{"list":"other","total":78,"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":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1606.03498","title":"Improved Techniques for Training GANs","created":"2016-06-10","cited_by_count":2970},{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611},{"id":"1703.06868","title":"Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization","created":"2017-03-20","cited_by_count":2010},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"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":"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":"2301.12503","title":"AudioLDM: Text-to-Audio Generation with Latent Diffusion Models","created":"2023-01-29","cited_by_count":599},{"id":"1912.10211","title":"PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition","created":"2019-12-21","cited_by_count":574},{"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":"2010.00475","title":"FSD50K: An Open Dataset of Human-Labeled Sound Events","created":"2020-10-01","cited_by_count":342},{"id":"1804.03641","title":"Audio-Visual Scene Analysis with Self-Supervised Multisensory Features","created":"2018-04-10","cited_by_count":335},{"id":"2301.12661","title":"Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models","created":"2023-01-30","cited_by_count":324},{"id":"1809.02108","title":"Deep Audio-Visual Speech Recognition","created":"2018-09-06","cited_by_count":322},{"id":"2209.15352","title":"AudioGen: Textually Guided Audio Generation","created":"2022-09-30","cited_by_count":295},{"id":"2207.06405","title":"Masked Autoencoders that Listen","created":"2022-07-13","cited_by_count":273},{"id":"2303.17395","title":"WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research","created":"2023-03-30","cited_by_count":267},{"id":"1804.03160","title":"The Sound of Pixels","created":"2018-04-09","cited_by_count":259},{"id":"2207.09983","title":"Diffsound: Discrete Diffusion Model for Text-to-sound Generation","created":"2022-07-20","cited_by_count":257},{"id":"1807.00230","title":"Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization","created":"2018-06-30","cited_by_count":249},{"id":"1611.05358","title":"Lip Reading Sentences in the Wild","created":"2016-11-16","cited_by_count":228},{"id":"1708.07860","title":"Multi-task Self-Supervised Visual Learning","created":"2017-08-25","cited_by_count":200},{"id":"2004.12943","title":"Audio-Visual Instance Discrimination with Cross-Modal Agreement","created":"2020-04-27","cited_by_count":195},{"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":"2306.17203","title":"Diff-Foley: Synchronized Video-to-Audio Synthesis with Latent Diffusion Models","created":"2023-06-29","cited_by_count":134},{"id":"1512.08512","title":"Visually Indicated Sounds","created":"2015-12-28","cited_by_count":128},{"id":"1904.08352","title":"MOSNet: Deep Learning based Objective Assessment for Voice Conversion","created":"2019-04-17","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":"2103.10951","title":"Paint by Word","created":"2021-03-19","cited_by_count":107},{"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":"2211.03089","title":"I Hear Your True Colors: Image Guided Audio Generation","created":"2022-11-06","cited_by_count":92},{"id":"1707.06873","title":"Semantic Image Synthesis via Adversarial Learning","created":"2017-07-21","cited_by_count":87},{"id":"2211.12498","title":"Touch and Go: Learning from Human-Collected Vision and Touch","created":"2022-11-22","cited_by_count":87},{"id":"2301.01767","title":"Self-Supervised Video Forensics by Audio-Visual Anomaly Detection","created":"2023-01-04","cited_by_count":85},{"id":"2007.10984","title":"Foley Music: Learning to Generate Music from Videos","created":"2020-07-21","cited_by_count":83},{"id":"2304.00830","title":"AUDIT: Audio Editing by Following Instructions with Latent Diffusion Models","created":"2023-04-03","cited_by_count":83},{"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":"1712.07271","title":"Learning Sight from Sound: Ambient Sound Provides Supervision for Visual Learning","created":"2017-12-20","cited_by_count":67},{"id":"2301.12662","title":"SingSong: Generating musical accompaniments from singing","created":"2023-01-30","cited_by_count":55},{"id":"1701.00495","title":"Vid2speech: Speech Reconstruction from Silent Video","created":"2017-01-02","cited_by_count":53},{"id":"2305.01233","title":"On Uni-Modal Feature Learning in Supervised Multi-Modal Learning","created":"2023-05-02","cited_by_count":53},{"id":"2304.08490","title":"Conditional Generation of Audio from Video via Foley Analogies","created":"2023-04-17","cited_by_count":52},{"id":"2302.00646","title":"Epic-Sounds: A Large-scale Dataset of Actions That Sound","created":"2023-02-01","cited_by_count":47},{"id":"2202.06875","title":"Visual Acoustic Matching","created":"2022-02-14","cited_by_count":45},{"id":"2006.06175","title":"Telling Left from Right: Learning Spatial Correspondence of Sight and Sound","created":"2020-06-11","cited_by_count":43},{"id":"2112.04432","title":"Audio-Visual Synchronisation in the wild","created":"2021-12-08","cited_by_count":40},{"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":"2103.14201","title":"Image2Reverb: Cross-Modal Reverb Impulse Response Synthesis","created":"2021-03-26","cited_by_count":34},{"id":"1811.09620","title":"TimbreTron: A WaveNet(CycleGAN(CQT(Audio))) Pipeline for Musical Timbre Transfer","created":"2018-11-22","cited_by_count":33},{"id":"2103.10211","title":"Space-Time Crop & Attend: Improving Cross-modal Video Representation Learning","created":"2021-03-18","cited_by_count":31},{"id":"2309.15117","title":"Generating Visual Scenes from Touch","created":"2023-09-26","cited_by_count":26},{"id":"2205.05072","title":"Learning Visual Styles from Audio-Visual Associations","created":"2022-05-10","cited_by_count":22},{"id":"2110.09958","title":"The Cocktail Fork Problem: Three-Stem Audio Separation for Real-World Soundtracks","created":"2021-10-19","cited_by_count":19},{"id":"1801.01589","title":"Neural Style Transfer for Audio Spectograms","created":"2018-01-04","cited_by_count":18},{"id":"2207.08759","title":"Style Transfer of Audio Effects with Differentiable Signal Processing","created":"2022-07-18","cited_by_count":18},{"id":"2303.11329","title":"Sound Localization from Motion: Jointly Learning Sound Direction and Camera Rotation","created":"2023-03-20","cited_by_count":18},{"id":"2307.15064","title":"Self-Supervised Visual Acoustic Matching","created":"2023-07-27","cited_by_count":14},{"id":"2005.09200","title":"Atss-Net: Target Speaker Separation via Attention-based Neural Network","created":"2020-05-19","cited_by_count":8},{"id":"2011.00782","title":"CVC: Contrastive Learning for Non-parallel Voice Conversion","created":"2020-11-02","cited_by_count":4}],"next_cursor":null}