{"list":"other","total":54,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"1709.06158","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","created":"2017-09-18","cited_by_count":1376},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"id":"1906.05797","title":"The Replica Dataset: A Digital Replica of Indoor Spaces","created":"2019-06-13","cited_by_count":904},{"id":"1706.08612","title":"VoxCeleb: a large-scale speaker identification dataset","created":"2017-06-26","cited_by_count":732},{"id":"1606.01868","title":"Unifying Count-Based Exploration and Intrinsic Motivation","created":"2016-06-06","cited_by_count":639},{"id":"1808.10654","title":"Gibson Env: Real-World Perception for Embodied Agents","created":"2018-08-31","cited_by_count":481},{"id":"2007.00643","title":"Object Goal Navigation using Goal-Oriented Semantic Exploration","created":"2020-07-01","cited_by_count":429},{"id":"1811.02508","title":"SDR - half-baked or well done?","created":"2018-11-06","cited_by_count":423},{"id":"1609.05143","title":"Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning","created":"2016-09-16","cited_by_count":366},{"id":"1506.02216","title":"A Recurrent Latent Variable Model for Sequential Data","created":"2015-06-07","cited_by_count":362},{"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":"1804.03641","title":"Audio-Visual Scene Analysis with Self-Supervised Multisensory Features","created":"2018-04-10","cited_by_count":335},{"id":"1804.03160","title":"The Sound of Pixels","created":"2018-04-09","cited_by_count":259},{"id":"2006.13171","title":"ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objects","created":"2020-06-23","cited_by_count":244},{"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":"2005.12256","title":"Neural Topological SLAM for Visual Navigation","created":"2020-05-25","cited_by_count":195},{"id":"1810.06543","title":"Visual Semantic Navigation using Scene Priors","created":"2018-10-15","cited_by_count":128},{"id":"1609.07088","title":"Learning Modular Neural Network Policies for Multi-Task and Multi-Robot Transfer","created":"2016-09-22","cited_by_count":127},{"id":"1804.01665","title":"Learning to Separate Object Sounds by Watching Unlabeled Video","created":"2018-04-05","cited_by_count":114},{"id":"2101.03149","title":"VisualVoice: Audio-Visual Speech Separation with Cross-Modal Consistency","created":"2021-01-08","cited_by_count":114},{"id":"2004.09476","title":"Music Gesture for Visual Sound Separation","created":"2020-04-20","cited_by_count":112},{"id":"1904.07750","title":"Co-Separating Sounds of Visual Objects","created":"2019-04-16","cited_by_count":110},{"id":"1804.04121","title":"The Conversation: Deep Audio-Visual Speech Enhancement","created":"2018-04-11","cited_by_count":109},{"id":"2008.09285","title":"Occupancy Anticipation for Efficient Exploration and Navigation","created":"2020-08-21","cited_by_count":106},{"id":"1912.11684","title":"Look, Listen, and Act: Towards Audio-Visual Embodied Navigation","created":"2019-12-25","cited_by_count":96},{"id":"1805.06066","title":"Visual Representations for Semantic Target Driven Navigation","created":"2018-05-15","cited_by_count":89},{"id":"2012.11583","title":"Semantic Audio-Visual Navigation","created":"2020-12-21","cited_by_count":82},{"id":"1803.06773","title":"Composable Deep Reinforcement Learning for Robotic Manipulation","created":"2018-03-19","cited_by_count":72},{"id":"1812.04204","title":"2.5D Visual Sound","created":"2018-12-11","cited_by_count":63},{"id":"2006.10034","title":"Semantic Visual Navigation by Watching YouTube Videos","created":"2020-06-17","cited_by_count":60},{"id":"1412.1265","title":"Deeply learned face representations are sparse, selective, and robust","created":"2014-12-03","cited_by_count":56},{"id":"2005.01616","title":"VisualEchoes: Spatial Image Representation Learning through Echolocation","created":"2020-05-04","cited_by_count":55},{"id":"2011.01143","title":"Into the Wild with AudioScope: Unsupervised Audio-Visual Separation of On-Screen Sounds","created":"2020-11-02","cited_by_count":55},{"id":"1908.11602","title":"Recursive Visual Sound Separation Using Minus-Plus Net","created":"2019-08-30","cited_by_count":53},{"id":"1909.04306","title":"Bayesian Relational Memory for Semantic Visual Navigation","created":"2019-09-10","cited_by_count":48},{"id":"1705.08080","title":"Visual Semantic Planning using Deep Successor Representations","created":"2017-05-23","cited_by_count":45},{"id":"2012.15470","title":"Audio-Visual Floorplan Reconstruction","created":"2020-12-31","cited_by_count":32},{"id":"2006.05712","title":"Listen to What You Want: Neural Network-based Universal Sound Selector","created":"2020-06-10","cited_by_count":27},{"id":"1907.04975","title":"My lips are concealed: Audio-visual speech enhancement through obstructions","created":"2019-07-11","cited_by_count":26},{"id":"2005.07074","title":"FaceFilter: Audio-visual speech separation using still images","created":"2020-05-14","cited_by_count":25},{"id":"1901.10915","title":"Benchmarking Classic and Learned Navigation in Complex 3D Environments","created":"2019-01-30","cited_by_count":24},{"id":"1911.07951","title":"Improving Universal Sound Separation Using Sound Classification","created":"2019-11-18","cited_by_count":17},{"id":"1706.09588","title":"Multi-scale Multi-band DenseNets for Audio Source Separation","created":"2017-06-29","cited_by_count":15},{"id":"1811.03076","title":"Class-conditional embeddings for music source separation","created":"2018-11-07","cited_by_count":12},{"id":"1504.04658","title":"Deep Karaoke: Extracting Vocals from Musical Mixtures Using a Convolutional Deep Neural Network","created":"2015-04-17","cited_by_count":5},{"id":"1311.2460","title":"Vision-Guided Robot Hearing","created":"2013-11-06","cited_by_count":4},{"id":"2001.00391","title":"Temporal-Spatial Neural Filter: Direction Informed End-to-End Multi-channel Target Speech Separation","created":"2020-01-02","cited_by_count":4},{"id":"2007.06123","title":"OtoWorld: Towards Learning to Separate by Learning to Move","created":"2020-07-12","cited_by_count":1}],"next_cursor":null}