{"list":"other","total":63,"rows":[{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"2005.08100","title":"Conformer: Convolution-augmented Transformer for Speech Recognition","created":"2020-05-16","cited_by_count":1863},{"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":"1806.05622","title":"VoxCeleb2: Deep Speaker Recognition","created":"2018-06-14","cited_by_count":875},{"id":"1712.05884","title":"Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions","created":"2017-12-16","cited_by_count":804},{"id":"2008.00951","title":"Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation","created":"2020-08-03","cited_by_count":727},{"id":"2003.00196","title":"First Order Motion Model for Image Animation","created":"2020-02-29","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":"1703.07332","title":"How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)","created":"2017-03-21","cited_by_count":525},{"id":"1903.08527","title":"Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set","created":"2019-03-20","cited_by_count":482},{"id":"2105.06337","title":"Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech","created":"2021-05-13","cited_by_count":447},{"id":"2011.15126","title":"One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing","created":"2020-11-30","cited_by_count":444},{"id":"2211.12194","title":"SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation","created":"2022-11-22","cited_by_count":382},{"id":"1911.11544","title":"Image2StyleGAN++: How to Edit the Embedded Images?","created":"2019-11-26","cited_by_count":356},{"id":"1809.02108","title":"Deep Audio-Visual Speech Recognition","created":"2018-09-06","cited_by_count":322},{"id":"2004.00288","title":"CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition","created":"2020-04-01","cited_by_count":321},{"id":"2004.12992","title":"MakeItTalk: Speaker-Aware Talking-Head Animation","created":"2020-04-27","cited_by_count":312},{"id":"1809.00496","title":"LRS3-TED: a large-scale dataset for visual speech recognition","created":"2018-09-03","cited_by_count":308},{"id":"2104.11116","title":"Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation","created":"2021-04-22","cited_by_count":288},{"id":"1806.04558","title":"Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis","created":"2018-06-12","cited_by_count":282},{"id":"2005.11129","title":"Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search","created":"2020-05-22","cited_by_count":273},{"id":"2104.11280","title":"Motion Representations for Articulated Animation","created":"2021-04-22","cited_by_count":255},{"id":"1905.03820","title":"Hierarchical Cross-Modal Talking Face Generationwith Dynamic Pixel-Wise Loss","created":"2019-05-09","cited_by_count":252},{"id":"1912.05566","title":"Neural Voice Puppetry: Audio-driven Facial Reenactment","created":"2019-12-11","cited_by_count":250},{"id":"1807.07860","title":"Talking Face Generation by Adversarially Disentangled Audio-Visual Representation","created":"2018-07-20","cited_by_count":212},{"id":"2203.09043","title":"Latent Image Animator: Learning to Animate Images via Latent Space Navigation","created":"2022-03-17","cited_by_count":175},{"id":"1710.00925","title":"Fine-Grained Head Pose Estimation Without Keypoints","created":"2017-10-02","cited_by_count":163},{"id":"2107.09293","title":"Audio2Head: Audio-driven One-shot Talking-head Generation with Natural Head Motion","created":"2021-07-20","cited_by_count":149},{"id":"2309.03199","title":"Matcha-TTS: A fast TTS architecture with conditional flow matching","created":"2023-09-06","cited_by_count":145},{"id":"2004.12000","title":"Neural Head Reenactment with Latent Pose Descriptors","created":"2020-04-24","cited_by_count":106},{"id":"1906.01524","title":"Text-based Editing of Talking-head Video","created":"2019-06-04","cited_by_count":103},{"id":"1705.02966","title":"You