{"list":"other","total":54,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2006.11477","title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","created":"2020-06-20","cited_by_count":3905},{"id":"2108.12409","title":"Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation","created":"2021-08-27","cited_by_count":1103},{"id":"1912.01865","title":"StarGAN v2: Diverse Image Synthesis for Multiple Domains","created":"2019-12-04","cited_by_count":1098},{"id":"1710.08092","title":"VGGFace2: A dataset for recognising faces across pose and age","created":"2017-10-23","cited_by_count":914},{"id":"1806.05622","title":"VoxCeleb2: Deep Speaker Recognition","created":"2018-06-14","cited_by_count":875},{"id":"2007.08501","title":"Accelerating 3D Deep Learning with PyTorch3D","created":"2020-07-16","cited_by_count":784},{"id":"1706.08612","title":"VoxCeleb: a large-scale speaker identification dataset","created":"2017-06-26","cited_by_count":732},{"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":"1810.02508","title":"MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations","created":"2018-10-05","cited_by_count":643},{"id":"1906.08172","title":"MediaPipe: A Framework for Building Perception Pipelines","created":"2019-06-14","cited_by_count":583},{"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":"1708.03985","title":"AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wild","created":"2017-08-14","cited_by_count":492},{"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":"2012.04012","title":"Learning an Animatable Detailed 3D Face Model from In-The-Wild Images","created":"2020-12-07","cited_by_count":477},{"id":"1809.02108","title":"Deep Audio-Visual Speech Recognition","created":"2018-09-06","cited_by_count":322},{"id":"1809.00496","title":"LRS3-TED: a large-scale dataset for visual speech recognition","created":"2018-09-03","cited_by_count":308},{"id":"1905.08233","title":"Few-Shot Adversarial Learning of Realistic Neural Talking Head Models","created":"2019-05-20","cited_by_count":284},{"id":"1909.01815","title":"3D Morphable Face Models -- Past, Present and Future","created":"2019-09-03","cited_by_count":270},{"id":"1905.03079","title":"Capture, Learning, and Synthesis of 3D Speaking Styles","created":"2019-05-08","cited_by_count":259},{"id":"2204.11312","title":"EMOCA: Emotion Driven Monocular Face Capture and Animation","created":"2022-04-24","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":"2207.12393","title":"CelebV-HQ: A Large-Scale Video Facial Attributes Dataset","created":"2022-07-25","cited_by_count":250},{"id":"2112.05329","title":"FaceFormer: Speech-Driven 3D Facial Animation with Transformers","created":"2021-12-10","cited_by_count":209},{"id":"2003.13989","title":"FaceScape: a Large-scale High Quality 3D Face Dataset and Detailed Riggable 3D Face Prediction","created":"2020-03-31","cited_by_count":196},{"id":"1606.06259","title":"MOSI: Multimodal Corpus of Sentiment Intensity and Subjectivity Analysis in Online Opinion Videos","created":"2016-06-20","cited_by_count":194},{"id":"2104.08223","title":"MeshTalk: 3D Face Animation from Speech using Cross-Modality Disentanglement","created":"2021-04-16","cited_by_count":190},{"id":"2301.02379","title":"CodeTalker: Speech-Driven 3D Facial Animation with Discrete Motion Prior","created":"2023-01-06","cited_by_count":184},{"id":"2104.07452","title":"Audio-Driven Emotional Video Portraits","created":"2021-04-15","cited_by_count":180},{"id":"1905.06817","title":"Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision","created":"2019-05-16","cited_by_count":176},{"id":"2204.06607","title":"Towards Metrical Reconstruction of Human Faces","created":"2022-04-13","cited_by_count":166},{"id":"1703.10580","title":"MoFA: Model-based Deep Convolutional Face Autoencoder for Unsupervised Monocular Reconstruction","created":"2017-03-30","cited_by_count":163},{"id":"2303.11089","title":"EmoTalk: Speech-Driven Emotional Disentanglement for 3D Face Animation","created":"2023-03-20","cited_by_count":142},{"id":"2204.08451","title":"Learning to Listen: Modeling Non-Deterministic Dyadic Facial Motion","created":"2022-04-18","cited_by_count":126},{"id":"1803.09179","title":"FaceForensics: A Large-scale Video Dataset for Forgery Detection in Human Faces","created":"2018-03-24","cited_by_count":119},{"id":"2211.14758","title":"VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild","created":"2022-11-27","cited_by_count":106},{"id":"1806.06098","title":"Unsupervised Training for 3D Morphable Model Regression","created":"2018-06-15","cited_by_count":100},{"id":"1712.02859","title":"Self-supervised Multi-level Face Model Learning for Monocular Reconstruction at over 250 Hz","created":"2017-12-07","cited_by_count":91},{"id":"2207.11243","title":"Multiface: A Dataset for Neural Face Rendering","created":"2022-07-22","cited_by_count":87},{"id":"1812.07603","title":"FML: Face Model Learning from Videos","created":"2018-12-18","cited_by_count":78},{"id":"2007.12494","title":"Self-Supervised Monocular 3D Face Reconstruction by Occlusion-Aware Multi-view Geometry Consistency","created":"2020-07-24","cited_by_count":78},{"id":"2301.00023","title":"Imitator: Personalized Speech-driven 3D Facial Animation","created":"2022-12-30","cited_by_count":74},{"id":"1805.09488","title":"VisemeNet: Audio-Driven Animator-Centric Speech Animation","created":"2018-05-24","cited_by_count":63},{"id":"1904.01909","title":"ICface: Interpretable and Controllable Face Reenactment Using GANs","created":"2019-04-03","cited_by_count":50},{"id":"2207.11094","title":"Visual Speech-Aware Perceptual 3D Facial Expression Reconstruction from Videos","created":"2022-07-22","cited_by_count":50},{"id":"1709.03842","title":"ExprGAN: Facial Expression Editing with Controllable Expression Intensity","created":"2017-09-12","cited_by_count":47},{"id":"1909.02518","title":"Neural Style-Preserving Visual Dubbing","created":"2019-09-05","cited_by_count":47},{"id":"2011.04439","title":"FACEGAN: Facial Attribute Controllable rEenactment GAN","created":"2020-11-09","cited_by_count":32},{"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":"2006.12210","title":"Facial Expression Editing with Continuous Emotion Labels","created":"2020-06-22","cited_by_count":6},{"id":"1710.00920","title":"End-to-end Learning for 3D Facial Animation from Raw Waveforms of Speech","created":"2017-10-02","cited_by_count":4}],"next_cursor":null}