{"list":"other","total":56,"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":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"1603.08155","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","created":"2016-03-27","cited_by_count":2694},{"id":"1703.06868","title":"Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization","created":"2017-03-20","cited_by_count":2010},{"id":"1611.04076","title":"Least Squares Generative Adversarial Networks","created":"2016-11-13","cited_by_count":1001},{"id":"1605.05396","title":"Generative Adversarial Text to Image Synthesis","created":"2016-05-17","cited_by_count":735},{"id":"1609.09430","title":"CNN Architectures for Large-Scale Audio Classification","created":"2016-09-29","cited_by_count":704},{"id":"2008.10010","title":"A Lip Sync Expert Is All You Need for Speech to Lip Generation In The Wild","created":"2020-08-23","cited_by_count":672},{"id":"2004.14368","title":"VGGSound: A Large-scale Audio-Visual Dataset","created":"2020-04-29","cited_by_count":648},{"id":"2007.15651","title":"Contrastive Learning for Unpaired Image-to-Image Translation","created":"2020-07-30","cited_by_count":639},{"id":"1805.00932","title":"Exploring the Limits of Weakly Supervised Pretraining","created":"2018-05-02","cited_by_count":605},{"id":"1508.06576","title":"A Neural Algorithm of Artistic Style","created":"2015-08-26","cited_by_count":483},{"id":"1705.08168","title":"Look, Listen and Learn","created":"2017-05-23","cited_by_count":458},{"id":"1905.12681","title":"What Makes Training Multi-Modal Classification Networks Hard?","created":"2019-05-29","cited_by_count":344},{"id":"1804.03641","title":"Audio-Visual Scene Analysis with Self-Supervised Multisensory Features","created":"2018-04-10","cited_by_count":335},{"id":"1804.01622","title":"Image Generation from Scene Graphs","created":"2018-04-04","cited_by_count":324},{"id":"1809.02108","title":"Deep Audio-Visual Speech Recognition","created":"2018-09-06","cited_by_count":322},{"id":"1704.02510","title":"DualGAN: Unsupervised Dual Learning for Image-to-Image Translation","created":"2017-04-08","cited_by_count":310},{"id":"1703.05192","title":"Learning to Discover Cross-Domain Relations with Generative Adversarial Networks","created":"2017-03-15","cited_by_count":278},{"id":"1804.03160","title":"The Sound of Pixels","created":"2018-04-09","cited_by_count":259},{"id":"1807.00230","title":"Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization","created":"2018-06-30","cited_by_count":249},{"id":"2110.11499","title":"Wav2CLIP: Learning Robust Audio Representations From CLIP","created":"2021-10-21","cited_by_count":213},{"id":"1807.07860","title":"Talking Face Generation by Adversarially Disentangled Audio-Visual Representation","created":"2018-07-20","cited_by_count":212},{"id":"2004.12943","title":"Audio-Visual Instance Discrimination with Cross-Modal Agreement","created":"2020-04-27","cited_by_count":195},{"id":"1906.04160","title":"Learning Individual Styles of Conversational Gesture","created":"2019-06-10","cited_by_count":191},{"id":"2104.02691","title":"Localizing Visual Sounds the Hard Way","created":"2021-04-06","cited_by_count":170},{"id":"1804.03619","title":"Looking to Listen at the Cocktail Party: A Speaker-Independent Audio-Visual Model for Speech Separation","created":"2018-04-10","cited_by_count":162},{"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":"1512.08512","title":"Visually Indicated Sounds","created":"2015-12-28","cited_by_count":128},{"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":"2103.10951","title":"Paint by Word","created":"2021-03-19","cited_by_count":107},{"id":"2006.13662","title":"Labelling unlabelled videos from scratch with multi-modal self-supervision","created":"2020-06-24","cited_by_count":100},{"id":"1705.02966","title":"You said that?","created":"2017-05-08","cited_by_count":99},{"id":"1712.01393","title":"Visual to Sound: Generating Natural Sound for Videos in the Wild","created":"2017-12-04","cited_by_count":98},{"id":"1809.02587","title":"Self-Supervised Generation of Spatial Audio for 360 Video","created":"2018-09-07","cited_by_count":93},{"id":"1810.11919","title":"Text-Adaptive Generative Adversarial Networks: Manipulating Images with Natural Language","created":"2018-10-29","cited_by_count":90},{"id":"1707.06873","title":"Semantic Image Synthesis via Adversarial Learning","created":"2017-07-21","cited_by_count":87},{"id":"1804.01452","title":"Jointly Discovering Visual Objects and Spoken Words from Raw Sensory Input","created":"2018-04-04","cited_by_count":81},{"id":"2005.08209","title":"Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis","created":"2020-05-17","cited_by_count":74},{"id":"2104.11222","title":"On Aliased Resizing and Surprising Subtleties in GAN Evaluation","created":"2021-04-22","cited_by_count":51},{"id":"1712.09382","title":"Audio to Body Dynamics","created":"2017-12-19","cited_by_count":48},{"id":"2006.06175","title":"Telling Left from Right: Learning Spatial Correspondence of Sight and Sound","created":"2020-06-11","cited_by_count":43},{"id":"2110.08243","title":"Neural Dubber: Dubbing for Videos According to Scripts","created":"2021-10-15","cited_by_count":39},{"id":"2112.00007","title":"Sound-Guided Semantic Image Manipulation","created":"2021-11-30","cited_by_count":35},{"id":"2007.12130","title":"Sound2Sight: Generating Visual Dynamics from Sound and Context","created":"2020-07-23","cited_by_count":28},{"id":"2111.05846","title":"Structure from Silence: Learning Scene Structure from Ambient Sound","created":"2021-11-10","cited_by_count":17},{"id":"2008.01180","title":"Describing Textures using Natural Language","created":"2020-08-03","cited_by_count":5}],"next_cursor":null}