said that?","created":"2017-05-08","cited_by_count":99},{"id":"2103.00993","title":"AdaSpeech: Adaptive Text to Speech for Custom Voice","created":"2021-03-01","cited_by_count":98},{"id":"2003.00418","title":"Towards Automatic Face-to-Face Translation","created":"2020-03-01","cited_by_count":96},{"id":"2106.03153","title":"Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation","created":"2021-06-06","cited_by_count":93},{"id":"2211.14506","title":"Progressive Disentangled Representation Learning for Fine-Grained Controllable Talking Head Synthesis","created":"2022-11-26","cited_by_count":93},{"id":"2002.10137","title":"Audio-driven Talking Face Video Generation with Learning-based Personalized Head Pose","created":"2020-02-24","cited_by_count":92},{"id":"2301.01081","title":"StyleTalk: One-shot Talking Head Generation with Controllable Speaking Styles","created":"2023-01-03","cited_by_count":92},{"id":"2112.02749","title":"One-shot Talking Face Generation from Single-speaker Audio-Visual Correlation Learning","created":"2021-12-06","cited_by_count":87},{"id":"1804.04786","title":"Talking Face Generation by Conditional Recurrent Adversarial Network","created":"2018-04-13","cited_by_count":84},{"id":"2001.05201","title":"Everybody's Talkin': Let Me Talk as You Want","created":"2020-01-15","cited_by_count":83},{"id":"2001.04758","title":"Deep Audio-Visual Learning: A Survey","created":"2020-01-14","cited_by_count":69},{"id":"2211.00924","title":"SyncTalkFace: Talking Face Generation with Precise Lip-Syncing via Audio-Lip Memory","created":"2022-11-02","cited_by_count":65},{"id":"1902.09887","title":"Disentangled Representation Learning for 3D Face Shape","created":"2019-02-26","cited_by_count":48},{"id":"1801.01442","title":"ObamaNet: Photo-realistic lip-sync from text","created":"2017-12-06","cited_by_count":42},{"id":"2005.03201","title":"What comprises a good talking-head video generation?: A Survey and Benchmark","created":"2020-05-07","cited_by_count":42},{"id":"2012.07267","title":"Multi-SpectroGAN: High-Diversity and High-Fidelity Spectrogram Generation with Adversarial Style Combination for Speech Synthesis","created":"2020-12-14","cited_by_count":28},{"id":"2104.14631","title":"Text2Video: Text-driven Talking-head Video Synthesis with Personalized Phoneme-Pose Dictionary","created":"2021-04-29","cited_by_count":27},{"id":"2302.13700","title":"Imaginary Voice: Face-styled Diffusion Model for Text-to-Speech","created":"2023-02-27","cited_by_count":27},{"id":"2205.07211","title":"GenerSpeech: Towards Style Transfer for Generalizable Out-Of-Domain Text-to-Speech","created":"2022-05-15","cited_by_count":21},{"id":"2208.10922","title":"StyleTalker: One-shot Style-based Audio-driven Talking Head Video Generation","created":"2022-08-23","cited_by_count":14},{"id":"2204.01672","title":"Residual-guided Personalized Speech Synthesis based on Face Image","created":"2022-04-01","cited_by_count":10},{"id":"2302.14337","title":"UniFLG: Unified Facial Landmark Generator from Text or Speech","created":"2023-02-28","cited_by_count":8},{"id":"2304.03275","title":"That's What I Said: Fully-Controllable Talking Face Generation","created":"2023-04-06","cited_by_count":8},{"id":"2306.03504","title":"Ada-TTA: Towards Adaptive High-Quality Text-to-Talking Avatar Synthesis","created":"2023-06-06","cited_by_count":8},{"id":"2308.06457","title":"Text-to-Video: a Two-stage Framework for Zero-shot Identity-agnostic Talking-head Generation","created":"2023-08-12","cited_by_count":8},{"id":"2107.06831","title":"Parallel and High-Fidelity Text-to-Lip Generation","created":"2021-07-14","cited_by_count":7},{"id":"2303.07697","title":"DisCoHead: Audio-and-Video-Driven Talking Head Generation by Disentangled Control of Head Pose and Facial Expressions","created":"2023-03-14","cited_by_count":7}],"next_cursor":null}