{"list":"other","total":51,"rows":[{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1511.06434","title":"Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks","created":"2015-11-19","cited_by_count":2054},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"1609.03499","title":"WaveNet: A Generative Model for Raw Audio","created":"2016-09-12","cited_by_count":1722},{"id":"1802.05957","title":"Spectral Normalization for Generative Adversarial Networks","created":"2018-02-16","cited_by_count":1636},{"id":"1906.00446","title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","created":"2019-06-02","cited_by_count":1387},{"id":"1711.11585","title":"High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs","created":"2017-11-30","cited_by_count":1179},{"id":"1812.08008","title":"OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2018-12-18","cited_by_count":1162},{"id":"2010.05646","title":"HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis","created":"2020-10-12","cited_by_count":1154},{"id":"1611.08050","title":"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2016-11-24","cited_by_count":1064},{"id":"1609.09430","title":"CNN Architectures for Large-Scale Audio Classification","created":"2016-09-29","cited_by_count":704},{"id":"1602.07868","title":"Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks","created":"2016-02-25","cited_by_count":543},{"id":"2005.00341","title":"Jukebox: A Generative Model for Music","created":"2020-04-30","cited_by_count":542},{"id":"1505.00853","title":"Empirical Evaluation of Rectified Activations in Convolutional Network","created":"2015-05-05","cited_by_count":519},{"id":"2101.08779","title":"AI Choreographer: Music Conditioned 3D Dance Generation with AIST++","created":"2021-01-21","cited_by_count":485},{"id":"1705.08168","title":"Look, Listen and Learn","created":"2017-05-23","cited_by_count":458},{"id":"1512.09300","title":"Autoencoding beyond pixels using a learned similarity metric","created":"2015-12-31","cited_by_count":407},{"id":"1910.06711","title":"MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis","created":"2019-10-08","cited_by_count":354},{"id":"1804.03641","title":"Audio-Visual Scene Analysis with Self-Supervised Multisensory Features","created":"2018-04-10","cited_by_count":335},{"id":"1711.10337","title":"Are GANs Created Equal? A Large-Scale Study","created":"2017-11-28","cited_by_count":267},{"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":"1705.02894","title":"Geometric GAN","created":"2017-05-08","cited_by_count":233},{"id":"1908.08498","title":"EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition","created":"2019-08-22","cited_by_count":226},{"id":"1802.04208","title":"Adversarial Audio Synthesis","created":"2018-02-12","cited_by_count":225},{"id":"1809.04281","title":"Music Transformer","created":"2018-09-12","cited_by_count":211},{"id":"1912.04487","title":"Listen to Look: Action Recognition by Previewing Audio","created":"2019-12-10","cited_by_count":163},{"id":"1709.06298","title":"MuseGAN: Multi-track Sequential Generative Adversarial Networks for Symbolic Music Generation and Accompaniment","created":"2017-09-19","cited_by_count":151},{"id":"1904.05979","title":"The Sound of Motions","created":"2019-04-11","cited_by_count":146},{"id":"2110.08791","title":"Taming Visually Guided Sound Generation","created":"2021-10-17","cited_by_count":136},{"id":"1804.01665","title":"Learning to Separate Object Sounds by Watching Unlabeled Video","created":"2018-04-05","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":"2007.10984","title":"Foley Music: Learning to Generate Music from Videos","created":"2020-07-21","cited_by_count":83},{"id":"1808.03715","title":"This Time with Feeling: Learning Expressive Musical Performance","created":"2018-08-10","cited_by_count":68},{"id":"1712.07271","title":"Learning Sight from Sound: Ambient Sound Provides Supervision for Visual Learning","created":"2017-12-20","cited_by_count":67},{"id":"2011.06801","title":"A Comprehensive Survey on Deep Music Generation: Multi-level Representations, Algorithms, Evaluations, and Future Directions","created":"2020-11-13","cited_by_count":56},{"id":"2111.08380","title":"Video Background Music Generation with Controllable Music Transformer","created":"2021-11-16","cited_by_count":56},{"id":"1712.09382","title":"Audio to Body Dynamics","created":"2017-12-19","cited_by_count":48},{"id":"2006.14348","title":"Audeo: Audio Generation for a Silent Performance Video","created":"2020-06-23","cited_by_count":47},{"id":"1909.09944","title":"Watch, Listen and Tell: Multi-modal Weakly Supervised Dense Event Captioning","created":"2019-09-22","cited_by_count":38},{"id":"2011.12999","title":"Learning to dance: A graph convolutional adversarial network to generate realistic dance motions from audio","created":"2020-11-25","cited_by_count":33},{"id":"1804.05448","title":"Watch, Listen, and Describe: Globally and Locally Aligned Cross-Modal Attentions for Video Captioning","created":"2018-04-15","cited_by_count":21},{"id":"2009.08015","title":"Temporally Guided Music-to-Body-Movement Generation","created":"2020-09-17","cited_by_count":21},{"id":"2107.06252","title":"Dance2Music: Automatic Dance-driven Music Generation","created":"2021-07-13","cited_by_count":16},{"id":"2102.03424","title":"Learning Audio-Visual Correlations from Variational Cross-Modal Generation","created":"2021-02-05","cited_by_count":14},{"id":"2202.11374","title":"Skeleton Sequence and RGB Frame Based Multi-Modality Feature Fusion Network for Action Recognition","created":"2022-02-23","cited_by_count":6}],"next_cursor":null}