{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"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":"2010.05646","title":"HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis","created":"2020-10-12","cited_by_count":1154},{"id":"1611.04076","title":"Least Squares Generative Adversarial Networks","created":"2016-11-13","cited_by_count":1001},{"id":"1712.05884","title":"Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions","created":"2017-12-16","cited_by_count":804},{"id":"2006.04558","title":"FastSpeech 2: Fast and High-Quality End-to-End Text to Speech","created":"2020-06-08","cited_by_count":717},{"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":"1703.10135","title":"Tacotron: Towards End-to-End Speech Synthesis","created":"2017-03-29","cited_by_count":490},{"id":"1910.06711","title":"MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis","created":"2019-10-08","cited_by_count":354},{"id":"2004.12992","title":"MakeItTalk: Speaker-Aware Talking-Head Animation","created":"2020-04-27","cited_by_count":312},{"id":"2011.13922","title":"A Recurrent Vision-and-Language BERT for Navigation","created":"2020-11-26","cited_by_count":302},{"id":"2201.02184","title":"Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction","created":"2022-01-05","cited_by_count":287},{"id":"1806.04558","title":"Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis","created":"2018-06-12","cited_by_count":282},{"id":"1905.03820","title":"Hierarchical Cross-Modal Talking Face Generationwith Dynamic Pixel-Wise Loss","created":"2019-05-09","cited_by_count":252},{"id":"1611.05358","title":"Lip Reading Sentences in the Wild","created":"2016-11-16","cited_by_count":228},{"id":"1807.07860","title":"Talking Face Generation by Adversarially Disentangled Audio-Visual Representation","created":"2018-07-20","cited_by_count":212},{"id":"2203.04036","title":"StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGAN","created":"2022-03-08","cited_by_count":169},{"id":"1708.05237","title":"S$^3$FD: Single Shot Scale-invariant Face Detector","created":"2017-08-17","cited_by_count":142},{"id":"2203.13161","title":"Learning Hierarchical Cross-Modal Association for Co-Speech Gesture Generation","created":"2022-03-24","cited_by_count":107},{"id":"2001.08702","title":"Lipreading using Temporal Convolutional Networks","created":"2020-01-23","cited_by_count":102},{"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":"1702.07825","title":"Deep Voice: Real-time Neural Text-to-Speech","created":"2017-02-25","cited_by_count":83},{"id":"2001.05201","title":"Everybody's Talkin': Let Me Talk as You Want","created":"2020-01-15","cited_by_count":83},{"id":"1611.01599","title":"LipNet: End-to-End Sentence-level Lipreading","created":"2016-11-05","cited_by_count":80},{"id":"2201.01763","title":"Robust Self-Supervised Audio-Visual Speech Recognition","created":"2022-01-05","cited_by_count":75},{"id":"2005.08209","title":"Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis","created":"2020-05-17","cited_by_count":74},{"id":"1807.07281","title":"ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech","created":"2018-07-19","cited_by_count":70},{"id":"1701.00495","title":"Vid2speech: Speech Reconstruction from Silent Video","created":"2017-01-02","cited_by_count":53},{"id":"2007.06504","title":"Towards Practical Lipreading with Distilled and Efficient Models","created":"2020-07-13","cited_by_count":45},{"id":"1910.10288","title":"Location-Relative Attention Mechanisms For Robust Long-Form Speech Synthesis","created":"2019-10-23","cited_by_count":44},{"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":"2103.16561","title":"Diagnosing Vision-and-Language Navigation: What Really Matters","created":"2021-03-30","cited_by_count":36},{"id":"2205.02058","title":"SVTS: Scalable Video-to-Speech Synthesis","created":"2022-05-04","cited_by_count":35},{"id":"2112.00585","title":"Neural Emotion Director: Speech-preserving semantic control of facial expressions in \"in-the-wild\" videos","created":"2021-12-01","cited_by_count":28},{"id":"2207.12622","title":"Multi-Attention Network for Compressed Video Referring Object Segmentation","created":"2022-07-26","cited_by_count":28},{"id":"1708.01204","title":"Improved Speech Reconstruction from Silent Video","created":"2017-08-01","cited_by_count":26},{"id":"1806.06053","title":"Deep Lip Reading: a comparison of models and an online application","created":"2018-06-15","cited_by_count":26},{"id":"2009.14233","title":"Lip-reading with Densely Connected Temporal Convolutional Networks","created":"2020-09-29","cited_by_count":26},{"id":"2209.01383","title":"Training Strategies for Improved Lip-reading","created":"2022-09-03","cited_by_count":25},{"id":"2111.12890","title":"V2C: Visual Voice Cloning","created":"2021-11-25","cited_by_count":24},{"id":"2201.06260","title":"Towards Realistic Visual Dubbing with Heterogeneous Sources","created":"2022-01-17","cited_by_count":24},{"id":"1907.01367","title":"Lipper: Synthesizing Thy Speech using Multi-View Lipreading","created":"2019-06-28","cited_by_count":19},{"id":"2207.11524","title":"Audio-driven Neural Gesture Reenactment with Video Motion Graphs","created":"2022-07-23","cited_by_count":18},{"id":"2011.03530","title":"Large-scale multilingual audio visual dubbing","created":"2020-11-06","cited_by_count":15},{"id":"2110.03342","title":"VisualTTS: TTS with Accurate Lip-Speech Synchronization for Automatic Voice Over","created":"2021-10-07","cited_by_count":13},{"id":"2111.10139","title":"More than Words: In-the-Wild Visually-Driven Prosody for Text-to-Speech","created":"2021-11-19","cited_by_count":12},{"id":"2207.03800","title":"FastLTS: Non-Autoregressive End-to-End Unconstrained Lip-to-Speech Synthesis","created":"2022-07-08","cited_by_count":8},{"id":"2209.00642","title":"Lip-to-Speech Synthesis for Arbitrary Speakers in the Wild","created":"2022-09-01","cited_by_count":8}],"next_cursor":null}