{"list":"other","total":59,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"1603.08155","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","created":"2016-03-27","cited_by_count":2694},{"id":"1605.08803","title":"Density estimation using Real NVP","created":"2016-05-27","cited_by_count":2042},{"id":"1911.00172","title":"Generalization through Memorization: Nearest Neighbor Language Models","created":"2019-11-01","cited_by_count":800},{"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":"2012.03065","title":"Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstruction","created":"2020-12-05","cited_by_count":467},{"id":"1512.02595","title":"Deep Speech 2: End-to-End Speech Recognition in English and Mandarin","created":"2015-12-08","cited_by_count":451},{"id":"1410.3916","title":"Memory Networks","created":"2014-10-15","cited_by_count":363},{"id":"1412.5567","title":"Deep Speech: Scaling up end-to-end speech recognition","created":"2014-12-17","cited_by_count":354},{"id":"2103.11078","title":"AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesis","created":"2021-03-20","cited_by_count":339},{"id":"2104.11116","title":"Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation","created":"2021-04-22","cited_by_count":288},{"id":"2112.02418","title":"YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone","created":"2021-12-04","cited_by_count":278},{"id":"1805.11714","title":"Deep Video Portraits","created":"2018-05-29","cited_by_count":267},{"id":"1905.03079","title":"Capture, Learning, and Synthesis of 3D Speaking Styles","created":"2019-05-08","cited_by_count":259},{"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":"1606.03126","title":"Key-Value Memory Networks for Directly Reading Documents","created":"2016-06-09","cited_by_count":223},{"id":"2010.00710","title":"Nearest Neighbor Machine Translation","created":"2020-10-01","cited_by_count":209},{"id":"2109.15102","title":"Fake It Till You Make It: Face analysis in the wild using synthetic data alone","created":"2021-09-30","cited_by_count":200},{"id":"2109.05923","title":"Low-Light Image Enhancement with Normalizing Flow","created":"2021-09-13","cited_by_count":185},{"id":"2104.07452","title":"Audio-Driven Emotional Video Portraits","created":"2021-04-15","cited_by_count":180},{"id":"2203.06605","title":"Depth-Aware Generative Adversarial Network for Talking Head Video Generation","created":"2022-03-13","cited_by_count":178},{"id":"2205.04421","title":"NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Quality","created":"2022-05-09","cited_by_count":152},{"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":"2204.02849","title":"KNN-Diffusion: Image Generation via Large-Scale Retrieval","created":"2022-04-06","cited_by_count":137},{"id":"2201.07786","title":"Semantic-Aware Implicit Neural Audio-Driven Video Portrait Generation","created":"2022-01-19","cited_by_count":119},{"id":"1506.07285","title":"Ask Me Anything: Dynamic Memory Networks for Natural Language Processing","created":"2015-06-24","cited_by_count":117},{"id":"2007.08547","title":"Talking-head Generation with Rhythmic Head Motion","created":"2020-07-16","cited_by_count":112},{"id":"2108.06720","title":"Audio2Gestures: Generating Diverse Gestures from Speech Audio with Conditional Variational Autoencoders","created":"2021-08-15","cited_by_count":109},{"id":"2202.11233","title":"Retrieval Augmented Classification for Long-Tail Visual Recognition","created":"2022-02-22","cited_by_count":106},{"id":"2207.11770","title":"Learning Dynamic Facial Radiance Fields for Few-Shot Talking Head Synthesis","created":"2022-07-24","cited_by_count":97},{"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":"2108.07938","title":"FACIAL: Synthesizing Dynamic Talking Face with Implicit Attribute Learning","created":"2021-08-18","cited_by_count":90},{"id":"2211.12368","title":"Real-time Neural Radiance Talking Portrait Synthesis via Audio-spatial Decomposition","created":"2022-11-22","cited_by_count":81},{"id":"2106.04185","title":"LipSync3D: Data-Efficient Learning of Personalized 3D Talking Faces from Video using Pose and Lighting Normalization","created":"2021-06-08","cited_by_count":67},{"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":"2108.08020","title":"Speech Drives Templates: Co-Speech Gesture Synthesis with Learned Templates","created":"2021-08-18","cited_by_count":58},{"id":"2111.00203","title":"Imitating Arbitrary Talking Style for Realistic Audio-DrivenTalking Face Synthesis","created":"2021-10-30","cited_by_count":56},{"id":"2212.04248","title":"Talking Head Generation with Probabilistic Audio-to-Visual Diffusion Priors","created":"2022-12-07","cited_by_count":55},{"id":"2004.02711","title":"A Morphable Face Albedo Model","created":"2020-04-06","cited_by_count":54},{"id":"2104.07995","title":"Write-a-speaker: Text-based Emotional and Rhythmic Talking-head Generation","created":"2021-04-16","cited_by_count":47},{"id":"2204.00436","title":"AdaSpeech 4: Adaptive Text to Speech in Zero-Shot Scenarios","created":"2022-04-01","cited_by_count":41},{"id":"2203.02573","title":"Show Me What and Tell Me How: Video Synthesis via Multimodal Conditioning","created":"2022-03-04","cited_by_count":37},{"id":"2007.08513","title":"RetrieveGAN: Image Synthesis via Differentiable Patch Retrieval","created":"2020-07-16","cited_by_count":35},{"id":"2104.14557","title":"Learned Spatial Representations for Few-shot Talking-Head Synthesis","created":"2021-04-29","cited_by_count":32},{"id":"1805.02838","title":"A Memory Network Approach for Story-based Temporal Summarization of 360{\\deg} Videos","created":"2018-05-08","cited_by_count":29},{"id":"2104.00024","title":"RetrievalFuse: Neural 3D Scene Reconstruction with a Database","created":"2021-03-31","cited_by_count":28},{"id":"2009.07047","title":"Old Photo Restoration via Deep Latent Space Translation","created":"2020-09-14","cited_by_count":27},{"id":"2002.01048","title":"Multi-Channel Attention Selection GANs for Guided Image-to-Image Translation","created":"2020-02-03","cited_by_count":23},{"id":"2009.05784","title":"DualLip: A System for Joint Lip Reading and Generation","created":"2020-09-12","cited_by_count":10},{"id":"2111.09771","title":"Transformer-S2A: Robust and Efficient Speech-to-Animation","created":"2021-11-18","cited_by_count":10},{"id":"2208.13717","title":"StableFace: Analyzing and Improving Motion Stability for Talking Face Generation","created":"2022-08-29","cited_by_count":9},{"id":"1811.11979","title":"Unsupervised Image-to-Image Translation Using Domain-Specific Variational Information Bound","created":"2018-11-29","cited_by_count":7},{"id":"1909.04110","title":"One-to-one Mapping for Unpaired Image-to-image Translation","created":"2019-09-09","cited_by_count":7}],"next_cursor":null}