{"list":"other","total":51,"rows":[{"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":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1503.03832","title":"FaceNet: A Unified Embedding for Face Recognition and Clustering","created":"2015-03-12","cited_by_count":2849},{"id":"1806.05622","title":"VoxCeleb2: Deep Speaker Recognition","created":"2018-06-14","cited_by_count":875},{"id":"1609.09430","title":"CNN Architectures for Large-Scale Audio Classification","created":"2016-09-29","cited_by_count":704},{"id":"2004.01177","title":"Tracking Objects as Points","created":"2020-04-02","cited_by_count":483},{"id":"1804.03641","title":"Audio-Visual Scene Analysis with Self-Supervised Multisensory Features","created":"2018-04-10","cited_by_count":335},{"id":"1406.6909","title":"Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networks","created":"2014-06-26","cited_by_count":300},{"id":"1903.07593","title":"Learning Correspondence from the Cycle-Consistency of Time","created":"2019-03-18","cited_by_count":269},{"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":"2006.14613","title":"Space-Time Correspondence as a Contrastive Random Walk","created":"2020-06-25","cited_by_count":239},{"id":"1612.01840","title":"FMA: A Dataset For Music Analysis","created":"2016-12-06","cited_by_count":207},{"id":"1803.03849","title":"Learning to Localize Sound Source in Visual Scenes","created":"2018-03-10","cited_by_count":189},{"id":"1904.03240","title":"An Unsupervised Autoregressive Model for Speech Representation Learning","created":"2019-04-05","cited_by_count":186},{"id":"2110.09784","title":"SSAST: Self-Supervised Audio Spectrogram Transformer","created":"2021-10-19","cited_by_count":169},{"id":"1806.09594","title":"Tracking Emerges by Colorizing Videos","created":"2018-06-25","cited_by_count":166},{"id":"1710.04196","title":"Pyroomacoustics: A Python package for audio room simulations and array processing algorithms","created":"2017-10-11","cited_by_count":132},{"id":"2006.04902","title":"What Matters in Unsupervised Optical Flow","created":"2020-06-08","cited_by_count":124},{"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":"1804.04121","title":"The Conversation: Deep Audio-Visual Speech Enhancement","created":"2018-04-11","cited_by_count":109},{"id":"1904.03416","title":"Learning Problem-agnostic Speech Representations from Multiple Self-supervised Tasks","created":"2019-04-06","cited_by_count":87},{"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":"2107.02156","title":"Do Different Tracking Tasks Require Different Appearance Models?","created":"2021-07-05","cited_by_count":62},{"id":"1804.00326","title":"Seeing Voices and Hearing Faces: Cross-modal biometric matching","created":"2018-04-01","cited_by_count":60},{"id":"2003.07990","title":"Watching the World Go By: Representation Learning from Unlabeled Videos","created":"2020-03-18","cited_by_count":59},{"id":"2111.12124","title":"Towards Learning Universal Audio Representations","created":"2021-11-23","cited_by_count":51},{"id":"2104.06162","title":"Visually Informed Binaural Audio Generation without Binaural Audios","created":"2021-04-13","cited_by_count":46},{"id":"2103.01353","title":"There is More than Meets the Eye: Self-Supervised Multi-Object Detection and Tracking with Sound by Distilling Multimodal Knowledge","created":"2021-03-01","cited_by_count":44},{"id":"2105.05217","title":"Representation Learning via Global Temporal Alignment and Cycle-Consistency","created":"2021-05-11","cited_by_count":44},{"id":"2006.06175","title":"Telling Left from Right: Learning Spatial Correspondence of Sight and Sound","created":"2020-06-11","cited_by_count":43},{"id":"2103.06508","title":"Multi-Format Contrastive Learning of Audio Representations","created":"2021-03-11","cited_by_count":39},{"id":"1905.04418","title":"Machine learning in acoustics: theory and applications","created":"2019-05-11","cited_by_count":36},{"id":"2201.08379","title":"Learning Pixel Trajectories with Multiscale Contrastive Random Walks","created":"2022-01-20","cited_by_count":36},{"id":"2010.13991","title":"Speech SIMCLR: Combining Contrastive and Reconstruction Objective for Self-supervised Speech Representation Learning","created":"2020-10-27","cited_by_count":34},{"id":"1710.10059","title":"Direction of arrival estimation for multiple sound sources using convolutional recurrent neural network","created":"2017-10-27","cited_by_count":27},{"id":"2111.10882","title":"Geometry-Aware Multi-Task Learning for Binaural Audio Generation from Video","created":"2021-11-21","cited_by_count":22},{"id":"1904.07556","title":"Unsupervised acoustic unit discovery for speech synthesis using discrete latent-variable neural networks","created":"2019-04-16","cited_by_count":20},{"id":"1705.00919","title":"Broadband DOA estimation using Convolutional neural networks trained with noise signals","created":"2017-05-02","cited_by_count":15},{"id":"2006.09006","title":"Robust Sound Source Tracking Using SRP-PHAT and 3D Convolutional Neural Networks","created":"2020-06-16","cited_by_count":15},{"id":"1904.01916","title":"End-to-end Binaural Sound Localisation from the Raw Waveform","created":"2019-04-03","cited_by_count":6},{"id":"2006.07995","title":"BatVision with GCC-PHAT Features for Better Sound to Vision Predictions","created":"2020-06-14","cited_by_count":5},{"id":"2002.00641","title":"Time Difference of Arrival Estimation from Frequency-Sliding Generalized Cross-Correlations Using Convolutional Neural Networks","created":"2020-02-03","cited_by_count":4},{"id":"2109.02763","title":"Binaural SoundNet: Predicting Semantics, Depth and Motion with Binaural Sounds","created":"2021-09-06","cited_by_count":4}],"next_cursor":null}