":"Scene Memory Transformer for Embodied Agents in Long-Horizon Tasks","created":"2019-03-09","cited_by_count":107},{"id":"1812.00971","title":"Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning","created":"2018-12-03","cited_by_count":93},{"id":"1702.08360","title":"Neural Map: Structured Memory for Deep Reinforcement Learning","created":"2017-02-27","cited_by_count":90},{"id":"1805.06066","title":"Visual Representations for Semantic Target Driven Navigation","created":"2018-05-15","cited_by_count":89},{"id":"1709.10489","title":"Self-supervised Deep Reinforcement Learning with Generalized Computation Graphs for Robot Navigation","created":"2017-09-29","cited_by_count":77},{"id":"1706.07230","title":"Gated-Attention Architectures for Task-Oriented Language Grounding","created":"2017-06-22","cited_by_count":72},{"id":"2007.06811","title":"A Single Stream Network for Robust and Real-time RGB-D Salient Object Detection","created":"2020-07-14","cited_by_count":67},{"id":"2007.11018","title":"Learning Object Relation Graph and Tentative Policy for Visual Navigation","created":"2020-07-21","cited_by_count":64},{"id":"2106.12735","title":"Multi-Modal 3D Object Detection in Autonomous Driving: a Survey","created":"2021-06-24","cited_by_count":63},{"id":"2010.01191","title":"Semantic MapNet: Building Allocentric Semantic Maps and Representations from Egocentric Views","created":"2020-10-02","cited_by_count":58},{"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":"2105.09447","title":"VTNet: Visual Transformer Network for Object Goal Navigation","created":"2021-05-20","cited_by_count":51},{"id":"2007.07051","title":"RGB-D Salient Object Detection with Cross-Modality Modulation and Selection","created":"2020-07-14","cited_by_count":50},{"id":"1907.06023","title":"Structure-Aware Residual Pyramid Network for Monocular Depth Estimation","created":"2019-07-13","cited_by_count":49},{"id":"1611.06256","title":"Reinforcement Learning through Asynchronous Advantage Actor-Critic on a GPU","created":"2016-11-18","cited_by_count":48},{"id":"1909.04306","title":"Bayesian Relational Memory for Semantic Visual Navigation","created":"2019-09-10","cited_by_count":48},{"id":"2007.04901","title":"Cross-Modal Weighting Network for RGB-D Salient Object Detection","created":"2020-07-09","cited_by_count":47},{"id":"2012.04512","title":"SSCNav: Confidence-Aware Semantic Scene Completion for Visual Semantic Navigation","created":"2020-12-08","cited_by_count":44},{"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":"1908.09073","title":"Situational Fusion of Visual Representation for Visual Navigation","created":"2019-08-24","cited_by_count":28},{"id":"2011.10972","title":"Language-guided Navigation via Cross-Modal Grounding and Alternate Adversarial Learning","created":"2020-11-22","cited_by_count":22},{"id":"1911.07980","title":"Simultaneous Mapping and Target Driven Navigation","created":"2019-11-18","cited_by_count":11},{"id":"1803.04119","title":"A Deep Learning Based Behavioral Approach to Indoor Autonomous Navigation","created":"2018-03-12","cited_by_count":9}],"next_cursor":null}