{"list":"other","total":51,"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":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"id":"1804.00607","title":"MegaDepth: Learning Single-View Depth Prediction from Internet Photos","created":"2018-04-02","cited_by_count":737},{"id":"1609.09430","title":"CNN Architectures for Large-Scale Audio Classification","created":"2016-09-29","cited_by_count":704},{"id":"2004.14368","title":"VGGSound: A Large-scale Audio-Visual Dataset","created":"2020-04-29","cited_by_count":648},{"id":"1411.4734","title":"Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture","created":"2014-11-18","cited_by_count":483},{"id":"1705.08168","title":"Look, Listen and Learn","created":"2017-05-23","cited_by_count":458},{"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":"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":"1712.06651","title":"Objects that Sound","created":"2017-12-18","cited_by_count":256},{"id":"1807.00230","title":"Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization","created":"2018-06-30","cited_by_count":249},{"id":"1610.09001","title":"SoundNet: Learning Sound Representations from Unlabeled Video","created":"2016-10-27","cited_by_count":247},{"id":"2012.09365","title":"Learning to Recover 3D Scene Shape from a Single Image","created":"2020-12-17","cited_by_count":216},{"id":"1611.03673","title":"Learning to Navigate in Complex Environments","created":"2016-11-11","cited_by_count":198},{"id":"2004.12943","title":"Audio-Visual Instance Discrimination with Cross-Modal Agreement","created":"2020-04-27","cited_by_count":195},{"id":"1803.03849","title":"Learning to Localize Sound Source in Visual Scenes","created":"2018-03-10","cited_by_count":189},{"id":"2008.04237","title":"Self-Supervised Learning of Audio-Visual Objects from Video","created":"2020-08-10","cited_by_count":188},{"id":"1604.03901","title":"Single-Image Depth Perception in the Wild","created":"2016-04-13","cited_by_count":180},{"id":"1603.08637","title":"Learning a Predictable and Generative Vector Representation for Objects","created":"2016-03-29","cited_by_count":173},{"id":"2104.02691","title":"Localizing Visual Sounds the Hard Way","created":"2021-04-06","cited_by_count":170},{"id":"1904.05979","title":"The Sound of Motions","created":"2019-04-11","cited_by_count":146},{"id":"2001.08740","title":"Audiovisual SlowFast Networks for Video Recognition","created":"2020-01-23","cited_by_count":146},{"id":"1512.08512","title":"Visually Indicated Sounds","created":"2015-12-28","cited_by_count":128},{"id":"2007.06355","title":"Multiple Sound Sources Localization from Coarse to Fine","created":"2020-07-13","cited_by_count":118},{"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":"2010.05466","title":"Discriminative Sounding Objects Localization via Self-supervised Audiovisual Matching","created":"2020-10-12","cited_by_count":104},{"id":"2006.13662","title":"Labelling unlabelled videos from scratch with multi-modal self-supervision","created":"2020-06-24","cited_by_count":100},{"id":"1912.11684","title":"Look, Listen, and Act: Towards Audio-Visual Embodied Navigation","created":"2019-12-25","cited_by_count":96},{"id":"1809.02587","title":"Self-Supervised Generation of Spatial Audio for 360 Video","created":"2018-09-07","cited_by_count":93},{"id":"1901.01342","title":"AVA-ActiveSpeaker: An Audio-Visual Dataset for Active Speaker Detection","created":"2019-01-05","cited_by_count":83},{"id":"2012.11583","title":"Semantic Audio-Visual Navigation","created":"2020-12-21","cited_by_count":82},{"id":"1804.01452","title":"Jointly Discovering Visual Objects and Spoken Words from Raw Sensory Input","created":"2018-04-04","cited_by_count":81},{"id":"1712.07271","title":"Learning Sight from Sound: Ambient Sound Provides Supervision for Visual Learning","created":"2017-12-20","cited_by_count":67},{"id":"1910.11760","title":"Self-supervised Moving Vehicle Tracking with Stereo Sound","created":"2019-10-25","cited_by_count":63},{"id":"1809.08001","title":"Perfect match: Improved cross-modal embeddings for audio-visual synchronisation","created":"2018-09-21","cited_by_count":60},{"id":"2005.01616","title":"VisualEchoes: Spatial Image Representation Learning through Echolocation","created":"2020-05-04","cited_by_count":55},{"id":"1712.01812","title":"Factoring Shape, Pose, and Layout from the 2D Image of a 3D Scene","created":"2017-12-05","cited_by_count":50},{"id":"2006.06175","title":"Telling Left from Right: Learning Spatial Correspondence of Sight and Sound","created":"2020-06-11","cited_by_count":43},{"id":"2104.13530","title":"Extreme Rotation Estimation using Dense Correlation Volumes","created":"2021-04-28","cited_by_count":42},{"id":"1704.05588","title":"Learning to Fly by Crashing","created":"2017-04-19","cited_by_count":41},{"id":"2012.15470","title":"Audio-Visual Floorplan Reconstruction","created":"2020-12-31","cited_by_count":32},{"id":"1912.07011","title":"BatVision: Learning to See 3D Spatial Layout with Two Ears","created":"2019-12-15","cited_by_count":26},{"id":"1806.09573","title":"Learning Single-Image Depth from Videos using Quality Assessment Networks","created":"2018-06-25","cited_by_count":25},{"id":"2007.13727","title":"Associative3D: Volumetric Reconstruction from Sparse Views","created":"2020-07-27","cited_by_count":18},{"id":"1711.07791","title":"Reflection-Aware Sound Source Localization","created":"2017-11-21","cited_by_count":5},{"id":"2105.08052","title":"The Boombox: Visual Reconstruction from Acoustic Vibrations","created":"2021-05-17","cited_by_count":3}],"next_cursor":null}